CN119338818A

CN119338818A - Method for detecting benign and malignant lung lesions using MRI imaging

Info

Publication number: CN119338818A
Application number: CN202411884377.8A
Authority: CN
Inventors: 刘伟; 姚立农; 冯媛; 乔杜鹃; 黄玉敏; 孙静静
Original assignee: Air Force Medical University
Current assignee: Air Force Medical University
Priority date: 2024-12-20
Filing date: 2024-12-20
Publication date: 2025-01-21
Anticipated expiration: 2044-12-20
Also published as: CN119338818B

Abstract

The present invention relates to the field of image enhancement technology, and specifically to a method for detecting benign and malignant lung lesions using an MRI imaging group. The method analyzes the image distribution and image prominence state of lung MRI images, determines the recognizability of the lung area in the lung MRI image; determines the confidence of the recognizability according to the change in the recognizability during the respiratory movement detection process; determines the contrast-benefit ratio of the lung MRI image according to the change trend of the lung MRI image sequence; determines the contrast stretch coefficient of the lung MRI image in combination with the confidence of the recognizability and the contrast-benefit ratio; and performs contrast enhancement on the lung MRI image based on the contrast stretch coefficient to obtain an enhanced lung detection image. The lung detection image obtained by the present invention makes the boundary between the lesion and the normal tissue clearer, and improves the detection quality of the lung MRI image.

Description

Method for detecting benign and malignant lung lesions by using MRI imaging group

Technical Field

The invention relates to the technical field of image enhancement, in particular to a method for detecting benign and malignant lung lesions by using an MRI imaging group.

Background

Early detection of lung lesions is of great importance to prognosis for the user, especially in the management of lung cancer, pneumonia, tuberculosis and the like. In recent years, with the rapid development of imaging technology, magnetic resonance imaging (Magnetic Resonance Imaging, MRI) has become an important tool for diagnosis of pulmonary diseases. MRI has the characteristics of no wound, no radiation, excellent soft tissue contrast, and the like, and is particularly suitable for evaluating lung lesions. In addition, MRI is excellent in observing blood supply, tissue structure and metabolic changes thereof of lesions, and can provide more information support.

The existing method for detecting the lung by using the MRI imaging group mainly comprises image acquisition, image post-processing, feature extraction, classification, diagnosis and the like, and although the existing method for detecting the lung by using the MRI imaging group improves the detection capability of the lung to a certain extent, the existing method still has some defects, such as that the respiratory motion of the lung can cause image blurring so as to influence the definition and the visibility of lesions, the existing method often depends on empirical selection on feature extraction, can miss some valuable information so as to reduce the classification performance, and in addition, in the process of carrying out contrast stretching on the MRI image by using a histogram equalization algorithm, some detail information can be lost so as to cause certain errors and inaccuracy on the detection and classification of the region in the MRI image.

Disclosure of Invention

In order to solve the technical problem that in the process of carrying out contrast stretching on an MRI image by using a histogram equalization algorithm, some detail information may be lost, so that certain errors and inaccuracy are caused to detection and classification of regions in the MRI image, the invention aims to provide a method for detecting benign and malignant lung lesions by using an MRI imaging group, and the adopted technical scheme is as follows:

in a first aspect, embodiments of the present invention provide a method for detecting benign and malignant lung lesions using an MRI imaging modality, the method comprising:

Acquiring a lung MRI image;

analyzing the image distribution and the image salient state of the lung MRI image to determine the identifiable degree of the lung region in the lung MRI image;

determining the confidence level of the identifiable degree according to the change condition of the identifiable degree of the image in the respiratory motion detection process;

determining the contrast ratio of the lung MRI image according to the change trend of the lung MRI image sequence;

Determining a contrast stretch coefficient of the lung MRI image in combination with the confidence level of the recognizability and the contrast benefit ratio; and carrying out contrast enhancement on the lung MRI image based on the contrast stretch coefficient to obtain an enhanced lung detection image.

Preferably, the analyzing the image distribution and the image salient state of the lung MRI image to determine the identifiable degree of the lung region in the lung MRI image includes:

acquiring a gray value in the middle of a gray histogram of the lung MRI image, and marking the gray value as a gray representation value;

Analyzing the numerical stability of gray values of pixel points of the lung MRI image, and determining gray discrete values;

determining image distribution parameters of the lung MRI image according to the gray level representation value and the gray level discrete value;

Determining image salient parameters of the lung MRI image according to the overall gradient of the edge line;

And combining the image distribution parameters and the image protrusion parameters to determine the identifiable degree of the lung region in the lung MRI image.

Preferably, the analyzing the numerical stability of the gray value of the pixel point of the lung MRI image, determining the gray discrete value includes:

and taking the standard deviation of gray values of pixel points of the lung MRI image as gray discrete values.

Preferably, the determining the image distribution parameter of the lung MRI image according to the gray scale representation value and the gray scale discrete value includes:

and calculating the absolute value of the difference between the average value of the gray values and the gray representation value of the pixel points of the lung MRI image to be used as an image difference value, and taking the product value of the image difference value and the gray discrete value as an image distribution parameter of the lung MRI image.

Preferably, the determining the confidence level of the identifiable degree according to the change condition of the identifiable degree of the image in the respiratory motion detection process includes:

acquiring a lung MRI image sequence in a preset respiratory cycle;

sequencing the acquisition time of the lung MRI images in the lung MRI image sequence according to the sequence to obtain a time sequence;

sequencing the identifiable degree of the lung region in the lung MRI image according to the sequence of the acquisition time to obtain an identifiable degree sequence;

Calculating the correlation coefficient of the time sequence and the identifiable degree sequence to obtain the identifiable degree correlation coefficient;

the magnetic induction intensities in the corresponding preset respiratory cycle are collected by using a magnetic sensing device, and the magnetic induction intensities are sequenced according to the sequence of the collection time to obtain a magnetic induction sequence;

calculating the correlation coefficient of the time sequence and the magnetic induction intensity sequence to obtain the magnetic induction intensity correlation coefficient;

And combining the identifiable degree correlation coefficient, the magnetic induction intensity correlation coefficient, the identifiable degree sequence and the magnetic induction intensity sequence to obtain the confidence degree of the identifiable degree.

Preferably, the combining the identifiable degree correlation coefficient, the magnetic induction intensity correlation coefficient, the identifiable degree sequence and the magnetic induction intensity sequence to obtain the identifiable degree confidence degree includes:

The method comprises the steps of normalizing sequence elements of a recognizable degree sequence and a magnetic induction intensity sequence, calculating the mean square error of the normalized sequence elements, calculating the absolute value of the difference value of the correlation coefficient of the recognizable degree and the correlation coefficient of the magnetic induction intensity as initial confidence, and taking the product value of the initial confidence and the mean square error as the confidence of the recognizable degree.

Preferably, the determining the contrast benefit ratio of the lung MRI image according to the change trend of the lung MRI image sequence includes:

acquiring a lung MRI image sequence in a preset respiratory cycle;

calculating the average value of pixel differences of pixel points at the same position of adjacent lung MRI images in the lung MRI image sequence to obtain signal differences;

identifying suspected lesion areas and normal areas in the lung MRI images, and calculating average values of differences between gray average values of the suspected lesion areas and gray average values of the normal areas of adjacent lung MRI images in a lung MRI image sequence to obtain area differences;

the contrast to benefit ratio of the lung MRI images is determined in combination with the signal differences and the region differences.

Preferably, the determining the contrast benefit ratio of the lung MRI image by combining the signal difference and the region difference comprises:

the negative correlation mapping value of the product of the signal difference and the region difference is used as the contrast benefit ratio of the lung MRI image.

Preferably, said determining the contrast stretch coefficient of the lung MRI image in combination with the confidence of the recognizability and the contrast benefit ratio comprises:

Taking the confidence coefficient of the identifiable degree as a numerator, taking the contrast beneficial ratio as a denominator, and normalizing the ratio corresponding to the numerator and the denominator to obtain the contrast stretching coefficient of the lung MRI image.

Preferably, the contrast enhancement is performed on the lung MRI image based on the contrast stretch coefficient, so as to obtain an enhanced lung detection image, which includes:

identifying a suspected lesion region in the lung MRI image;

And taking any gray value of the suspected lesion area as a gray value to be adjusted, comparing the sum value of the stretching coefficient and the preset constant adjustment value as an adjustment coefficient of the gray value to be adjusted in histogram equalization, and directly performing histogram equalization operation on gray values except the gray value of the suspected lesion area to enhance the lung detection image.

In a second aspect, a pulmonary lesion benign and malignant detection system using an MRI imaging modality is provided, the system comprising the following modules:

the image acquisition module is used for acquiring lung MRI images;

The static analysis module is used for analyzing the image distribution and the image salient state of the lung MRI image and determining the identifiable degree of the lung region in the lung MRI image;

The dynamic analysis module is used for determining the confidence coefficient of the identifiable degree according to the change condition of the identifiable degree of the image in the respiratory motion detection process;

The contrast analysis module is used for determining the contrast benefit ratio of the lung MRI image according to the change trend of the lung MRI image sequence;

the enhancement module is used for determining the contrast stretching coefficient of the lung MRI image by combining the confidence coefficient of the identifiable degree and the contrast beneficial ratio, and carrying out contrast enhancement on the lung MRI image based on the contrast stretching coefficient to obtain an enhanced lung detection image.

In a third aspect, embodiments of the present invention provide an electronic device, including a memory and a processor, where the memory stores executable code, and where the processor executes the executable code to implement embodiments as possible in the first aspect.

In a fourth aspect, embodiments of the present invention provide a computer program product comprising computer program code which, when run on a computer, causes the computer to perform the method of the first aspect or any one of the possible implementations of the first aspect.

In a fifth aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the embodiments as possible in the first aspect.

The embodiment of the invention has at least the following beneficial effects:

The invention relates to the technical field of image enhancement. In order to solve the problems that in the existing detection method, the respiratory motion of the lung possibly causes image blurring, thereby affecting the definition and visibility of lesions, and in the process of carrying out contrast stretching on the MRI image of the lung by using a histogram equalization algorithm, some detail information can be lost, so that certain errors and inaccuracy are caused for detection and classification. The method comprises the steps of firstly obtaining the identifiable degree of a lung region through the gray level distribution state of an image in a lung MRI image and the integral image salient state in the image, then calculating the identifiable degree confidence degree of the lung region by combining the respiratory motion change condition in the monitoring process, then obtaining the contrast beneficial ratio of image data through the change trend of the lung MRI image in a dynamic lung MRI image sequence, finally calculating the contrast stretching coefficient by combining the confidence degree obtained by dynamic and static frame image analysis and the contrast beneficial ratio, carrying out contrast enhancement on the acquired lung lesion MRI image to obtain a lung detection image, enabling the boundary between the lesion and normal tissues to be clearer, further improving the quality of the lung MRI image, and improving reliable data support for subsequent diagnosis and treatment.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for detecting benign and malignant lung lesions using MRI imaging modalities according to an embodiment of the present invention;

fig. 2 is a block diagram of a system for detecting benign and malignant lung lesions using MRI imaging modalities according to an embodiment of the present invention.

Detailed Description

In order to further describe the technical means and effects adopted for achieving the preset aim of the present invention, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the method for detecting benign and malignant lung lesions by using MRI imaging set according to the present invention with reference to the accompanying drawings and preferred embodiments.

In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

In the description of the embodiment of the present invention, unless otherwise indicated, "/" means or, for example, a/B may mean a or B, "and/or" in the text is only one association relationship describing the association object, and it means that there may be three relationships, for example, a and/or B, three cases where a exists alone, a and B exist together, and B exists alone, and further, "a plurality" means two or more in the description of the embodiment of the present invention.

The terms "first," "second," and the like, are used below for descriptive purposes only and are not to be construed as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

Embodiments of the present invention will be described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the invention is also applicable to similar technical problems.

The following specifically describes a specific scheme of the method for detecting benign and malignant lung lesions by using an MRI imaging group provided by the present invention with reference to the accompanying drawings.

Referring to fig. 1, a flowchart of a method for detecting benign and malignant lung lesions using MRI imaging set according to an embodiment of the present invention is shown, the method comprising the steps of:

Step S100, acquiring a lung MRI image.

First, medical and allergy history of the user is collected, suitability of the magnetic resonance imaging (Magnetic Resonance Imaging, MRI) examination is assessed, and then the examination procedure, in particular the importance of keeping stationary and fitting respiratory instructions, is explained to the user.

Ensuring that the MRI device processes the best working state, performing necessary calibration and quality inspection, selecting the best scanning sequence and parameters according to clinical needs and specific lesion characteristics, and taking care that if contrast agent is needed to be used, evaluating the practicability and preparing injection, and ensuring that the user has no contrast agent allergy.

The user is determined to be on the scanning bed, ensuring comfort and fixation to reduce movement, and the target area is used to set the appropriate scanning range, ensuring coverage of the entire area.

Starting an MRI scanning program, taking care of testing and monitoring image quality, obtaining lung MRI images of a user, storing the obtained lung MRI image data into a safe database system, and making backup.

Step S200, analyzing the image distribution and the image salient state of the lung MRI image, and determining the identifiable degree of the lung region in the lung MRI image.

In the lung MRI image processing process, the benign and malignant lung lesions are accurately evaluated according to the shape, size, position, texture characteristics and other information of the lesion areas in the lung images, but if the contrast of image data is poor, the identification and feature extraction of the lesion areas can be affected, and the accuracy of detecting the benign and malignant lesions is further affected.

The lung MRI image is preprocessed according to the acquired lung MRI image data, so that a gray level histogram of the lung MRI image is acquired, and a gray level value in the middle of the gray level histogram of the lung MRI image is acquired and is recorded as a gray level characterization value. The preprocessing includes the preprocessing operation of denoising the lung MRI image and the like, and the practitioner can process the lung MRI image according to the actual situation or directly acquire the gray level histogram of the lung MRI image without preprocessing.

And analyzing the numerical stability of the gray value of the pixel point of the lung MRI image, and determining a gray discrete value, wherein the standard deviation of the gray value of the pixel point of the lung MRI image is taken as the gray discrete value.

According to the gray level representation value and the gray level discrete value, determining the image distribution parameter of the lung MRI image, specifically, calculating the average value of the gray level values of pixel points of the lung MRI image and the absolute value of the difference value of the gray level representation values as image difference values, and taking the product value of the image difference values and the gray level discrete values as the image distribution parameter of the lung MRI image.

And performing edge detection on the lung MRI image, and identifying edge lines of the lung MRI image. It should be noted that, the method for obtaining the edge line by performing edge detection on the image is a well-known technique of those skilled in the art, and will not be described herein.

And determining the image salient parameters of the lung MRI image according to the overall gradient of the edge lines, wherein the gradient average value of all edge points on all edge lines is taken as the image salient parameters of the lung MRI image.

And combining the image distribution parameters and the image salient parameters to determine the identifiable degree of the lung region in the lung MRI image, wherein the product value of the image distribution parameters and the image salient parameters is used as the identifiable degree of the lung region in the lung MRI image.

The calculation formula of the identifiable degree is as follows:

;

Wherein R is the identifiable degree; The mean value of gray values of pixel points of the lung MRI image; Is a gray scale representation value; is a gray discrete value; the gradient mean value of the g-th edge line; g is the number of edge lines of the MRI image of the lung; Is an image distribution parameter.

Image distribution parametersThe smaller the product of (c), the closer the average gray value is to the intermediate value and the smaller the standard deviation, possibly indicating poor contrast; the average gradient value of all edge lines is represented, and the smaller the average gradient value is, the lower the overall gradient intensity in the lung MRI image is, and the unclear edges and details in the lung MRI image are represented; the larger the product of (2) is, the higher the recognizability of the lung region in the image is, i.e. the higher the recognizability R is.

Step S300, determining the confidence level of the identifiable degree according to the change condition of the identifiable degree of the image in the respiratory motion detection process. The image during respiratory motion detection is an MRI image of the lung during respiratory motion detection.

The quality of the lung MRI image is easily interfered by respiratory motion, and thus errors may be introduced in the actual detection process, resulting in inaccurate detection results, i.e. interference conditions caused by motion artifacts need to be further analyzed. And particularly analyzing the interference of the respiratory motion on the image recognizability.

In the process of acquiring the lung MRI image, a user is required to keep a certain static state or cooperate with a breathing instruction, but the breathing state of the user cannot completely meet the requirement of acquiring the image, namely the quality of the image can be influenced by the breathing state of the user, namely the image identification degree is required to be verified.

In the process of acquiring the lung MRI image of a user, the magnetic sensitive equipment is utilized to record the magnetic field change in the process, the magnetic induction intensity in the process is acquired by the magnetic sensitive equipment, the change of the magnetic induction intensity is used for representing the change of respiration, namely the magnetic sensitive equipment can reflect the respiration state through the recorded magnetic field change, then the time corresponding to the first peak value and the second peak value of the magnetic induction intensity is set as a preset respiration period, and an operator can manually set a preset respiration period.

And acquiring a lung MRI image sequence in a preset respiratory cycle, wherein the lung MRI image sequence is an image sequence which is formed by lung MRI images and is ordered according to acquisition time.

Sequencing the acquisition time of the lung MRI images in the lung MRI image sequence according to the sequence of the acquisition time to obtain a time sequence, sequencing the identifiable degree of the lung region in the lung MRI image according to the sequence of the acquisition time to obtain an identifiable degree sequence, and calculating the correlation coefficient of the time sequence and the identifiable degree sequence to obtain an identifiable degree correlation coefficient.

The method comprises the steps of collecting magnetic induction intensity in a corresponding preset respiratory period by using magnetic sensitive equipment, sequencing the magnetic induction intensity according to the sequence of collecting time to obtain a magnetic induction intensity sequence, and calculating correlation coefficients of the time sequence and the magnetic induction intensity sequence to obtain the magnetic induction intensity correlation coefficient. In the embodiment of the present invention, the correlation coefficient is pearson correlation coefficient, and in other embodiments, other methods for obtaining the correlation coefficient may be set by the practitioner. When the correlation coefficient is difficult to determine in the data in one preset respiratory cycle, the method can also be used for analyzing and calculating the correlation coefficient of the time sequence and the identifiable degree sequence corresponding to the lung MRI image sequences in the preset number of preset respiratory cycles, and the correlation coefficient of the time sequence and the magnetic induction intensity sequence. In the embodiment of the present invention, the preset number of values is 5, and in other embodiments, the value may be adjusted by an implementer according to the actual situation.

And normalizing the sequence elements of the recognizable degree sequence and the magnetic induction intensity sequence, and calculating the mean square error of the normalized sequence elements. Here, the standard deviation of the two sequence elements is performed to unify the dimensions of the two sequences. And calculating the absolute value of the difference value combining the identifiable degree correlation coefficient and the magnetic induction intensity correlation coefficient as an initial confidence degree, and taking the product value of the initial confidence degree and the mean square error as the confidence degree of the identifiable degree.

The calculation formula of the confidence coefficient w of the identifiable degree is as follows: Wherein, the method comprises the steps of, Is a recognizable degree correlation coefficient; Is the magnetic induction intensity correlation coefficient; Is an initial confidence; is the mean square error of the normalized sequence element.

Initial confidenceThe smaller the value of (2) is, the more synchronous the change of the identifiable degree of the lung region in the lung MRI image is in the change process of the respiratory motion is, namely the quality of the lung MRI image can be more disturbed by the respiratory motion; The larger the product is, the higher the confidence that the lung MRI image is poor in identification degree is, namely the acquired lung MRI image is low in quality, and the contrast condition of the lung MRI image can be further measured by combining a dynamic change process.

Step S400, determining the contrast benefit ratio of the lung MRI image according to the change trend of the lung MRI image sequence.

In the process of acquiring lung MRI images, a dynamic lung MRI image sequence is acquired. The dynamic lung MRI image sequence refers to the dynamic lung MRI image of each frame in the preset respiratory cycle, the contrast state of the lung MRI image can be further effectively identified through the change condition of the dynamic lung MRI image sequence, the quality of the lung MRI image can be further analyzed by combining the identification degree of the lung MRI image, and better data support is provided for subsequent lung MRI image processing.

After a lung MRI image sequence in a preset respiratory cycle is acquired, calculating the average value of pixel differences of pixel points at the same position of adjacent lung MRI images in the lung MRI image sequence to obtain signal differences.

Taking the ith lung MRI image and the (i+1) th lung MRI image as examples, the corresponding signal differencesThe calculation formula of (2) is as follows: M is the number of pixel points in the MRI image of the lung; the pixel value of the pixel point at the mth position in the ith lung MRI image is obtained; Is the pixel value of the pixel point at the mth position in the ith+1th lung MRI image.

The smaller the signal difference is, the smaller the signal intensity variation amplitude of the same tissue or different tissues in the adjacent lung MRI images is reflected, namely the boundary between the tissues in the dynamic lung MRI images is not obvious or fuzzy, and the poor contrast of the lung MRI images is indicated.

Further, a suspected lesion region and a normal region in the lung MRI image are identified. Through a large amount of lung lesion image data in the medical libraries, characteristics of the image data, such as shape, texture, signal intensity and the like, are extracted, the large amount of lung lesion image data in the medical libraries are manually marked, a deep learning model is trained, automatic learning is performed by using the U-net deep learning model, suspected lesion areas in lung MRI images are identified, and marking is performed.

Calculating the average value of the difference value between the gray average value of the suspected lesion area of the adjacent lung MRI image and the gray average value of the normal area in the lung MRI image sequence to obtain the area difference;

the contrast to benefit ratio of the lung MRI images is determined in combination with the signal differences and the region differences. In some embodiments, the negative correlation mapping value of the product of the signal difference and the region difference is used as the contrast benefit ratio of the lung MRI image.

The calculation formula of the contrast benefit ratio s is as follows: wherein exp is an exponential function based on a natural constant; is the signal difference; The difference value of the gray average value of the suspected lesion area and the gray average value of the normal area of the b group of adjacent lung MRI images; The average value of the difference value of the gray average value of the suspected lesion areas of the adjacent lung MRI images in the lung MRI image sequence and the gray average value of the normal areas is the area difference.

Region differenceThe smaller the value of (c) is, the less or substantially no change in gray scale in the sequence of lung MRI images is, meaning that the contrast of the lung MRI images is in a lower state; The larger the product, the larger the signal difference between tissues in the lung MRI image and the larger the gray scale variation in the lung MRI image sequence, i.e. the higher the contrast in the image, i.e. the higher the contrast benefit ratio of the lung MRI image, i.e. the larger the contrast benefit ratio s.

And S500, determining a contrast stretching coefficient of the lung MRI image by combining the confidence coefficient of the identifiable degree and the contrast beneficial ratio, and carrying out contrast enhancement on the lung MRI image based on the contrast stretching coefficient to obtain an enhanced lung detection image.

In the process of detecting benign and malignant lung lesions by using an MRI imaging group, the image contrast in an actually acquired lung MRI image may be poor, so that key details in the image are not highlighted, and in the process of carrying out contrast stretching by using histogram equalization, the situation that the key details are lost may occur, so that more accurate contrast stretching adjustment is required.

The contrast quality of the acquired MRI image of the lung lesions is further evaluated according to the data acquired in steps S100-S400, and then the contrast stretching coefficient of the image data is further acquired to realize contrast enhancement.

The calculation formula of the comparative stretch coefficient z is: Wherein th is hyperbolic tangent function for normalizing data, w is confidence of identifiability, and s is contrast benefit ratio.

The larger the product is, the higher the confidence that the identifiability of the lung MRI image is poor and the contrast of the lung MRI image is beneficial to be lower, namely, the contrast stretch coefficient z of the actual MRI image obtained by combining dynamic and static lung MRI image features is larger, and the quality of the obtained lung MRI image needs to be further improved, so that the features of the lesion area are more obvious.

And carrying out contrast enhancement on the lung MRI image based on the contrast stretching coefficient to obtain an enhanced lung detection image, wherein the contrast stretching coefficient of the obtained lung MRI image is followed by obtaining a gray value range in a suspected lesion area marked in the image, taking any gray value of the suspected lesion area as a gray value to be adjusted, taking the sum of the contrast stretching coefficient and a preset constant adjusting value as an adjusting coefficient of the gray value to be adjusted during histogram equalization, and carrying out histogram equalization operation directly on gray values except the gray value of the suspected lesion area. In the embodiment of the invention, the value of the preset constant adjustment value is 1. It can be understood that the adaptive histogram equalization operation is performed on the lung MRI image, that is, in the process of performing histogram equalization on the gray level in the marked suspected lesion area, the adjustment coefficient 1+z is used as the adjustment coefficient of all gray levels in the suspected lesion area, and the preset constant adjustment value is added to ensure that the contrast enhancement operation with the contrast stretch coefficient z as the adjustment value is performed on the basis of the conventional histogram equalization operation, and it can be understood that when z is 0, the corresponding adjustment coefficient is 1, and at this time, the default histogram equalization operation is performed on the gray level to be adjusted corresponding to z being 0. Also, it is equivalent to widening the gray level in the original image at the time of the conventional histogram equalization process.

It can be understood that the gray value after the conventional histogram equalization of the gray value to be adjusted is obtained first, the difference between the gray value to be adjusted and the gray value after the histogram equalization is taken as an initial widening value, the product of the adjustment coefficient 1+z and the initial widening value is taken as an adaptive widening value, and the sum of the gray value to be adjusted and the adaptive widening value is taken as the gray value of the gray value to be adjusted after the contrast enhancement. The gray value herein may be understood as a gray level at the time of histogram equalization. For example, for the initial gray level 50, after conventional histogram equalization, the gray level 50 is equalized to the gray level 70, the adjustment coefficient corresponding to the initial gray level 50 is 1.2, which corresponds to 20 for the gray level 50, after conventional histogram equalization, the spread value of the initial gray level 50 is 20, and for the gray level 70, the gray level corresponding to the gray level 50 adjusted by the adjustment coefficient 1.2 is 50+20×1.2=50+24=74. And then the gray level of the rest non-suspected lesion areas is equalized according to a default histogram, and then the lung MRI image with stretched contrast is obtained, namely the enhanced lung detection image.

As a preferred embodiment of the invention, the shape features of the lesions, such as the area, the perimeter, the irregular shape, the texture features and the like, are extracted through the lung detection image with enhanced contrast, so that the detection and classification of benign and malignant lesions are realized, and reliable data support is provided for subsequent diagnosis and treatment. For example, the lung lesion detection of the user corresponding to the lung MRI image can be realized by identifying the area of the suspected lesion region in the lung detection image.

Referring to fig. 2, a system block diagram of a lung lesion benign and malignant detection system using MRI imaging modality according to an embodiment of the present invention is shown, the system comprising the following modules:

the image acquisition module is used for acquiring lung MRI images;

Alternatively, the transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic, and digital subscriber lines, etc., or a wireless link, such as, but not limited to, wireless internet (WIRELESS FIDELITY, WIFI), bluetooth, and mobile device networks, etc.

It should be noted that, in the apparatus provided in the above embodiment, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to perform all or part of the functions described above.

The embodiment of the invention provides computer equipment. The computer device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, causes the computer device to perform any of the methods for detecting benign and malignant lung lesions using MRI imaging groups described above.

In addition, the embodiment of the invention also protects a device, which can comprise a memory and a processor, wherein executable program codes are stored in the memory, and the processor is used for calling and executing the executable program codes to execute the lung lesion benign and malignant detection method using the MRI imaging group.

The embodiment of the invention can divide the functional modules of the device according to the method example, for example, the functional modules can be corresponding, or two or more functions can be integrated into one processing module, and the integrated modules can be realized in a hardware form. It should be noted that, in this embodiment, the division of the modules is schematic, only one logic function is divided, and another division manner may be implemented in actual implementation.

In the case of dividing the respective modules by the respective functions, the apparatus may further include a signal uploading module, a determining module, an adjusting module, and the like. It should be noted that, all relevant contents of each step related to the above method embodiment may be cited to the functional description of the corresponding functional module, which is not described herein.

It should be understood that the apparatus provided in the embodiments of the present invention is used to perform the method for detecting benign and malignant lung lesions using MRI imaging set as described above, so that the same effects as those of the implementation method described above can be achieved.

In case of an integrated unit, the apparatus may comprise a processing module, a memory module. When the device is applied to equipment, the processing module can be used for controlling and managing the actions of the equipment. The memory module may be used to support devices executing inter-program code, etc. Wherein a processing module may be a processor or controller that may implement or execute the various illustrative logical blocks, modules, and circuits described in connection with the present disclosure. A processor may also be a combination of computing functions, including for example one or more microprocessors, digital Signal Processing (DSP) and microprocessor combinations, etc., and a memory module may be a memory.

In addition, the device provided by the embodiment of the invention can be a chip, a component or a module, the chip can comprise a processor and a memory which are connected, wherein the memory is used for storing instructions, and when the processor calls and executes the instructions, the chip can be made to execute the lung lesion benign and malignant detection method using the MRI imaging group provided by the embodiment.

The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores computer program code, and when the computer program code runs on a computer, the computer executes the related method steps to realize the lung lesion benign and malignant detection method using the MRI imaging group provided by the embodiment.

The embodiment of the invention also provides a computer program product, which when run on a computer, causes the computer to execute the related steps so as to realize the method for detecting benign and malignant lung lesions by using the MRI imaging group.

The apparatus, the computer readable storage medium, the computer program product, or the chip provided by the embodiments of the present invention are used to execute the corresponding method provided above, so that the beneficial effects thereof can be referred to the beneficial effects in the corresponding method provided above, and will not be described herein. It will be appreciated by those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above. In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners.

The above-described apparatus embodiments are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

It should also be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.

It should be noted that the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention.

Claims

1. A method for detecting benign and malignant lung lesions by using an MRI imaging set, comprising the steps of:

Acquiring a lung MRI image;

2. The method for detecting benign and malignant lung lesions by MRI imaging according to claim 1, wherein said analyzing the image distribution and image saliency of said MRI image of the lung to determine the degree of identification of the lung region in the MRI image of the lung comprises:

3. The method for detecting benign and malignant lung lesions by MRI imaging according to claim 2, wherein said analyzing the numerical stability of gray values of pixels of the MRI lung images, determining gray discrete values, comprises:

4. The method for detecting benign and malignant lung lesions by MRI imaging set according to claim 2, wherein said determining the image distribution parameters of the MRI lung images according to the gray scale representation values and the gray scale discrete values comprises:

5. The method for detecting benign and malignant lung lesions by MRI imaging set according to claim 1, wherein said determining the confidence level of the recognition level according to the change of the recognition level of the images during the respiratory motion detection process comprises:

acquiring a lung MRI image sequence in a preset respiratory cycle;

6. The method for detecting benign and malignant lung lesions by MRI imaging set according to claim 5, wherein said combining the identifiable degree correlation coefficient, the magnetic induction intensity correlation coefficient, the identifiable degree sequence and the magnetic induction intensity sequence to obtain the confidence of the identifiable degree comprises:

7. The method for detecting benign and malignant lung lesions by MRI imaging set according to claim 1, wherein said determining the contrast-to-benefit ratio of the MRI lung images according to the trend of the MRI lung image sequence comprises:

acquiring a lung MRI image sequence in a preset respiratory cycle;

8. The method for detecting benign and malignant lung lesions using MRI imaging set according to claim 7, wherein said combining signal differences and regional differences to determine the contrast-to-benefit ratio of the MRI images of the lung comprises:

9. The method for detecting benign and malignant lung lesions using MRI imaging set according to claim 1, wherein said determining the contrast stretch factor of the MRI image of the lung in combination with the confidence level of the intelligibility and the contrast benefit ratio comprises:

10. The method for detecting benign and malignant lung lesions by MRI imaging according to claim 1, wherein said contrast enhancement of said MRI image of lung based on said contrast stretch factor, resulting in an enhanced lung detection image, comprises:

identifying a suspected lesion region in the lung MRI image;