JP7560280B2 - Medical image processing device, medical image processing system, and medical image processing method - Google Patents

Description

The embodiments disclosed in this specification relate to a medical image processing device, a medical image processing system, and a medical image processing method.

Patients often visit hospitals because they have some symptoms. In addition, hospitals collect medical images depending on the reason for the patient's visit, and diagnoses are made using the collected medical images. For example, if a patient visits a hospital complaining of shoulder pain, X-ray images are collected of the area including the shoulder, and the doctor refers to the X-ray images to check for any abnormalities in the patient's shoulder joint.

Special Publication No. 2006-511882 Patent No. 4799251 specification Patent No. 6275876 specification

One of the problems that the embodiments disclosed in this specification etc. aim to solve is to make more effective use of collected medical images. However, the problems solved by the embodiments disclosed in this specification etc. are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems solved by the embodiments disclosed in this specification etc.

The medical image processing device of the embodiment includes a diagnostic support unit and a notification unit. The diagnostic support unit executes diagnostic support processing according to a second diagnostic purpose different from the first diagnostic purpose based on a first diagnostic purpose in a first examination and medical images collected in the first examination. The notification unit notifies at least one of the patient who was the subject of the first examination and the user who executed the first examination of the results of the diagnostic support processing.

FIG. 1 is a block diagram showing an example of the configuration of a medical image processing system according to the first embodiment. FIG. 2 is a block diagram showing an example of the configuration of the X-ray diagnostic apparatus according to the first embodiment. FIG. 3 is a schematic diagram showing a series of processes according to the first embodiment. FIG. 4A is a diagram for explaining a process for generating a trained model according to the first embodiment. FIG. 4B is a diagram for explaining the process of generating a trained model according to the first embodiment. FIG. 5 is a flowchart for explaining a series of processing steps performed by the X-ray diagnostic apparatus and medical image processing apparatus according to the first embodiment.

Below, embodiments of a medical image processing device, a medical image processing system, and a medical image processing method will be described in detail with reference to the drawings.

First Embodiment
In the first embodiment, a medical image processing system 1 including a medical image processing device 30 will be described as an example. For example, as shown in Fig. 1, the medical image processing system 1 includes a medical image diagnostic device 10 and a medical image processing device 30. The medical image diagnostic device 10 and the medical image processing device 30 are connected via a network NW. Fig. 1 is a block diagram showing an example of the configuration of the medical image processing system 1 according to the first embodiment.

The medical image diagnostic device 10 is a device that collects medical images from a patient P1. For example, the medical image diagnostic device 10 is an X-ray diagnostic device, an X-ray CT (Computed Tomography) device, an ultrasound diagnostic device, a Magnetic Resonance Imaging (MRI) device, a SPECT (Single Photon Emission Computed Tomography) device, a PET (Positron Emission Computed Tomography) device, etc. Note that although one medical image diagnostic device 10 is shown in FIG. 1, the medical image processing system 1 may include multiple medical image diagnostic devices 10.

The medical image processing device 30 performs various processes based on the medical images collected by the medical image diagnostic device 10. For example, as shown in FIG. 1, the medical image processing device 30 has an input interface 31, a display 32, a memory 33, and a processing circuit 34.

The input interface 31 accepts various input operations from the user, converts the accepted input operations into electrical signals, and outputs the electrical signals to the processing circuitry 34. For example, the input interface 31 is realized by a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad that performs input operations by touching the operation surface, a touch screen that integrates a display screen and a touchpad, a non-contact input circuit using an optical sensor, a voice input circuit, and the like. The input interface 31 may be configured as a tablet terminal or the like that can wirelessly communicate with the main body of the medical image processing device 30. In addition, the input interface 31 is not limited to only those that have physical operating parts such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the medical image processing device 30 and outputs the electrical signal to the processing circuitry 34 is also included as an example of the input interface 31.

The display 32 displays various information. For example, the display 32 displays the results of the diagnostic support process described below. Also, for example, the display 32 displays a GUI (Graphical User Interface) for receiving various instructions and settings from the user via the input interface 31. For example, the display 32 is a liquid crystal display or a CRT (Cathode Ray Tube) display. The display 32 may be a desktop type, or may be configured as a tablet terminal or the like capable of wireless communication with the medical image processing device 30 main body.

The memory 33 is realized, for example, by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, a hard disk, an optical disk, etc. For example, the memory 33 stores a program for the circuits included in the medical image processing device 30 to realize their functions. The memory 33 also stores various images acquired from the medical image diagnostic device 10. The memory 33 may also be realized by a group of servers (cloud) connected to the medical image processing device 30 via a network NW.

The processing circuitry 34 controls the operation of the entire medical image processing device 30 by executing the control function 34a, the diagnosis support function 34b, the notification function 34c, and the display control function 34d. Here, the diagnosis support function 34b is an example of a diagnosis support unit. The notification function 34c is an example of a notification unit. The display control function 34d is an example of a display control unit.

For example, the processing circuitry 34 reads out a program corresponding to the control function 34a from the memory 33 and executes it to control various functions such as the diagnostic support function 34b, the notification function 34c, and the display control function 34d based on various input operations received from the user via the input interface 31. In addition, the control function 34a controls the transmission and reception of data via the network NW.

For example, the processing circuitry 34 reads out from the memory 33 a program corresponding to the diagnostic support function 34b and executes it to perform diagnostic support processing using medical images collected by the medical image diagnostic device 10. For example, the processing circuitry 34 reads out from the memory 33 a program corresponding to the notification function 34c and executes it to notify the result of the diagnostic support processing by the diagnostic support function 34b. For example, the processing circuitry 34 reads out from the memory 33 a program corresponding to the display control function 34d and executes it to display the result of the diagnostic support processing by the diagnostic support function 34b on the display 32. Note that the processing by the diagnostic support function 34b, the notification function 34c, and the display control function 34d will be described later.

Next, an X-ray diagnostic apparatus 110 shown in FIG. 2 will be described as an example of a medical image diagnostic apparatus 10. FIG. 2 is a block diagram showing an example of the configuration of the X-ray diagnostic apparatus 110 according to the first embodiment. For example, the X-ray diagnostic apparatus 110 includes an X-ray high voltage device 111, an X-ray tube 112, an X-ray aperture 113, an X-ray detector 114, an input interface 115, a display 116, a memory 117, and a processing circuit 118.

The X-ray high voltage device 111 supplies a high voltage to the X-ray tube 112 under the control of the processing circuit 118. For example, the X-ray high voltage device 111 has electrical circuits such as a transformer and a rectifier, and includes a high voltage generator that generates a high voltage to be applied to the X-ray tube 112, and an X-ray control device that controls the output voltage according to the X-rays emitted by the X-ray tube 112. The high voltage generator may be of a transformer type or an inverter type.

The X-ray tube 112 is a vacuum tube that has a cathode (filament) that generates thermoelectrons and an anode (target) that generates X-rays when struck by the thermoelectrons. The X-ray tube 112 generates X-rays by irradiating thermoelectrons from the cathode to the anode using a high voltage supplied from the X-ray high voltage device 111.

The X-ray aperture 113 has a collimator that narrows the X-ray irradiation range and a filter that adjusts the X-rays. For example, the collimator has four slidable aperture blades, and by sliding these aperture blades, the X-rays generated by the X-ray tube 112 are narrowed down and irradiated to the patient P1. Here, the aperture blades are plate-shaped members made of lead or the like, and are provided near the X-ray irradiation port of the X-ray tube 112 to adjust the X-ray irradiation range. In addition, the filter changes the radiation quality of the transmitted X-rays depending on its material and thickness, with the aim of reducing the radiation dose to the patient P1 and improving the image quality of the X-ray image, reducing soft ray components that are easily absorbed by the patient P1 and reducing high energy components that cause a decrease in the contrast of the X-ray image. In addition, the filter changes the dose and irradiation range of the X-rays depending on its material, thickness, position, etc., and attenuates the X-rays so that the X-rays irradiated to the patient P1 have a predetermined distribution.

For example, the X-ray aperture 113 has a driving mechanism such as a motor and an actuator, and controls the irradiation of X-rays by operating the driving mechanism under the control of the processing circuit 118 described below. For example, the X-ray aperture 113 applies a driving voltage to the driving mechanism in response to a control signal received from the processing circuit 118, thereby adjusting the opening of the aperture blades of the collimator and controlling the irradiation range of the X-rays irradiated to the patient P1. Also, for example, the X-ray aperture 113 applies a driving voltage to the driving mechanism in response to a control signal received from the processing circuit 118, thereby adjusting the position of the filter, thereby controlling the distribution of the X-ray dose irradiated to the patient P1.

The X-ray detector 114 is, for example, an X-ray flat panel detector (FPD) having detection elements arranged in a matrix. The X-ray detector 114 detects X-rays emitted from the X-ray tube 112 and transmitted through the patient P1, and outputs a detection signal corresponding to the detected X-ray amount to the processing circuit 118. The X-ray detector 114 may be an indirect conversion type detector having a grid, a scintillator array, and a photosensor array, or may be a direct conversion type detector having a semiconductor element that converts the incident X-rays into an electrical signal.

The input interface 115 receives various input operations from the operator, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 118. For example, the input interface 115 is realized by a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad that performs input operations by touching the operation surface, a touch screen that integrates a display screen and a touchpad, a non-contact input circuit using an optical sensor, a voice input circuit, and the like. The input interface 115 may be configured as a tablet terminal or the like that can wirelessly communicate with the processing circuit 118. The input interface 115 is not limited to only those that have physical operating parts such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the X-ray diagnostic apparatus 110 and outputs the electrical signal to the processing circuit 118 is also included as an example of the input interface 115.

The display 116 displays various types of information. For example, the display 116 displays X-ray images and the results of the diagnostic support processing described below. In addition, for example, the display 116 displays a GUI for accepting user instructions under the control of the processing circuitry 118. For example, the display 116 is a liquid crystal display or a CRT display. The display 116 may be a desktop type, or may be configured as a tablet terminal or the like capable of wireless communication with the processing circuitry 118.

The memory 117 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, a hard disk, an optical disk, or the like. For example, the memory 117 accepts and stores X-ray images collected by the processing circuitry 118. The memory 117 also stores programs corresponding to various functions that are read and executed by the processing circuitry 118. The memory 117 may also be realized by a group of servers (cloud) connected to the X-ray diagnostic apparatus 110 via a network.

The processing circuitry 118 controls the operation of the entire X-ray diagnostic apparatus 110 by executing the control function 118a, the collection function 118b, the diagnostic support function 118c, and the display control function 118d. For example, the processing circuitry 118 reads out a program corresponding to the control function 118a from the memory 117 and executes it to control various functions such as the collection function 118b, the diagnostic support function 118c, and the display control function 118d based on various input operations received from the user via the input interface 115. In addition, the control function 118a controls the transmission and reception of data via the network NW.

For example, the processing circuit 118 reads out a program corresponding to the collection function 118b from the memory 117 and executes it to collect an X-ray image from the patient P1. For example, the collection function 118b controls the X-ray high voltage device 111 and adjusts the voltage supplied to the X-ray tube 112 to control the amount of X-rays irradiated from the X-ray tube 112 to the patient P1 and on/off. The collection function 118b also controls the operation of the X-ray aperture 113 and adjusts the opening of the aperture blades of the collimator to control the irradiation range of the X-rays irradiated to the patient P1. The collection function 118b also controls the operation of the X-ray aperture 113 and adjusts the position of the filter to control the distribution of the X-ray dose. The collection function 118b also generates an X-ray image based on a detection signal received from the X-ray detector 114 and stores the generated X-ray image in the memory 117. The collection function 118b may perform various image processing on the generated X-ray image. For example, the collection function 118b performs noise reduction processing and scattered radiation correction using an image processing filter on the generated X-ray image.

For example, the processing circuitry 118 reads out a program corresponding to the diagnostic support function 118c from the memory 117 and executes it to perform diagnostic support processing using X-ray images. For example, the processing circuitry 118 reads out a program corresponding to the display control function 118d from the memory 117 and executes it to display the results of the diagnostic support processing by the diagnostic support function 118c on the display 116.

An example of the medical image processing system 1 has been described above. With this configuration, the processing circuitry 34 in the medical image processing device 30 makes it possible to more effectively utilize the collected medical images.

An example of the collection and use of medical images will be described below with reference to FIG. 3. FIG. 3 is a schematic diagram showing a series of processes according to the first embodiment. In FIG. 3, a case will be described in which a patient P1 comes to the hospital complaining of shoulder pain, as shown in step S1.

When patient P1 visits the hospital, a first examination is first performed. For example, if patient P1 complains of shoulder pain, a diagnosis based on the reason for the visit is made in the orthopedic department, as shown in step S2.

Specifically, when patient P1 visits an orthopedic surgeon, a user such as a doctor interviews patient P1 about his or her symptoms. If the user determines that an X-ray image is necessary for diagnosis, the user uses X-ray diagnostic device 110 to collect an X-ray image including the shoulder of patient P1. For example, collection function 118b performs a chest X-ray on patient P1 based on an input operation received from the user via input interface 115, and collects X-ray image I1.

Next, the diagnostic support function 118c executes diagnostic support processing based on the X-ray image I1. For example, the diagnostic support function 118c adjusts the window level and window width in the X-ray image I1 to make it easier to observe the shoulder joint, and generates an X-ray image I11. In addition, for example, the diagnostic support function 118c executes computer-aided diagnosis (CAD) processing on the X-ray image I11, and generates an X-ray image I111 in which markers are added to areas in the X-ray image I11 where lesions such as fractures are suspected.

Next, the display control function 118d displays the results of the diagnostic support processing by the diagnostic support function 118c on the display 116. For example, the display control function 118d displays X-ray images such as X-ray image I11 and X-ray image I111 on the display 116. Note that the diagnostic support processing by the diagnostic support function 118c may be omitted. In this case, the display control function 118d displays the collected X-ray image I1 on the display 116. The user can then refer to the X-ray image displayed on the display 116 to check whether or not there is a lesion in the shoulder joint of the patient P1 and make a diagnosis.

The collected X-ray image I1 is generally discarded after being stored for a certain period of time in the memory 117 or an external device. In other words, the collected X-ray image I1 is appropriately discarded after being used for diagnostic purposes in an examination performed according to the reason for the patient P1's visit to the hospital. In contrast, the medical image processing device 30 further performs various types of processing using the collected X-ray image I1 to make more effective use of the X-ray image I1.

Hereinafter, the diagnostic purpose of the first examination will also be referred to as the first diagnostic purpose. For example, in the case shown in FIG. 3, the first diagnostic purpose is to identify a lesion in the shoulder joint that is causing shoulder pain. A diagnostic purpose different from the first diagnostic purpose will also be referred to as the second diagnostic purpose. In other words, the medical image processing device 30 makes more effective use of the X-ray image I1 by using it for the second diagnostic purpose in addition to the first diagnostic purpose.

Specifically, the control function 118a in the X-ray diagnostic device 110 transmits the X-ray image I1 to the medical image processing device 30 via the network NW, as shown in step S3 in FIG. 3. Here, the network NW may be configured as a local network closed within the hospital, or may be a network via the Internet. In other words, the X-ray diagnostic device 110 and the medical image processing device 30 may be installed in the same facility or in different facilities.

Next, as shown in step S4 of FIG. 3, a diagnosis different from the reason for the visit is made. For example, as described above, a diagnosis to identify a lesion in the shoulder joint has already been made based on the X-ray image I1. However, the X-ray image I1 may contain lesions other than the shoulder joint. For example, the X-ray image I1 collected by a chest X-ray examination includes the lungs in addition to the shoulder joint, and lesions such as lung cancer, pulmonary tuberculosis, and pneumothorax may appear. Therefore, the medical image processing device 30 executes a diagnostic support process to determine the presence or absence of lung cancer, etc. Note that "determining the presence or absence of lung cancer," "determining the presence or absence of pulmonary tuberculosis," and "determining the presence or absence of pneumothorax" are examples of the second diagnostic purpose.

For example, the diagnostic support function 34b first acquires a CAD corresponding to the second diagnostic purpose. For example, the diagnostic support function 34b extracts a CAD that can be applied to a chest X-ray image from among the multiple CADs stored in the memory 33. In addition, the diagnostic support function 34b excludes, from the extracted CADs, a CAD that has already been used for the X-ray image I1. In other words, the diagnostic support function 34b excludes, from the extracted CADs, a CAD corresponding to the first diagnostic purpose. In the following, as an example, a case will be described in which CADc1 for determining the presence or absence of lung cancer, CADc2 for determining the presence or absence of pulmonary tuberculosis, and CADc3 for determining the presence or absence of pneumothorax are extracted.

The diagnostic support process by the diagnostic support function 34b may be performed using machine learning techniques. This will be described later.

Next, the diagnostic support function 34b performs image processing on the X-ray image I1 to generate an X-ray image I12, and applies CADc1 to the generated X-ray image I12. For example, the diagnostic support function 34b adjusts the window value and window width in the X-ray image I1 so that the lungs are easily observed, and generates the X-ray image I12. For example, the diagnostic support function 34b adjusts the window value and window width in the X-ray image I1 so that the lungs are easily observed, and generates the X-ray image I12 by performing a process to remove bones from the X-ray image I1. Then, the diagnostic support function 34b executes CAD processing using the X-ray image I12 and CADc1. Similarly, the diagnostic support function 34b performs image processing on the X-ray image I1 to generate an X-ray image I13, and applies CADc2 to the generated X-ray image I13. Similarly, the diagnostic support function 34b performs image processing on the X-ray image I1 to generate an X-ray image I14, and applies CADc3 to the generated X-ray image I14.

Next, the notification function 34c notifies the result of the diagnostic support processing by the diagnostic support function 34b. For example, as shown in step S5 of FIG. 3, the notification function 34c generates a report R1 based on the result of the diagnostic support processing by the diagnostic support function 34b, and feeds back the generated report R1 to the patient P1.

As an example, the notification function 34c generates a report R1 stating that there is a suspicion of lung cancer, as shown in FIG. 3. Here, in the report R1, the suspicion of lung cancer may be displayed in text or in an image. As an example, the notification function 34c generates an X-ray image I121 in which a marker is added to an area suspected of being lung cancer in the X-ray image I12 based on the results of CAD processing using CADc1, and generates a report R1 including the X-ray image I121.

The notification function 34c may also receive consultation from the user of the medical image processing device 30 regarding the results of the diagnostic support processing by the diagnostic support function 34b. For example, the display control function 34d first displays the results of the diagnostic support processing by the diagnostic support function 34b on the display 32. As an example, the display control function 34d displays an X-ray image I121 with a marker added to an area suspected of lung cancer on the display 32. Here, the user considers whether the marker in the X-ray image I121 is appropriate, and if the marker is not appropriate, performs an input operation to correct the marker in the X-ray image I121. Alternatively, if the marker is appropriate, performs an input operation to add information that the marker is determined to be appropriate. Then, the notification function 34c generates a report R1 in response to the input operation received from the user.

The user of the medical image processing device 30 may be the same as the user of the X-ray diagnostic device 110, or may be a different person. In other words, the user who performed the diagnosis in step S2 and the user who consults on the results of the diagnostic support processing by the diagnostic support function 34b may be the same as or different from each other.

The notification function 34c may notify the results of the diagnostic support process by digital or analog means. For example, the notification function 34c may notify the patient P1 of the report R1 via email or an application installed on a terminal carried by the patient P1. Alternatively, the notification function 34c may notify the patient P1 of the report R1 by sending a printed copy of the report R1 to the patient P1's home or workplace.

The notification function 34c may also notify a person other than the patient P1 of the results of the diagnostic assistance process. For example, the notification function 34c may notify the user who performed the first test of the report R1. Here, the user can refer to the report R1 and determine whether or not to inform the patient P1 of the contents of the report R1. Generally, the hospital where the first test was performed has the contact information for the patient P1, and the user can contact the patient P1 as appropriate.

Patient P1 who has been notified of the results of the diagnostic support process can undergo additional examinations depending on the results of the diagnostic support process. Hereinafter, the examination performed on patient P1 based on the results of the diagnostic support process will also be referred to as the second examination. For example, patient P1 who has seen report R1 indicating that he or she is suspected of having lung cancer can visit a respiratory department and undergo a second examination, as shown in step S6 of FIG. 3. Note that the orthopedics department visited in step S1 and the respiratory department visited in step S6 may be the same hospital or different hospitals.

When notifying the patient P1 of the results of the diagnostic support process, the notification function 34c may further create a list of hospitals that are recommended for the patient P1 to visit, and notify the patient P1 of the created list. For example, based on the report R1 indicating that lung cancer is suspected, the notification function 34c creates a list of hospitals that can perform tests related to lung cancer, and notifies the patient P1 of the list. The notification function 34c may include the list in the report R1. This allows the patient P1 to easily determine which hospital to select to undergo the second test.

Here, the notification function 34c can give priority to including local hospitals in the list. For example, the notification function 34c gives priority to adding hospitals that are easy for patient P1 to visit to the list based on information such as the address and place of work of patient P1. Furthermore, the hospital where the first examination was performed is often an easy hospital for patient P1 to visit because patient P1 has visited the hospital at least once, and nearby hospitals are also often easy for patient P1 to visit. Therefore, the notification function 34c may give priority to including hospitals near the hospital where the first examination was performed in the list. Furthermore, the notification function 34c may assign priorities to hospitals in the list based on the treatment records for lung cancer.

The notification function 34c may also create a list of doctors recommended for patient P1 to see, and notify patient P1 of the created list. For example, the notification function 34c creates a list of lung cancer specialists in response to report R1 indicating a suspicion of lung cancer. Here, the notification function 34c may preferentially include doctors working at local hospitals in the list. The notification function 34c may also prioritize the doctors in the list based on their track record of treating lung cancer.

The notification function 34c may also identify a hospital or doctor that is recommended for patient P1 to visit, depending on the results of the diagnostic support process, and schedule a consultation for patient P1 with the identified hospital or doctor. That is, the notification function 34c may schedule a second examination. The reservation process by the notification function 34c may be performed only when requested by patient P1, or may be performed automatically. In this way, the notification function 34c can simplify various procedures leading up to the execution of the second examination.

As shown in step S7 of FIG. 3, in the second examination, a diagnosis is made according to report R1. For example, if report R1 indicates that lung cancer is suspected, a detailed lung examination is performed as the second examination. As an example, in the second examination, image diagnosis using X-ray CT images of patient P1's lungs and pathological diagnosis such as cytology are performed, and a definitive diagnosis is made by a doctor. The detailed examination results from such a second examination allow patient P1 to detect any lesions early. In addition, when performing the second examination, the doctor can refer to report R1, which reduces the burden of explanations from patient P1 to the doctor.

Next, a case where the diagnostic support process by the diagnostic support function 34b is performed using a machine learning technique will be described with reference to FIG. 4A. FIG. 4A is a diagram for explaining the process of generating a trained model according to the first embodiment. Note that in FIG. 4A, the trained model will be described as being configured by a neural network.

When the diagnostic support processing by the diagnostic support function 34b is performed using a machine learning technique, the hospital that performed the second examination transmits the detailed examination results to the medical image processing device 30, as shown in step S8 of FIG. 3. The medical image processing device 30 also acquires the results of the second examination and uses them as learning data.

For example, the diagnostic support function 34b acquires from the memory 33 a trained model M1 that is functionalized to receive input of an X-ray image and output the results of CAD processing. The trained model M1 may be generated by the diagnostic support function 34b using a method described below, or may be generated by an external device.

Next, as shown in FIG. 4A, the diagnostic assistance function 34b inputs the X-ray image I1 collected from the patient P1 in the first examination to the trained model M1 (neural network). The trained model M1 outputs the diagnosis result. For example, the trained model M1 performs image processing on the X-ray image I1 to generate a processed image, performs CAD processing on the processed image, and outputs the CAD processing result. As an example, the trained model M1 performs CAD processing equivalent to the above-mentioned CADc1, CADc2, and CADc3, and outputs the result.

Next, the notification function 34c notifies the patient P1 of the results of the diagnostic support process (diagnosis result). Next, a second examination is performed on the patient P1 based on the diagnosis result, and the detailed examination result is sent to the medical image processing device 30. Then, the diagnostic support function 34b executes a generation process of the trained model M1 based on the X-ray image I1 and the detailed examination result. In other words, the diagnostic support function 34b updates the trained model M1 as shown in FIG. 4A.

Here, a neural network is a network that has a structure in which adjacent layers are arranged in layers and are connected, and information propagates from the input layer side to the output layer side. For example, the diagnostic support function 34b generates a trained model M1 by performing deep learning on a multi-layered neural network using the above-mentioned learning data. Note that the multi-layered neural network is composed of, for example, an input layer, multiple intermediate layers (hidden layers), and an output layer.

As an example, the diagnostic support function 34b first generates a learning dataset including X-ray image I1 and detailed examination results for patient P1. Note that while only patient P1 has been described so far, the diagnostic support function 34b can collect learning data from multiple patients, including patient P1, and generate a learning dataset including many sets of X-ray images and detailed examination results.

Next, the diagnosis support function 34b inputs the X-ray image as input data to the neural network. Here, in the neural network, information propagates in one direction from the input layer side to the output layer side while connecting only between adjacent layers, and the output layer outputs the results of CAD processing based on the input X-ray image. For example, when an X-ray image I1 is input, a processed image is generated from the X-ray image I1 in the neural network, and various CAD processing is performed on the processed image. Note that a neural network in which information propagates in one direction from the input layer side to the output layer side is also called a convolutional neural network (CNN).

The diagnostic support function 34b generates a trained model M1 by adjusting the parameters of the neural network so that the neural network can output favorable results when input data is input. For example, the diagnostic support function 34b compares the CAD processing results output from the neural network with the detailed inspection results (results of the second inspection), and repeats the process while adjusting the parameters of the neural network until the difference between them falls below a threshold. This allows the diagnostic support function 34b to generate a trained model M1 that is functionalized to accept input of an X-ray image and output the results of CAD processing. The diagnostic support function 34b also stores the generated trained model M1 in the memory 33.

As described above, the diagnostic assistance function 34b executes the diagnostic assistance process using the trained model M1, and can also perform the generation process of the trained model M1. Therefore, the diagnostic assistance function 34b can update the trained model M1 each time a patient visits the hospital and the first and second examinations are performed, gradually improving the accuracy of the diagnostic assistance process.

Up to this point, the description has been given of performing image processing on the X-ray image I1 to generate a processed image, and then performing CAD processing on the generated processed image. However, the embodiment is not limited to this. That is, the diagnostic assistance function 34b may omit the image processing step and perform CAD processing on the X-ray image I1 (original data). This also applies to the case where diagnostic assistance processing is performed using the trained model M1.

In addition, in FIG. 4A, the trained model M1 that performs at least CAD processing is described, but the embodiment is not limited to this. For example, the diagnostic assistance function 34b may perform diagnostic assistance processing using the trained model M2 that is functionalized to receive input of an X-ray image and generate a processed image. The trained model M2 will be described below with reference to FIG. 4B. FIG. 4B is a diagram for explaining the generation process of the trained model according to the first embodiment.

For example, the diagnostic support function 34b acquires from the memory 33 a trained model M2 that is configured to receive an input of an X-ray image and output a processed image. The trained model M2 may be generated by the diagnostic support function 34b using a method described below, or may be generated by an external device.

Next, as shown in FIG. 4B, the diagnostic support function 34b inputs the X-ray image I1 collected from the patient P1 in the first examination to the trained model M2 (neural network). The trained model M2 also performs image processing on the X-ray image I1 to generate a processed image. For example, the trained model M2 generates processed images corresponding to the above-mentioned X-ray image I12, X-ray image I13, and X-ray image I14.

Next, the diagnostic support function 34b performs CAD processing on the processed image generated using the trained model M2. For example, the diagnostic support function 34b performs various CAD processes such as CADc1, CADc2, and CADc3 described above on the processed image generated using the trained model M2.

Next, the notification function 34c notifies the patient P1 of the results of the diagnostic support process (diagnosis result). Next, a second examination is performed on the patient P1 based on the diagnosis result, and the detailed examination result is sent to the medical image processing device 30. Then, the diagnostic support function 34b executes a generation process of the trained model M2 based on the X-ray image I1 and the detailed examination result. In other words, the diagnostic support function 34b updates the trained model M2 as shown in FIG. 4B.

As an example, the diagnostic support function 34b first generates a learning dataset including the X-ray image I1 and detailed examination results for patient P1. The diagnostic support function 34b also inputs the X-ray image I1 to the neural network as input data. Here, in the neural network, information propagates in one direction from the input layer to the output layer while connecting only between adjacent layers, and a processed image based on the input X-ray image I1 is output from the output layer. The diagnostic support function 34b then generates a trained model M2 by adjusting the parameters of the neural network so that the neural network can output favorable results when the input data is input.

As one example, the output layer of the neural network outputs a processed image in which the window value and window width in the X-ray image I1 have been adjusted. As another example, the output layer of the neural network outputs a processed image in which bones have been removed from the X-ray image I1. Here, the diagnostic support function 34b executes various CAD processes such as CADc1, CADc2, and CADc3 on the processed image output from the neural network. Also, the diagnostic support function 34b compares the results of the CAD processes with the detailed examination results (results of the second examination), and repeats the process while adjusting the parameters of the neural network until the difference between them falls below a threshold value.

In other words, the more appropriately the image processing is performed, the higher the accuracy of the CAD processing. The diagnostic support function 34b trains the neural network so that more appropriate image processing can be performed. This allows the diagnostic support function 34b to generate a trained model M2 that is functionally configured to accept input of an X-ray image and output a processed image. The diagnostic support function 34b also stores the generated trained model M2 in the memory 33.

As described above, the diagnostic support function 34b can generate a processed image using the trained model M2, perform CAD processing on the generated processed image, and further perform generation processing of the trained model M2. Therefore, the diagnostic support function 34b can update the trained model M2 every time a patient visits the hospital and a first examination and a second examination are performed, gradually improving the accuracy of image processing. For example, the diagnostic support function 34b can improve the accuracy of adjusting the window value and window width in the X-ray image and the bone removal process every time the trained model M2 is updated.

Up to this point, the trained model M1 and the trained model M2 have been described as being configured using a convolutional neural network (CNN), but the diagnostic support function 34b may configure the trained model M1 and the trained model M2 using other types of neural networks, such as a fully connected neural network or a recurrent neural network (RNN).

The diagnostic support function 34b may generate the trained model M1 and the trained model M2 using a machine learning method other than a neural network. For example, the diagnostic support function 34b may perform machine learning using algorithms such as logistic regression analysis, nonlinear discriminant analysis, a support vector machine (SVM), a random forest, and a naive Bayes to generate the trained model M1 and the trained model M2.

Next, an example of the processing procedure by the X-ray diagnostic device 110 and the medical image processing device 30 will be described with reference to FIG. 5. FIG. 5 is a flowchart for explaining a series of processing steps by the X-ray diagnostic device 110 and the medical image processing device 30 according to the first embodiment.

Step S101 corresponds to the collection function 118b of the processing circuit 118. Step S102 corresponds to the display control function 118d of the processing circuit 118. Step S103 corresponds to the control function 118a of the processing circuit 118. Steps S104, S105, S111, and S112 correspond to the diagnosis support function 34b of the processing circuit 34. Step S106 corresponds to the display control function 34d of the processing circuit 34. Steps S107, S108, S109, and S110 correspond to the notification function 34c of the processing circuit 34.

First, the processing circuitry 118 collects an X-ray image I1 from the patient P1 in the first examination (step S101). Next, the processing circuitry 118 presents the collected X-ray image I1 to the user (step S102). In step S102, the processing circuitry 118 may display the collected X-ray image I1 directly on the display 116, or may display the results of the diagnostic support process based on the X-ray image I1 on the display 116. Here, the user of the X-ray diagnostic device 110 performs a diagnosis according to the first diagnostic purpose. For example, if the patient P1 visits the hospital complaining of shoulder pain, the user refers to the X-ray image I1 to check whether there is a lesion in the shoulder joint of the patient P1 and performs a diagnosis.

Next, the processing circuitry 34 transmits the X-ray image I1 to the medical image processing device 30 (step S103). The processing circuitry 34 also executes CAD based on the X-ray image I1 (step S104). Specifically, the processing circuitry 34 executes CAD according to a second diagnostic purpose different from the first diagnostic purpose based on the first diagnostic purpose and the X-ray image I1. For example, if a diagnosis to identify a lesion in the shoulder joint is performed in the first examination, the processing circuitry 34 executes CAD related to lung cancer, pulmonary tuberculosis, pneumothorax, etc. The processing circuitry 34 may execute image processing on the X-ray image I1 and execute CAD processing on the processed image. The processing circuitry 34 may also execute image processing and CAD using the learned model M1 or the learned model M2.

Next, the processing circuitry 34 determines whether or not the results of the CAD processing are to be confirmed (consulted) by the user (step S105). If the results of the CAD processing are to be confirmed by the user (Yes in step S105), the processing circuitry 34 displays the results of the CAD processing on the display 32 (step S106). After step S106, or if the results are not to be confirmed by the user (No in step S105), the processing circuitry 34 creates a report R1 (step S107). For example, after step S106, the processing circuitry 34 creates a report R1 in response to an input operation received from the user.

Next, the processing circuitry 34 transmits the report R1 to the patient P1 (step S108). Here, the processing circuitry 34 may create a list of hospitals or doctors recommended for the patient P1 to visit, and notify the patient P1 of the list. The processing circuitry 34 also determines whether or not to make a reservation (step S109). If a reservation is to be made (Yes in step S109), the processing circuitry 34 identifies a hospital or doctor recommended for the patient P1 to visit according to the report R1, and makes a reservation with the identified hospital or doctor (step S110).

After step S110, or if no reservation is made (step S109: No), the processing circuitry 34 determines whether the detailed examination results have been received (step S111). That is, the processing circuitry 34 determines whether the results of the second examination have been received. If the detailed examination results have been received (step S111: Yes), the processing circuitry 34 uses the X-ray image I1 and the detailed examination results as learning data to update the learned model M1 or the learned model M2 (step S112). Then, after step S112, or if the detailed examination results have not been received (step S111), the processing circuitry 34 ends the process.

As described above, according to the first embodiment, the diagnostic assistance function 34b executes diagnostic assistance processing according to a second diagnostic purpose different from the first diagnostic purpose based on the first diagnostic purpose in the first examination and the X-ray image I1 collected in the first examination. In addition, the notification function 34c notifies at least one of the patient P1 who was the subject of the first examination and the user who performed the first examination of the results of the diagnostic assistance processing. Therefore, the medical image processing device 30 according to the first embodiment can use the X-ray image I1 not only for the first diagnostic purpose but also for the second diagnostic purpose, making more effective use of the X-ray image I1.

In addition, doctors generally have their own areas of expertise. For example, an orthopedic doctor will diagnose patient P1 who is complaining of shoulder pain by focusing on the shoulder joint. However, even if there is shoulder pain, the cause is not necessarily in the shoulder. In such cases, no matter how many times the patient visits an orthopedic surgeon, the pain will not be alleviated, which will be stressful for the patient and will increase the burden on the hospital. In contrast, according to the first embodiment, the medical image processing device 30 can detect the cause of pain regardless of the doctor's area of expertise, thereby reducing the burden on the patient and the hospital. For example, the burden of interpreting images is reduced for doctors. This will also ultimately lead to a reduction in medical expenses.

Also, as described above, according to the first embodiment, the notification function 34c can create and notify a list of hospitals or doctors recommended for patient P1 depending on the results of the diagnostic support process, or make an appointment with the recommended hospital or doctor. That is, the medical image processing device 30 can link multiple hospitals and doctors with different specialties to diagnose patient P1. This allows each doctor to focus on their own area of expertise when making a diagnosis, improving the efficiency of diagnosis.

Second Embodiment
In the above-mentioned first embodiment, a case where the first examination is performed on a patient P1 who complains of shoulder pain is described as an example. In contrast, in the second embodiment, a case where the first examination is performed on a patient P2 who complains of abdominal pain is described. A medical image processing system 1 according to the second embodiment has a configuration similar to that of the medical image processing system 1 shown in Figures 1 and 2. Hereinafter, the points described in the first embodiment are denoted by the same reference numerals as those in Figures 1 and 2, and description thereof will be omitted.

For example, when patient P2 complaining of abdominal pain visits an internal medicine doctor, a user such as a doctor interviews patient P2 about his/her symptoms. If the user determines that an X-ray image is necessary for diagnosis, the user uses the X-ray diagnostic device 110 to collect an X-ray image I2 including the abdomen of patient P2.

Next, the diagnostic support function 118c executes diagnostic support processing based on the X-ray image I2. For example, the diagnostic support function 118c executes CAD processing on the X-ray image I2 to generate an X-ray image I21 in which a marker is added to a portion of the digestive tract depicted in the X-ray image I12 where perforation is suspected. Next, the display control function 118d causes the X-ray image I21 to be displayed on the display 116. Alternatively, the display control function 118d may cause the collected X-ray image I2 to be displayed directly on the display 116. Then, the user refers to the X-ray image displayed on the display 116 to examine the presence or absence of a perforation in the digestive tract of the patient P2 and make a diagnosis. In addition, the control function 118a transmits the X-ray image I2 to the medical image processing device 30.

Next, the diagnostic support function 34b executes diagnostic support processing according to the second diagnostic purpose based on the X-ray image I2. For example, the diagnostic support function 34b acquires a CAD other than the CAD for determining perforation of the digestive tract that is applicable to abdominal X-ray images, and executes CAD processing using the acquired CAD. Examples of such CAD include a CAD for detecting gallstones and a CAD for detecting renal cysts. The diagnostic support function 34b may also execute diagnostic support processing based on the X-ray image I2 using the trained model M1 or trained model M2 described above.

Next, the notification function 34c notifies at least one of the patient P2 and the user who performed the first examination on the patient P2 of the results of the diagnostic support processing. For example, the notification function 34c generates a report R2 based on the results of the diagnostic support processing by the diagnostic support function 34b, and feeds back the generated report R2 to the patient P2. The notification function 34c may receive consultation from the user of the medical image processing device 30 regarding the report R2. The notification function 34c may also create a list of hospitals or doctors recommended for the patient P2 to visit, and notify the patient P2 of the created list. The notification function 34c may also identify a hospital or doctor recommended for the patient P2 to visit, and make an appointment for the patient P2 to visit the identified hospital or doctor.

Next, a second examination is performed on patient P2 based on the results of the diagnostic support processing. For example, if a renal cyst is detected from X-ray image I2, a detailed examination of the kidney is performed. This allows patient P2 to detect lesions in the kidney at an early stage. Furthermore, when the diagnostic support function 34b receives the results of the second examination, it can use the X-ray image I2 and the results of the second examination as learning data to update the trained model M1 or trained model M2.

Third Embodiment
Although the first and second embodiments have been described above, the present invention may be embodied in various different forms other than the above-described embodiments.

For example, in FIG. 1, the medical image diagnostic device 10 and the medical image processing device 30 are described as separate entities. However, the embodiment is not limited to this. For example, a console provided in the medical image diagnostic device 10 may function as the medical image processing device 30. As one example, the processing circuitry 118 of the X-ray diagnostic device 110 may execute functions such as the above-mentioned diagnostic support function 34b, notification function 34c, and display control function 34d.

Alternatively, processing circuits having various functions such as the diagnostic support function 34b, the notification function 34c, and the display control function 34d may be distributed and arranged in multiple devices. For example, the above-mentioned diagnostic support function 34b may be executed by the processing circuitry 34 of the medical image processing device 30, and the notification function 34c may be executed by the processing circuitry 118 of the X-ray diagnostic device 110.

In the above-described embodiment, X-ray image I1 and X-ray image I2 are described as medical images collected in the first examination. However, the embodiment is not limited to this. For example, the present invention can be similarly applied when X-ray CT images, ultrasound images, MR images, SPECT images, PET images, etc. are collected in the first examination. The present invention can also be similarly applied when fluoroscopic images are collected in the first examination. Note that a fluoroscopic image is a medical image that is displayed in parallel with collection.

In addition, in the first examination, the entire collected medical image may not be used. For example, when three-dimensional images such as X-ray CT images are collected, the doctor refers to a two-dimensional image generated by rendering processing or the like in the first examination. Many such two-dimensional images can be generated based on three-dimensional images, and it is not easy for a doctor to interpret all of them.

Here, the diagnostic support function 34b may perform diagnostic support processing on a portion of the medical image that was not used in the first examination. For example, the diagnostic support function 34b may generate a two-dimensional image at a position or angle that was not generated in the first examination based on the X-ray CT image collected in the first examination, and perform CAD processing on the generated two-dimensional image. Alternatively, the diagnostic support function 34b may perform CAD processing on the X-ray CT image (original data).

In the above-described embodiment, a definitive diagnosis by a doctor has been described as the result of the second examination. However, the embodiment is not limited to this, and the result of the second examination may be the result of CAD processing in the second examination. Furthermore, the diagnosis support function 34b may update the trained model M1 or trained model M2 using the medical images collected in the first examination and the result of CAD processing in the second examination as training data.

For example, in FIG. 3, in step S4, the presence or absence of lung cancer is determined by CAD processing using an X-ray image I1 collected for the purpose of diagnosing the shoulder joint. On the other hand, in step S7, the presence or absence of lung cancer is determined by CAD processing using a medical image collected for the purpose of diagnosing lung cancer. Therefore, the result of the CAD processing in step S7 is more accurate than the result of the CAD processing in step S4. As described above, the diagnosis support function 34b can update the trained model M1 or trained model M2 using the result of the CAD processing in step S7 as correct answer data.

Alternatively, the diagnostic support function 34b can update the trained model M1 or the trained model M2 based on the progression of the patient's symptoms after undergoing the first test. For example, as shown in FIG. 3, even when a report R1 indicating a suspicion of lung cancer is notified, it is conceivable that the patient P1 will not undergo the second test. In such a case, the diagnostic support function 34b can update the trained model M1 or the trained model M2 using as correct answer data whether or not the patient P1 has actually developed lung cancer.

The term "processor" used in the above description refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). If the processor is, for example, a CPU, the processor realizes the function by reading and executing a program stored in a memory circuit. On the other hand, if the processor is, for example, an ASIC, instead of storing a program in a memory circuit, the function is directly incorporated as a logic circuit in the circuit of the processor. Note that each processor in the embodiments is not limited to being configured as a single circuit for each processor, but may be configured as a single processor by combining multiple independent circuits to realize the function. Furthermore, multiple components in each figure may be integrated into a single processor to realize the function.

The components of each device according to the above-described embodiments are conceptual and functional, and do not necessarily need to be physically configured as shown in the figures. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figures, and all or part of the devices can be functionally or physically distributed and integrated in any unit depending on various loads and usage conditions. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

The medical image processing method described in the above embodiment can be realized by executing a prepared medical image processing program on a computer such as a personal computer or a workstation. This medical image processing program can be distributed via a network such as the Internet. This medical image processing program can also be recorded on a non-transitory recording medium that can be read by a computer, such as a hard disk, flexible disk (FD), CD-ROM, MO, or DVD, and executed by being read from the recording medium by a computer.

According to at least one of the embodiments described above, collected medical images can be utilized more effectively.

Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are within the scope of the invention and its equivalents as set forth in the claims, as well as the scope and spirit of the invention.

REFERENCE SIGNS LIST 1 Medical image processing system 110 X-ray diagnostic device 118 Processing circuit 118a Control function 118b Acquisition function 118c Diagnosis support function 118d Display control function 30 Medical image processing device 34 Processing circuit 34a Control function 34b Diagnosis support function 34c Notification function 34d Display control function

Claims (17)

a diagnostic support unit that executes a diagnostic support process according to a second diagnostic purpose, the second diagnostic purpose being in a field different from the first diagnostic purpose, based on a first diagnostic purpose in a first examination and medical images acquired in the first examination;
a notification unit that notifies at least one of a patient who was the subject of the first examination and a user who performed the first examination of a result of the diagnostic support processing, and further creates a list of hospitals or doctors that are recommended for the patient based on the result of the diagnostic support processing, and notifies the patient of the list . The medical image processing device according to claim 1, wherein the diagnostic support unit executes the diagnostic support processing by performing computer-aided diagnosis (CAD) processing on the medical image according to the second diagnostic purpose. The medical image processing device according to claim 1, wherein the diagnostic support unit performs image processing on the medical image in accordance with the second diagnostic purpose to generate a processed image, and performs CAD processing on the generated processed image, thereby executing the diagnostic support processing. The medical image processing device according to claim 2 or 3, wherein the diagnostic support unit executes the diagnostic support process using a trained model that is functionalized to accept input of the medical image and output the results of the CAD process. The medical image processing device according to claim 3, wherein the diagnostic support unit generates the processed image using a trained model that is functionalized to receive the input of the medical image and generate the processed image, and executes the diagnostic support process by performing CAD processing on the generated processed image. The medical image processing device according to claim 4 or 5, wherein the diagnostic support unit updates the trained model using the medical image and the results of a second examination performed on the patient based on the results of the diagnostic support processing as training data. The medical image processing device according to any one of claims 1 to 6, wherein the notification unit generates an image in which a marker is added to a location on the medical image where a lesion is suspected based on the result of the diagnostic support processing, and notifies at least one of the patient and the user of the result of the diagnostic support processing by a report including the image. A display control unit that displays a result of the diagnostic support processing,
The medical image processing device according to any one of claims 1 to 7, wherein the notification unit creates a report indicating the results of the diagnostic support processing in response to an input operation received from a first user who has referred to the results of the diagnostic support processing, and notifies at least one of the patient and a second user who performed the first examination and is different from the first user of the report. The medical image processing device according to any one of claims 1 to 8, wherein the notification unit further identifies a hospital or doctor to be recommended for the patient based on a result of the diagnostic support processing, and schedules a consultation for the patient at the identified hospital or doctor . an acquisition unit that acquires medical images according to a first diagnostic objective of a first examination;
a diagnostic support unit that executes a diagnostic support process according to a second diagnostic purpose, the second diagnostic purpose being in a field different from the first diagnostic purpose, based on the first diagnostic purpose and the medical image;
a notification unit that notifies at least one of the patient who was the subject of the first examination and the user who performed the first examination of the results of the diagnostic support processing, and further creates a list of hospitals or doctors that are recommended for the patient based on the results of the diagnostic support processing, and notifies the patient of the list . Executing a diagnostic support process according to a second diagnostic purpose, the second diagnostic purpose being in a field different from the first diagnostic purpose, based on a first diagnostic purpose in a first examination and medical images acquired in the first examination;
a medical image processing method including notifying a result of the diagnostic support processing to at least one of a patient who was the subject of the first examination and a user who performed the first examination, and further creating a list of hospitals or doctors recommended for the patient based on the result of the diagnostic support processing, and notifying the patient of the list . a diagnostic support unit that executes a diagnostic support process according to a second diagnostic purpose different from a first diagnostic purpose in a first examination based on a first diagnostic purpose in a first examination and medical images acquired in the first examination;
a notification unit that notifies at least one of a patient who was the subject of the first examination and a user who performed the first examination of a result of the diagnostic support processing, and further creates a list of hospitals or doctors that are recommended for the patient based on the result of the diagnostic support processing, and notifies the patient of the list. a diagnostic support unit that executes a diagnostic support process according to a second diagnostic purpose different from a first diagnostic purpose in a first examination based on a first diagnostic purpose in a first examination and medical images acquired in the first examination;
a notification unit that notifies at least one of a patient who was the subject of the first examination and a user who performed the first examination of a result of the diagnostic support processing, and further identifies a hospital or doctor that is recommended for the patient based on the result of the diagnostic support processing, and makes an appointment for the patient to be examined at the identified hospital or doctor. an acquisition unit that acquires medical images according to a first diagnostic objective of a first examination;
a diagnostic support unit that executes a diagnostic support process according to a second diagnostic purpose different from the first diagnostic purpose based on the first diagnostic purpose and the medical image;
a notification unit that notifies at least one of the patient who was the subject of the first examination and the user who performed the first examination of the results of the diagnostic support processing, and further creates a list of hospitals or doctors that are recommended for the patient based on the results of the diagnostic support processing, and notifies the patient of the list. an acquisition unit that acquires medical images according to a first diagnostic objective of a first examination;
a diagnostic support unit that executes a diagnostic support process according to a second diagnostic purpose different from the first diagnostic purpose based on the first diagnostic purpose and the medical image;
a notification unit that notifies at least one of the patient who was the subject of the first examination and the user who performed the first examination of the results of the diagnostic support processing, and further identifies a hospital or doctor that is recommended for the patient based on the results of the diagnostic support processing, and makes an appointment for the patient to be examined at the identified hospital or doctor. execute a diagnostic support process according to a second diagnostic purpose different from the first diagnostic purpose based on a first diagnostic purpose in a first examination and medical images acquired in the first examination;
a medical image processing method including notifying a result of the diagnostic support processing to at least one of a patient who was the subject of the first examination and a user who performed the first examination, and further creating a list of hospitals or doctors recommended for the patient based on the result of the diagnostic support processing, and notifying the patient of the list. execute a diagnostic support process according to a second diagnostic purpose different from the first diagnostic purpose based on a first diagnostic purpose in a first examination and medical images acquired in the first examination;
A medical image processing method comprising: notifying at least one of a patient who was the subject of the first examination and a user who performed the first examination of a result of the diagnostic support processing; identifying a hospital or doctor recommended for the patient based on the result of the diagnostic support processing; and scheduling a consultation for the patient with the identified hospital or doctor.

Images