WO2019143179A1 - Method for automatically detecting same regions of interest between images of same object taken with temporal interval, and apparatus using same - Google Patents

Abstract

The present invention relates to a method for detecting the same regions of interest in images of the same object taken with a temporal interval, and an apparatus using the method. In particular, the method according to the present invention acquires a first image, and a second image taken after a temporal interval from when the first image was taken, and, when an area of interest is set on the first image, a computing apparatus detects, as the same area of interest, an area of interest in the second image which is the same as said area of interest, or supports so that the detection is by means of an apparatus linked to the computing apparatus.

Description

A method for automatically detecting the same area of interest between images photographed with a time interval for the same subject, and a device using the same

The present invention relates to a method for detecting a region of interest between images photographed with a time interval for the same subject, and an apparatus using the same. Specifically, according to the method of the present invention, when a second image photographed at a time interval from the time of photographing of the first image and the second image is obtained, and a region of interest is set on the first image, And detects the same area of interest as the area of interest as the area of interest as the area of interest in the second image.

Currently, imaging techniques such as computed tomography (CT) are widely used for diagnosis by analyzing lesions. In the diagnosis by the image inspection, the progress of the lesion can be known according to the time change by tracking the same lesion change between sequential CT images sequentially captured on the same subject, that is, the subject. It is necessary to identify whether the lesions are the same lesion, that is, to match the same lesion with each other.

These lesions are characterized by progressive characteristics, that is, shape and size depending on time. Therefore, it is difficult to know whether the lesion is the same lesion only by simple matching and comparison, and thus it is difficult to automate.

In the present invention, a method of learning a deep learning model using pairs of lesions photographed at different viewpoints and determining a pair of lesions with the same degree of similarity or higher by measuring the similarity of newly given lesion pairs, And propose a device using the same.

[Prior Art Literature]

(Patent Document 1) US7660448 B

(Non-Patent Document 1): Goodfellow, Ian J .; Pouget-Abadie, Jean; Mirza, Mehdi; Xu, Bing; Warde-Farley, David; Ozair, Sherjil; Courville, Aaron; Bengio, Yoshua (2014). "Generative Adversarial Networks"

(Non-Patent Document 2): Dmitriy Serdyuk et al. Twin Networks: Matching the Future for Sequence Generation, arXiv preprint arXiv: 1708.06742v2

The present invention aims to enable detection of the same area of interest, especially lesion, between different images.

Specifically, the present invention aims at performing measurement and tracking observation of the shape and quantitative change of the area of interest through quantification of the same area of interest.

In particular, it is an object of the present invention to be able to determine the same area of interest among candidates of interest even when there are a plurality of areas of interest.

The characteristic configuration of the present invention for achieving the object of the present invention as described above and realizing the characteristic effects of the present invention described below is as follows.

According to an aspect of the present invention, there is provided a method for detecting the same area of interest between images photographed for the same subject, wherein the time from the shooting of the first image and the first image If a second image photographed at intervals is obtained and a region of interest is set on the first image, the computing device may detect in the second image the same area of interest as the area of interest as a region of interest, Thereby enabling other interlocked devices to be detected.

Advantageously, the method further comprises: (a) supporting the computing device to acquire or acquire the first and second images; (b) supporting the computing device to set or set a search area corresponding to a region of interest designated on the acquired first image to the second image; And (c) supporting the computing device to search for or retrieve at least one candidate image that is the same or similar to the region of interest within the set search subject area, thereby selecting one of the at least one candidate image To the same area of interest.

According to another aspect of the present invention, there is also provided a computer program stored in a machine readable non-transitory medium, comprising instructions embodied to perform the method of detecting a region of interest in accordance with the present invention.

According to another aspect of the present invention, there is provided a computing device for detecting the same area of interest between images photographed for the same subject, the computing device comprising: a first image and a time interval A communication unit for acquiring a second image photographed by the photographing unit; And when the first image and the second image are acquired and a region of interest is set on the first image, the same region of interest as the region of interest is detected as the same region of interest as the same region of interest, And to enable other devices to be detected.

Preferably, the processor is configured to set or otherwise set the search object zone corresponding to the region of interest designated on the acquired first image to the second image or to set the other device in the set search region To support the detection or detection of any one of the at least one candidate image selected according to a predetermined criterion in the same area of interest by assisting in searching or retrieving at least one candidate image that is the same as or similar to the region of interest.

According to the present invention, it is possible to determine one or more regions of interest in one image, particularly the same region of interest in another image, for each of the lesions.

Further, according to the present invention, it is possible to learn a degree-of-similarity measurement model having high accuracy based on data without designing subjective designers about the similarity of the interest area through learning based on the deep learning.

According to the present invention, it is possible to monitor the change of the region of interest from t to t 'through comparison determination between t' and t 'as well as t' and t '.

Therefore, according to the present invention, there is an effect that tracking observation of the same area of interest, particularly, lesion, and construction of a monitoring system using the same can be made possible.

This has the potential to ultimately save the staff time spent in diagnosing progressive lesions and improve the speed and quality of readings, thereby enabling a workflow in the medical field to be innovated.

Further, the present invention can be applied to a medical image used in a hospital, for example, a three-dimensionally acquired ultrasound image, an MRI image, and the like, and the method of the present invention is not dependent on a specific type of image or platform Of course not.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, The figures can be obtained.

1 schematically shows an exemplary configuration of a computing device that performs a method for detecting the same area of interest between images photographed for the same subject in accordance with the present invention It is a conceptual diagram.

2 is an exemplary block diagram illustrating the hardware or software components of a computing device that performs the method of detecting a region of interest in accordance with the present invention.

Figure 3 is a flow diagram illustrating an exemplary method of detecting a region of interest in accordance with the present invention.

FIG. 4 is a conceptual diagram illustrating a calculation method of the degree of similarity used in the method of detecting the same area of interest according to the present invention.

Figure 5 is an exemplary illustration of regions of interest detected in accordance with the present invention.

The following detailed description of the invention refers to the accompanying drawings, which illustrate, by way of example, specific embodiments in which the invention may be practiced in order to clarify the objects, technical solutions and advantages of the invention. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention.

The term "image" or "image data" used throughout the description and claims of the present invention refers to multidimensional data composed of discrete image elements (e.g., pixels in a two-dimensional image and voxels in a three- Quot; For example, "imaging" may be computed by (cone-beam) computed tomography, magnetic resonance imaging (MRI), ultrasound, or any other medical imaging system known in the art I.e., a medical image of a subject. The images may also be provided in a non-medical context, for example, a remote sensing system, an electron microscopy, and the like.

Throughout the description and claims of the present invention, an 'image' refers to an image that is visible (eg, displayed on a video screen) or an image (eg, a file corresponding to a pixel output, such as a CT or MRI detector) It is a term referring to a digital representation.

For convenience of illustration, cone-beam computed tomography (CBCT) image data is sometimes shown as an exemplary image modality in the drawings. However, those skilled in the art will appreciate that image formats used in various embodiments of the present invention may be used in various imaging formats such as X-ray imaging, MRI, CT, positron emission tomography (PET), PET-CT, SPECT, SPECT-CT, MR- But it is to be understood that the present invention is not limited to the three-dimensional image and the slice image derived therefrom.

Throughout the detailed description and claims of the present invention, the term 'DICOM' (Digital Imaging and Communications in Medicine) is a generic term for various standards used in digital image representation and communication in medical devices, The standard is presented at the Joint Committee composed of the American Radiation Medical Association (ACR) and the American Electrical Manufacturers Association (NEMA).

In addition, the term 'Picture Archiving and Communication System (PACS)' refers to a system for storing, processing and transmitting according to the DICOM standard throughout the detailed description and claims of the present invention, , And MRI can be stored in the DICOM format and transmitted to a terminal inside or outside the hospital through the network, and the result of reading and the medical record can be added to the terminal.

Throughout the detailed description and claims of the present invention, 'learning' or 'learning' refers to performing machine learning through computing according to a procedure, It will be understood by those of ordinary skill in the art that the present invention is not intended to be so-called.

And throughout the description and claims of this invention, the word 'comprise' and variations thereof are not intended to exclude other technical features, additions, elements or steps. Also, 'one' or 'one' is used in more than one meaning, and 'another' is limited to at least the second.

Other objects, advantages and features of the present invention will become apparent to those skilled in the art from this description, and in part from the practice of the invention. The following examples and figures are provided by way of illustration and are not intended to limit the invention. Accordingly, the details disclosed herein with respect to a particular structure or function are not to be construed in a limiting sense, but merely as being representative of the general inventive concept providing a guideline for carrying out the invention in various detail structures, It should be interpreted as basic data.

Moreover, the present invention encompasses all possible combinations of embodiments shown herein. It should be understood that the various embodiments of the present invention are different, but need not be mutually exclusive. For example, certain features, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with one embodiment. It should also be understood that the position or arrangement of individual components within each disclosed embodiment may be varied without departing from the spirit and scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is to be limited only by the appended claims, along with the full scope of equivalents to which such claims are entitled, if properly explained. In the drawings, like reference numerals refer to the same or similar functions throughout the several views.

Unless otherwise indicated herein or clearly contradicted by context, items referred to in the singular are intended to encompass a plurality unless otherwise specified in the context. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, so that those skilled in the art can easily carry out the present invention.

1 is a conceptual diagram schematically illustrating an exemplary configuration of a computing device that performs a method of detecting a region of interest according to the present invention.

1, a computing device 100 according to an embodiment of the present invention includes a communication unit 110 and a processor 120. The communication unit 110 communicates with an external computing device (not shown) Communication is possible.

In particular, the computing device 100 may be implemented as a computer-readable medium, such as conventional computer hardware (e.g., a computer processor, memory, storage, input and output devices, Electronic communication devices, electronic information storage systems such as network-attached storage (NAS) and storage area networks (SAN), and computer software (i.e., computing devices that enable a computing device to function in a particular manner) Commands) to achieve the desired system performance.

The communication unit 110 of the computing device can send and receive requests and responses to and from other interworking computing devices. As an example, such requests and responses can be made by the same transmission control protocol (TCP) session But not limited to, a user datagram protocol (UDP) datagram, for example. In addition, in a broad sense, the communication unit 110 may include a keyboard, a mouse, an external input device, a printer, a display, and other external output devices for receiving commands or instructions.

The processor 120 of the computing device may also be a micro processing unit (MPU), a central processing unit (CPU), a graphics processing unit (GPU), or a tensor processing unit (TPU), a cache memory, a data bus ). ≪ / RTI > It may further include a software configuration of an operating system and an application that performs a specific purpose.

2 is an exemplary block diagram illustrating the hardware or software components of a computing device that performs the method of detecting a region of interest in accordance with the present invention.

2, the computing device 100 may include an image acquisition module 210 as a component thereof. The image acquisition module 210 is configured to acquire a first image and a second image to which the method according to the present invention is applied, wherein the first image and the second image may be a two-dimensional image or a three-dimensional image. If these images are 3D images, the area of interest can be called the volume of interest. If these images are 2D images, the area of interest may be called the area of interest.

2 may be implemented, for example, by the communication unit 110 or the processor 120 included in the computing device 100, or by the interlocking of the communication unit 110 and the processor 120, The person skilled in the art will understand. The first image and the second image may be medical images and may be acquired from an external image storage system such as a radiographic imaging apparatus or a medical image storage transmission system (PACS) linked through the communication unit 110 But is not limited thereto. For example, these images may be captured by the imaging device and transmitted to the PACS in accordance with the DICOM standard, and then acquired by the image acquisition module 210 of the computing device 100.

Next, the acquired medical image may be transmitted to the search object zone setting module 220, which sets the search object zone corresponding to the area of interest designated on the first image to the second image As shown in FIG. For example, the search area may be set to be larger than the size of the area of interest in consideration of the position error e between the first image and the second image.

And, the candidate image search module 230 is configured to retrieve at least one candidate image that is the same or similar to the region of interest within the region of interest when the region of interest is set.

The candidate image retrieval module 230 may be implemented using a recent deep convolutional neural network such as a Fully Convolutional Neural Network or a generative adversarial network (GAN), for example. CNN). An exemplary hostile neural network configuration is described in Non-Patent Document 1: [Goodfellow, Ian J .; Pouget-Abadie, Jean; Mirza, Mehdi; Xu, Bing; Warde-Farley, David; Ozair, Sherjil; Courville, Aaron; Bengio, Yoshua (2014). "Generative Adversarial Networks".

For example, the neural network constituting the candidate image retrieval module 230 may be a generative hostile neural network including a production neural network 232 (not shown) and a classified neural network 234 (not shown). However, it goes without saying that the technique used in the candidate image search module 230 is not limited to the hostile neural network, and various techniques can be used. The candidate image retrieval module 220 that has completed the learning or training may be composed only of the generated neural network 232 because the classified neural network 234 is for learning as described later.

Next, the same area of interest detection module 240 is configured to detect, when at least one candidate image is searched, any one selected according to a predetermined criterion as a region of interest. Here, the predetermined criterion is related to the similarity to be described later.

If the same area of interest is detected in this way, information about the same pair of interest areas can be passed to the storage and transmission module 250 (not shown), which stores and transmits information May be stored or provided to an external entity.

Here, the external entity includes a user of the computing device 100, a manager, a medical professional in charge of the subject, and the like. In addition, a second slice image calculated from the first slice image is required It should be understood that any subject is included. For example, the external entity may be an external AI device that includes separate AI hardware and / or software modules utilizing the second slice image. Also, 'external' in an external entity may be used to exclude embodiments in which AI hardware and / or software modules that utilize at least one of the first slice image and the second slice image are integrated into the computing device 100 The present invention is not intended to suggest that the second slice image, which is the result of the hardware and / or software module performing the method of the present invention, can be used as input data of other methods. That is, the external entity may be the computing device 100 itself.

In addition, when provided to an external entity, the storage and transmission module 250 may perform this through a predetermined display device or the like. At this time, each image and a pair of the same interest area corresponding thereto are displayed on the display device It will be possible. Storage of information representative of this same pair of interest areas may be performed by other devices associated with the computing device 100, such as PACS.

Although the components shown in FIG. 2 are illustrated as being realized in one computing device for convenience of explanation, it will be understood that a plurality of computing devices 100 performing the method of the present invention may be configured to be interlocked with each other.

Now, an embodiment of the image reconstruction method according to the present invention will be described in more detail with reference to FIG. 3 to FIG.

Figure 3 is a flow diagram illustrating an exemplary method of detecting a region of interest in accordance with the present invention.

In the method of detecting a region of interest according to the present invention, a second image photographed at a time interval from the time of photographing the first image and the first image is obtained, and when a region of interest is set on the first image, 100 detects in the second image the same area of interest as the area of interest as a region of interest, or other device associated with the computing device.

3, the method of detecting a region of interest according to the present invention is characterized in that the image acquisition module 210 implemented by the communication unit 110 of the computing device 100 includes the first image and the second image, And acquiring or acquiring the second image (SlOO).

Next, the same-interest area detection method of the present invention is characterized in that the search target zone setting module 220 embodied by the computing device 100 searches for a search target zone corresponding to each of at least one ROI specified on the acquired first image, (S200) for setting or setting each of the first image and the second image with respect to the second image.

Prior to this step S200, a step of assigning a region of interest on the first image (S150) may be performed, which may be performed by a specialist (e.g., a doctor) who can identify a particular region of interest, Or by a lesion detection method (for example, a detection method such as U.S. Patent No. 7,660,448). Wherein at least one region of interest on the first image may be all of the regions of interest identified on the first image or may be regions of interest selected by predetermined manipulations or predetermined criteria.

The predetermined operation may be, for example, an operation (for example, a click operation) for selecting one of the list of the interest areas provided through the user interface, or a part of the image is boxed through the user interface ), And so on.

In addition, the predetermined criteria may be a numerical value indicating that the region of interest is meaningful, for example, a value such as confidence that a lesion identified in a medical image means a probability of an actual lesion is a certain level or more.

For convenience of explanation, it is assumed that the photographing time point of the first image is t, the photographing time point of the second image is t ', the list of the interest area designated by the first image at time t is touched with interest designated to the second image at time t_I, t' The list of zones can be called t'_I.

If t_I is found in step S150, an individual search subject area corresponding to the individual interest area included in t_I is set in step S200. The individual search subject area has a predetermined physical dimension, for example, a space within a predetermined distance d from a position corresponding to the individual attention area of the first image.

The search object zone is utilized to narrow the search object by using information of the position of the ROI relative to the images of the object, whereby detection of the same ROI can be efficiently performed.

It should be understood by those skilled in the art that the search target area is not necessarily set and that the search target area may be set as the entire area of the second image when sufficient operation resources are secured. That is, the search object zone corresponding to the region of interest designated on the first image may be set to be the entire second image.

Next, the method of detecting a region of interest according to the present invention is characterized in that the candidate image retrieval module 230 of the computing device 100 retrieves at least one candidate image identical or similar to the individual region of interest (S300) to detect or detect any one of the at least one candidate image selected according to a predetermined criterion by searching for or searching for the same interest area as the individual area of interest (S300).

Step S300 may include, for example, the step S310 of supporting the candidate image search module 230 to search for or retrieve the at least one candidate image and the step S310 of searching the candidate image, (S320) to detect or detect a candidate image in the second image having the highest degree of similarity with the individual region of interest in the same interest region. The meaning of searching for the candidate image in this step S310 does not mean to detect the region of interest in the second image at that time but it is to be understood as meaning that the region of interest of the second image in the region to be searched is selected . That is, the detection of regions of interest in the second image may be performed prior to step S310, preferably with step S150 described above.

Similarity is a measure of the degree of similarity between images, and can be roughly calculated using characteristics such as color, contrast and saturation according to the conventional image processing method. However, similarity is reflected in various layers of image characteristics ≪ / RTI > will be preferred in carrying out the method of the present invention.

For example, in step S320, the similarity between the individual interest area of the first image and the candidate image in the second image (i.e., the image selected from the individual interest areas of the second image) is determined by the following scheme of the deep learning model . ≪ / RTI >

FIG. 4 is a conceptual diagram illustrating a calculation method of the degree of similarity used in the method of detecting a similar area according to the present invention. FIG. 4 illustrates a pair of twin networks. The two networks may share weight and may be separate, non-shared, convolutional neural networks. The input to the network may be a two-dimensional patch or a three-dimensional voxel. The twin networks are learned to output the same interest area, for example 1 for the same lesion and 0 for the unequal area of interest. If the final output layer of the network is a softmax layer, the resultant value is always between 0 and 1. When any pair of images enters the input value, a value between 0 and 1 is output as a result, Can be used as the similarity between the interest zone images.

The deep learning model according to the present invention can be preliminarily learned using training data including image pairs that are photographed for the same object with a time interval and in which pairs of the same or different regions of interest are labeled. More specifically, the training data includes a pair of images acquired at different times t and t 'for the same subject, i.e., the subject, and a list of regions of interest detected in each of the images. The list includes information such as a region image of interest, e.g., an image corresponding to a lesion and a spatial location of the region of interest. For example, if there is an area of interest identified by an expert between the list of regions of interest t_I corresponding to the image at time t and the list of regions of interest t'_I corresponding to the image at time t ' It is defined. A pair of interest zones other than the same interest zone can also be constructed based on this list of interest zones, which is defined as a pair of non-identical interest zones. Since the data of the pair of the same interest area and the pair of the non-same interest area can be secured for various subjects and various viewpoints, the deep learning model of the present invention can obtain a value of 1 The result can be learned by putting out a value of 0 for the input of a pair of non-identical regions of interest as a result value.

In one example of step S320, if the similarity for all the candidate images is lower than a predetermined threshold value S, it can be determined that the same area of interest is not detected. On the other hand, if there is at least one candidate image in which the degree of similarity is equal to or greater than the predetermined threshold S, the candidate image having the highest degree of similarity may be detected as the same region of interest.

Figure 5 is an exemplary illustration of regions of interest detected in accordance with the present invention. Referring to FIG. 5, nodule lesions, which are the same areas of interest detected in a chest CT image, are illustrated. It will be appreciated by those of ordinary skill in the art that the method of the present invention is generally applicable to a variety of images including areas of interest that vary over time.

The method of detecting a region of interest in accordance with the present invention may include detecting information about the same areas of interest detected by the storage and transmission module 250 (not shown) implemented by the computing device 100, (Step S400) of providing, storing, providing, or storing the similarity between the regions of interest, the type, the identification number, the name of the lesion, and the similarity between regions of interest. Information on such areas of interest could be used to facilitate tracking and observation of areas of interest by including quantitative and morphological indicators.

In this step S400, the information about the same areas of interest generated is stored through the storage and transmission module 250 and / or provided to an external entity via a predetermined display device, and / or May be provided to other devices, such as PACS, that are interfaced to the computing device 100.

Thus, the present invention is able to determine and track the same area of interest in another image for each of at least one region of interest in one image over all of the embodiments and variations described above, It is possible to construct a system. This will allow a more accurate diagnosis of progressive lesions of the physician, which will ultimately improve the quality of care and improve the workflow in the medical field as aided by AI.

Based on the description of the embodiments above, those skilled in the art will recognize that the methods and / or processes of the present invention and their steps may be implemented in hardware, software, or any combination of hardware and software suitable for the particular application Points can be clearly understood. The hardware may include special features or components of a general purpose computer and / or a dedicated computing device or a specific computing device or a particular computing device. The processes may be realized by one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable devices having internal and / or external memory. Additionally or alternatively, the processes can be configured to process application specific integrated circuits (ASICs), programmable gate arrays, programmable array logic (PAL) Or any other device or combination of devices. Furthermore, the objects of the technical solution of the present invention, or portions contributing to the prior art, may be implemented in the form of program instructions that can be executed through various computer components and recorded on a machine-readable recording medium. The machine-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination. The program instructions recorded on the machine-readable recording medium may be those specially designed and constructed for the present invention or may be those known to those of ordinary skill in the computer software arts. Examples of the machine-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROM, DVD, Blu-ray, magneto-optical media such as floptical disks magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include, but are not limited to, any of the above devices, as well as a heterogeneous combination of processors, processor architectures or combinations of different hardware and software, Which may be constructed using a structured programming language such as C, an object-oriented programming language such as C ++ or an advanced or low-level programming language (assembly language, hardware description languages and database programming languages and techniques) This includes not only bytecode, but also high-level language code that can be executed by a computer using an interpreter or the like.

Thus, in one aspect of the present invention, when the methods and combinations described above are performed by one or more computing devices, combinations of the methods and methods may be implemented as executable code that performs each of the steps. In another aspect, the method may be implemented as systems for performing the steps, and the methods may be distributed in various ways throughout the devices, or all functions may be integrated into one dedicated, stand-alone device, or other hardware. In yet another aspect, the means for performing the steps associated with the processes described above may include any of the hardware and / or software described above. All such sequential combinations and combinations are intended to be within the scope of this disclosure.

For example, the hardware device may be configured to operate as one or more software modules to perform processing in accordance with the present invention, and vice versa. The hardware device may include a processor, such as an MPU, CPU, GPU, TPU, coupled to a memory, such as ROM / RAM, for storing program instructions and configured to execute instructions stored in the memory, And a communication unit capable of receiving and sending data. In addition, the hardware device may include a keyboard, a mouse, and other external input devices for receiving commands generated by the developers.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, Those skilled in the art will appreciate that various modifications and changes may be made thereto without departing from the scope of the present invention.

Therefore, the spirit of the present invention should not be construed as being limited to the above-described embodiments, and all of the equivalents or equivalents of the claims, as well as the following claims, I will say.

Such equally or equivalently modified means include, for example, a logically equivalent method which can produce the same result as the method according to the present invention, Should not be limited by the foregoing examples, but should be understood in the broadest sense permissible by law.

Claims (8)

A method for detecting the same area of interest between images photographed for the same subject, comprising the steps of: acquiring a first image and a second image photographed at a time interval from the time of photographing the first image; Once a zone is established, a computing device detects the same zone of interest as the zone of interest, as a zone of interest, in the second image, or supports other devices associated with the computing device to detect it. The method according to claim 1, (a) supporting the computing device to acquire or acquire the first image and the second image; (b) supporting the computing device to set or set a search area corresponding to a region of interest designated on the acquired first image to the second image; And (c) the computing device is adapted to search for or retrieve at least one candidate image that is the same or similar to the region of interest within the set search area, To detect or detect the same area of interest The method comprising the steps of: 3. The method of claim 2, The step (c) (c1) supporting the computing device to search for or retrieve the at least one candidate image; (c2) supporting the computing device to detect or detect, from the candidate images, a candidate image that is most similar to the region of interest to the same region of interest Wherein the method comprises the steps of: The method of claim 3, The step (c2) And if the similarity degree to all of the candidate images is lower than a predetermined threshold, it is determined that the same area of interest is not detected. The method according to claim 1, Characterized in that the detection is performed by a deep convolutional neural network (CNN). A computer program stored in a machine-readable non-transitory medium, comprising instructions embodied in a computer-readable medium for causing a computing device to perform the method of any one of claims 1 to 5. An apparatus for detecting the same area of interest between images photographed for the same subject, A communication unit for acquiring a second image photographed at a time interval from the time of photographing the first image and the first image; And The first image and the second image are acquired and when a region of interest is set on the first image, the same region of interest as the region of interest is detected as the same region of interest as the same region of interest, A processor that assists the device in detecting Wherein the apparatus further comprises: 8. The method of claim 7, The processor comprising: To set a search area corresponding to a region of interest designated on the acquired first image with respect to the second image or to allow the other device to set, Detecting or selecting any one of the at least one candidate image selected in accordance with a predetermined criterion as the same area of interest within the set search area, by supporting or searching for at least one candidate image that is the same as or similar to the area of interest, Wherein the at least one of the at least two of the at least two of the at least two of the at least one of the at least two of the at least one of the plurality

Images