WO2021259391A2

WO2021259391A2 - Image processing method and apparatus, and electronic device and storage medium

Info

Publication number: WO2021259391A2
Application number: PCT/CN2021/122143
Authority: WO
Inventors: 隋雨桐; 吴振洲; 刘盼
Original assignee: 北京安德医智科技有限公司
Priority date: 2021-03-01
Filing date: 2021-09-30
Publication date: 2021-12-30
Also published as: WO2021259391A3; CN112967291A; CN112967291B

Abstract

The present disclosure relates to an image processing method and apparatus, and an electronic device and a storage medium. The method comprises: segmenting an image to be processed, and determining an organ region corresponding to a target organ in said image, and a lesion region corresponding to a lesion on the target organ; according to the positions of the organ region and the lesion region, determining, from the organ region, an abnormal sub-region which may correspond to an organ part bearing the lesion; determining a lesion interface between the abnormal sub-region and the lesion region according to a positional relationship between a first pixel point in the abnormal sub-region and a second pixel point in the lesion region; and according to the lesion interface and the lesion region, determining a morphological analysis result of the lesion. According to the embodiments of the present disclosure, a morphological analysis result of a lesion in an image can be automatically and accurately determined, such that the workload of medical staff is reduced, and the working efficiency of medical staff is improved.

Description

Image processing method and device, electronic equipment and storage medium

Technical field

The present disclosure relates to the field of computer vision technology, and in particular to an image processing method and device, electronic equipment, and storage medium.

Background technique

In the field of computer vision technology, image recognition and analysis are widely used. For example, the recognition and analysis of lesion areas in medical images is the basis of disease diagnosis.

In related technologies, there are two types of methods for the identification and morphological analysis of the lesion area in medical images.

First, through the doctor's interpretation of medical images to identify and analyze the lesion area, the doctor can manually measure the lesion area, obtain the morphological parameters of the lesion area, and give the diagnosis result. However, the manual measurement of the diseased area by the doctor will have a difference in measurement consistency, which is more dependent on the doctor's diagnostic level and clinical experience, and some doctors may even experience misdiagnosis and missed diagnosis.

Second, the computer-assisted identification and analysis of the lesion area requires doctors to assist in determining certain characteristic points and characteristic areas in medical images. For example, to calculate the morphological parameters of aneurysms in medical images, doctors are required to assist in determining the neck point of the tumor. Or tumor neck plane. However, in the process of doctor's assistance, it is easy to introduce artificial errors.

Summary of the invention

In view of this, the present disclosure proposes an image processing method and device, electronic equipment, and storage medium.

According to an aspect of the present disclosure, there is provided an image processing method, the method comprising: segmentation processing an image to be processed, determining an organ region corresponding to a target organ in the image to be processed, and The lesion area corresponding to the lesion; according to the position of the organ area and the lesion area, an abnormal sub-area is determined from the organ area, and the abnormal sub-area corresponds to the part of the organ that carries the lesion; according to the The positional relationship between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area to determine the lesion interface between the abnormal sub-region and the lesion area; according to the lesion interface And the lesion area to determine the morphological analysis result of the lesion.

In a possible implementation, according to the positional relationship between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area, determine the difference between the abnormal sub-region and the lesion area. The boundary between the lesions includes: determining a boundary reference point from the first pixel point and the second pixel point according to the distance between the first pixel point and the second pixel point; The number of dividing reference points in the multiple reference planes is set, and the lesion interface is determined from the multiple reference planes, wherein the multiple reference planes are respectively perpendicular to each coordinate of the image coordinate system of the image to be processed axis.

In a possible implementation manner, determining a demarcation reference point from the first pixel and the second pixel according to the distance between the first pixel and the second pixel includes : For any first pixel, determine the first distance between the first pixel and each second pixel in the lesion area; if there is a first distance less than or equal to the distance threshold, Determine the first pixel point as a demarcation reference point; for any second pixel point, determine the second distance between the second pixel point and each first pixel point in the abnormal sub-region; In the case of a second distance less than or equal to the distance threshold, the second pixel point is determined as the demarcation reference point.

In a possible implementation manner, determining an abnormal sub-region from the organ area according to the positions of the organ area and the lesion area includes: obtaining a first spatial area circumscribing the lesion area; according to A preset expansion coefficient is used to expand the first spatial area to obtain an expanded second spatial area; among the second spatial areas, the spatial areas that belong to the organ area and do not belong to the lesion area, Determined as the abnormal sub-region.

In a possible implementation manner, the result of the morphological analysis of the lesion includes morphological parameters of the lesion, and the morphological parameters include a reference diameter, a maximum diameter, a width, and a height. The boundary and the lesion area, and determining the morphological analysis result of the lesion includes: among the boundary reference points included in the lesion boundary, the distance between the two boundary reference points with the largest distance is determined as the The reference diameter of the lesion; among the second pixels included in the lesion area, the maximum distance between the second pixel and the geometric center of the interface of the lesion is determined as the maximum diameter of the lesion; in the lesion area Among the included second pixel points, in the direction perpendicular to the maximum diameter, the distance between the two second pixel points with the largest distance is determined as the width of the lesion; the second pixel included in the lesion area Among the points, the maximum distance between the second pixel point and the interface of the lesion is determined as the height of the lesion.

In a possible implementation manner, performing segmentation processing on the image to be processed, and determining the organ area corresponding to the target organ in the image to be processed, and the lesion area corresponding to the lesion on the target organ, includes: Perform normalization processing on the image to obtain a processed first image; perform a first segmentation process on the first image to determine organ regions in the first image; perform a second segmentation process on the first image, Determine the lesion area in the first image.

In a possible implementation manner, performing a first segmentation process on the first image to determine the organ region in the first image includes: cutting the first image according to a first preset size, Obtain a first sampled image block; input the first sampled image block into a first segmentation network for segmentation to obtain a segmentation result of the first sampled image block; fuse the segmentation results of a plurality of first sampled image blocks, Obtaining the organ area in the first image;

Wherein, performing a second segmentation process on the first image to determine the lesion area in the first image includes: cutting the first image according to a second preset size to obtain a second sampled image block; The second sampled image block is input into the second segmentation network for segmentation to obtain the segmentation result of the second sampled image block; the segmentation results of multiple second sampled image blocks are merged to obtain the first image Of the lesion area.

In a possible implementation manner, the image to be processed includes a three-dimensional angiographic image, the target organ includes a blood vessel, the lesion on the target organ includes an aneurysm, and the abnormal sub-region includes a tumor-bearing artery region, The lesion interface includes the aneurysm neck plane.

According to one aspect of the present disclosure, there is provided an image processing device, including: a segmentation module for performing segmentation processing on an image to be processed, determining an organ region corresponding to a target organ in the image to be processed, and The lesion area corresponding to the lesion on the organ; the abnormal sub-area determining module is used to determine the abnormal sub-area from the organ area according to the position of the organ area and the lesion area, and the abnormal sub-area corresponds to the bearing The organ part of the lesion; the lesion interface determination module, configured to determine the abnormal subregion according to the positional relationship between the first pixel point in the abnormal subregion and the second pixel point in the lesion region The lesion interface with the lesion area; the lesion analysis module is used to determine the morphological analysis result of the lesion according to the lesion interface and the lesion area.

According to another aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to call the instructions stored in the memory to execute The above method.

According to another aspect of the present disclosure, there is provided a non-volatile computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions implement the above method when executed by a processor.

In the embodiment of the present disclosure, the organ area and the lesion area are determined by segmenting the image to be processed, and the lesion interface is determined according to the positional relationship between the organ area and the lesion area; finally, the lesion interface is determined according to the lesion interface and the lesion area. Morphological analysis results of the lesion. This method can automatically and accurately determine the morphological analysis result of the lesion in the image, thereby reducing the workload of medical staff and improving the work efficiency of medical staff.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, rather than limiting the present disclosure. According to the following detailed description of exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present disclosure will become clear.

Description of the drawings

The drawings included in the specification and constituting a part of the specification together with the specification illustrate exemplary embodiments, features, and aspects of the present disclosure, and are used to explain the principle of the present disclosure.

Fig. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure;

Fig. 2 shows a schematic diagram of an abnormal sub-region according to an embodiment of the present disclosure;

Fig. 3 shows a schematic diagram of a morphological analysis result of a lesion according to an embodiment of the present disclosure;

Fig. 4 shows a block diagram of an image processing device according to an embodiment of the present disclosure;

Figure 5 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

FIG. 6 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

detailed description

Hereinafter, various exemplary embodiments, features, and aspects of the present disclosure will be described in detail with reference to the drawings. The same reference numerals in the drawings indicate elements with the same or similar functions. Although various aspects of the embodiments are shown in the drawings, unless otherwise noted, the drawings are not necessarily drawn to scale.

The dedicated word "exemplary" here means "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" need not be construed as being superior or better than other embodiments.

The term "and/or" in this article is only an association relationship that describes the associated objects, which means that there can be three relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, exist alone B these three situations. In addition, the term "at least one" in this document means any one of a plurality of or any combination of at least two of the plurality, for example, including at least one of A, B, and C, and may mean including A, Any one or more elements selected in the set formed by B and C.

In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. Those skilled in the art should understand that the present disclosure can also be implemented without certain specific details. In some instances, the methods, means, elements, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the gist of the present disclosure.

Fig. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure. As shown in Fig. 1, the image processing method includes:

In step S11, segmentation processing is performed on the image to be processed, and the organ area corresponding to the target organ in the image to be processed is determined, and the lesion area corresponding to the lesion on the target organ is determined;

In step S12, according to the positions of the organ area and the lesion area, an abnormal sub-area is determined from the organ area, and the abnormal sub-area corresponds to the part of the organ that carries the lesion;

In step S13, according to the positional relationship between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area, the lesion division between the abnormal sub-region and the lesion area is determined. interface;

In step S14, the morphological analysis result of the lesion is determined according to the interface of the lesion and the area of the lesion.

In a possible implementation manner, the image processing method can be executed by electronic devices such as a terminal device or a server, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, etc., and other processing equipment It can be a server or a cloud server, etc. In some possible implementation manners, the image processing method may be implemented by a processor invoking computer-readable instructions stored in the memory. Alternatively, the method can be executed by the server.

In a possible implementation, the image to be processed may be a medical image, which may be an image taken by various types of medical equipment, or an image used for medical diagnosis, for example, a computer tomography (Computed Tomography). , CT) images or MRI (Magnetic Resonance Imaging, MRI) images, etc. The present disclosure does not limit the type of image to be processed and the specific acquisition method.

In a possible implementation, the image to be processed may be a three-dimensional medical image, for example, including a three-dimensional angiography image. In order to describe the position of organs, tissues or lesions in the image to be processed more specifically in the clinic, the Coronal View, Sagittal View and Axial View can be set in the three-dimensional medical image;

Among them, the coronal position can mean the position where the human body is longitudinally cut into the front and back parts along the long axis of the human body, the sagittal position can mean the position where the human body is longitudinally cut into the left and right parts along the long axis of the human body, and the axis position can mean the position along the long axis of the human body. The human body is transversely cut into the upper and lower parts in the horizontal direction. The coronal position, the sagittal position and the axial position can be equivalent to the position of the coordinate axis in the rectangular coordinate system formed by xyz.

In a possible implementation manner, the image to be processed includes a target organ and a lesion on the target organ. For example, the target organ of the image to be processed may be an intracranial blood vessel, a coronary artery of the heart, a pulmonary artery, etc., and a lesion on the target organ It may be an intracranial saccular aneurysm, coronary aneurysm, pulmonary aneurysm, etc. The present disclosure does not limit specific target organs and lesions on the target organs. Among them, there may be one or more lesions on the target organ, and the present disclosure does not limit the number of lesions on the target organ.

In a possible implementation manner, before segmenting the image to be processed, the image to be processed may be preprocessed to facilitate subsequent image segmentation processing. Among them, the preprocessing may include unifying the resolution of the physical space (Spacing) of the image to be processed, unifying the range of pixel values in the image to be processed, and performing regional cropping on the image to be processed, and so on. In this way, the image size can be unified, the amount of data to be processed can be reduced, and subsequent image segmentation operations can be facilitated. The present disclosure does not limit the specific content and processing method of preprocessing.

In a possible implementation manner, in step S11, the image to be processed may be segmented to determine the organ region corresponding to the target organ in the image to be processed, and the lesion corresponding to the lesion on the target organ Area; wherein the target organ includes, for example, blood vessels, and the lesion on the target organ includes, for example, aneurysms.

For example, the image to be processed is a three-dimensional medical image, and the image may include a target organ and one or more lesions on the target organ. By performing segmentation processing on the image to be processed, a segmentation result can be obtained, the result including the organ area corresponding to the target organ in the image to be processed, and the lesion area corresponding to the lesion on the target organ. For example, the image to be processed is an intracranial angiography image, and segmentation of the image can be performed to obtain the segmentation result. The result includes the blood vessel area in the intracranial angiography image and the lesion where one or more aneurysms on the blood vessel are located. area.

In a possible implementation, since the target organ and the lesion on the target organ are in a state of adhesion on the image to be processed, there may be overlapping areas between the organ area and the lesion area determined after the segmentation process, that is, there may be One or more pixels belong to both the organ area and the lesion area.

In a possible implementation manner, in the process of performing segmentation processing on the image to be processed, the segmentation result can be obtained through one segmentation processing. In the segmentation result, each pixel in the organ area can be marked as 1, each pixel in the lesion area carried on the organ can be marked as 2, and each pixel in other background areas can be marked as 0. By performing a segmentation process on the image to be processed, the organ area and the lesion area can be quickly obtained.

Or, in the process of segmenting the image to be processed, the segmentation result can be obtained through two segmentation processing. That is, the first segmentation process can be performed on the image to be processed to obtain the first segmentation result. In the first segmentation result, each pixel in the organ area can be marked as 1, and each pixel in the background area outside the organ area can be marked as 0. . According to the first segmentation result, the organ region of the image to be processed can be determined. The second segmentation result can be obtained by performing the second segmentation process on the image to be processed. In the second segmentation result, each pixel in the lesion area carried on the target organ can be marked as 1, and each pixel in the background area outside the lesion area can be Marked as 0. According to the second segmentation result, the lesion area of the image to be processed can be determined. By performing two segmentation processing on the image to be processed, the information of the image to be processed can be fully utilized to obtain more accurate segmentation results.

It should be understood that the present disclosure can perform the first segmentation processing and the second segmentation processing on the image to be processed in parallel, or perform the second segmentation processing on the image to be processed first, and then perform the first segmentation processing. The sequence of the two segmentation processing and There is no restriction on the split processing method.

In a possible implementation, in step S12, an abnormal sub-region is determined from the organ region according to the positions of the organ region and the lesion region, and the abnormal sub-region corresponds to bearing the lesion. Part of the organ. Wherein, the abnormal sub-region includes, for example, the tumor-bearing artery region.

For example, since the organ area contains a large amount of pixel data, in the process of obtaining the morphological analysis results of the lesion based on the organ area and the lesion area, the data of some pixels in the organ area far away from the lesion area does not affect the shape of the lesion Learn to analyze the results.

In order to reduce the amount of data calculation and improve the efficiency of calculation, according to the positional relationship between the organ area and the lesion area, an abnormal sub-area that will affect the morphological analysis result of the lesion can be determined from the organ area. The abnormal sub-area corresponds to the bearing lesion. Organ part, that is, the sub-area part of the organ area adjacent to the lesion area. Among them, in order to improve the accuracy of the morphological analysis results of the lesion, in the process of determining the abnormal subregion from the organ area according to the position of the organ area and the lesion area, the overlapping area in both the organ area and the lesion area can be removed.

Wherein, each lesion in the lesion area corresponds to an abnormal sub-area, and the organ area may include one or more abnormal sub-areas. The present disclosure can determine the abnormal sub-regions corresponding to each lesion one by one, or determine the abnormal sub-regions corresponding to each lesion in parallel, which is not limited in the present disclosure.

In a possible implementation manner, in step S13, according to the positional relationship between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area, it is determined that the abnormal sub-region and The lesion interface between the lesion areas. Wherein, the lesion interface includes, for example, the aneurysm neck plane.

For example, according to the abnormal sub-region and the lesion area, determine the lesion interface between the two, which can be based on the positional relationship between the first pixel point included in the abnormal sub-region and the second pixel point included in the lesion area , To determine the lesion interface between the abnormal sub-area and the lesion area. For example, the abnormal sub-area is the tumor-bearing blood vessel area in the blood vessel area, and the lesion area is the aneurysm area. The carrier can be determined according to the positional relationship between the first pixel in the tumor-bearing blood vessel area and the second pixel in the aneurysm area. The interface between the tumor blood vessel area and the aneurysm area, which is the plane of the tumor neck.

In a possible implementation manner, in step S14, the morphological analysis result of the lesion is determined according to the interface of the lesion and the area of the lesion.

For example, the lesion interface and the lesion area can be obtained according to the above steps, and the morphological analysis result of the lesion can be determined. That is, the morphological analysis result of the lesion area can be determined according to the positional relationship between the boundary reference point in the lesion interface and the second pixel point in the lesion area. Among them, the morphological analysis result of the lesion may include multiple morphological parameters of the lesion, for example, the reference diameter, maximum diameter, width, and height of the lesion.

In this way, the morphological analysis results of the lesion can be automatically determined without the assistance of the doctor, which can avoid errors caused by the doctor’s manual intervention, improve the accuracy of the morphological analysis results of the lesion, and reduce the doctor’s Workload, improve the work efficiency of medical staff.

The following is an expanded description of the image processing method according to the embodiment of the present disclosure.

In a possible implementation, step S11 may include: performing normalization processing on the image to be processed to obtain a processed first image; performing a first segmentation process on the first image to determine that the first image is The organ area of the first image is subjected to a second segmentation process to determine the lesion area in the first image.

For example, the image to be processed is normalized, that is, the pixel value of each pixel in the image to be processed is normalized to a value range of 0-1, so as to improve the processing efficiency. For example, assuming that the image to be processed is an 8-bit grayscale image and the pixel value of each pixel ranges from 0 to 255, the pixel value of each pixel can be divided by 255 to normalize the pixel value of each pixel in the image to be processed to Within the value range of 0-1. After normalizing the image to be processed, the first image can be obtained. It is understandable that the normalization method may include, but is not limited to, linear function normalization (Min-Max Scaling), zero-mean normalization (Z-Score Standardization), non-linear normalization, etc. The present disclosure does not limit the normalization method .

In a possible implementation manner, after the normalized first image is obtained, the first segmentation process can be performed on the first image, and the first segmentation result can be obtained. The result includes the organ region where the target organ is located, and The background area outside the organ area. For example, the first image is a normalized intracranial angiography (CT Angiography, CTA) image. The first segmentation process can be performed on the image, and the first segmentation result obtained is the blood vessel in the intracranial angiography image. Area, and the background area outside the blood vessel area. The first segmentation result may be a binary label, that is, the blood vessel area in the intracranial angiography image is marked as 1, and the background area outside the blood vessel area is marked as 0.

In a possible implementation manner, the first segmentation network may be preset to perform the first segmentation processing on the first image to determine the organ region where the target organ is located in the first image. The first segmentation network can be a deep convolutional neural network, including multiple convolutional layers, multiple deconvolutional layers, fully connected layers, etc. The specific segmentation networks that can be used include but are not limited to U Network (U-Network, U-Network). NET), V-Network (V-NET) and other network structures. The present disclosure does not limit the specific network structure of the first segmented network.

Refer to the above-mentioned first segmentation processing method to perform the second segmentation processing on the first image to obtain the second segmentation result. The result includes the lesion area where the lesion on the target organ is located and the background area outside the lesion area. For example, the first image is a normalized intracranial angiography (CT Angiography, CTA) image, and the second segmentation process can be performed on the image to obtain the second segmentation result, that is, the blood vessels in the intracranial angiography image The aneurysm area on the area, and the background area outside the aneurysm area; where the second segmentation result can be a binary label, that is, the aneurysm area in the intracranial angiography image is marked as 1, and the background outside the blood vessel area The area is marked as 0.

In a possible implementation manner, a second segmentation network may be preset to perform a second segmentation process on the second image to determine the lesion area where the lesion on the target organ in the second image is located. The second segmentation network can be a deep convolutional neural network, including multiple convolutional layers, multiple deconvolutional layers, fully connected layers, etc. The specific segmentation networks that can be used include but are not limited to U Network (U-Network, U-Network). NET), V-Network (V-NET) and other network structures. The present disclosure does not limit the specific network structure of the second split network.

In this way, the organ area and the lesion area in the first image can be automatically segmented without the assistance of a doctor.

In a possible implementation manner, performing a first segmentation process on the first image in step S11 to determine the organ region in the first image includes: performing a first segmentation process on the first image according to a first preset size Perform cutting to obtain a first sampled image block; input the first sampled image block into a first segmentation network for segmentation to obtain a segmentation result of the first sampled image block; segmentation results for a plurality of first sampled image blocks Performing fusion to obtain the organ region in the first image;

For example, in the process of performing the first segmentation process on the first image, the first preset size may be set so that the sizes of the first sampled image blocks input to the first segmentation network are consistent. For example, suppose the size of the first image is 256×512×512, that is, there are 256 pixels in the z-axis direction (that is, the direction of the medical image slice pitch), and the x-axis (width) direction and the y-axis (height) direction are respectively 512 pixels. The first preset size can be set to 64×384×384, that is, there are 64 pixels in the z-axis direction, and 384 pixels in the x-axis direction and y-axis direction respectively.

The first image can be cut with overlap in the x-axis direction, y-axis direction and z-axis direction according to a fixed cutting step length to obtain multiple cut image blocks with a first preset size of 64×384×384. Each cut image block is the first sampled image block. Part of the image areas of the adjacent multiple first sampled image blocks overlap. Wherein, the number of first sampled image blocks and the size of the overlapping area of each first sampled image block can be determined according to the first preset size and the cutting step. The present disclosure does not limit the first preset size and cutting step length.

The multiple first sampling image blocks are input into the first segmentation network for processing, and the segmentation results of the multiple first sampling blocks can be obtained. According to the cutting position of each first sampled image block, multiple first sampled image blocks can be merged to obtain the first segmentation result.

Among them, in the process of fusing multiple first sampled image blocks, each pixel can be respectively fused according to the coordinate position in the first image corresponding to each first sampled image block, to obtain the same size as the first image Fusion result. The fusion result includes the probability that each pixel in the first image belongs to the organ area. The predicted probability that each pixel belongs to the organ area can be binarized based on a preset threshold. For example, each pixel that is larger than the preset threshold can be binarized. Marked as 1, the area it represents is the organ area; each pixel that is less than or equal to the preset threshold can be marked as 0, and the area it represents is the background area. Finally, it is also possible to filter each connected domain (that is, the connected domain formed by the pixels marked as 1) in the fusion result, and remove the connected domains whose volume is less than a certain threshold to obtain the first segmentation result. That is, the organ area in the first image.

In this way, the first image is overlapped and cut, and each acquired first sampled image block is input into the first segmentation network to obtain the segmentation results of multiple first sampled image blocks. Finally, the first image is divided into multiple first sampled image blocks. The segmentation results of the sampled image blocks are fused to obtain the organ regions in the first image, which can make full use of the information in the first image to improve the accuracy of image segmentation.

In a possible implementation manner, performing a second segmentation process on the first image to determine the lesion area in the first image includes: cutting the first image according to a second preset size, Obtain a second sampled image block; input the second sampled image block into a second segmentation network for segmentation to obtain a segmentation result of the second sampled image block; fuse the segmentation results of a plurality of second sampled image blocks, Obtain the lesion area in the first image.

It should be understood that for performing the second segmentation processing on the first image to determine the lesion area in the first image, reference may be made to the above process of performing the first segmentation processing on the first image to determine the organ area, which will not be repeated here. Wherein, the second preset size may be the same as the first preset size, or may be different from the first preset size, which is not limited in the present disclosure.

The segmentation process is performed in step S11, and after the segmentation result is obtained, the abnormal subregion can be determined in step S12 according to the organ area and the lesion area in the segmentation result.

In a possible implementation manner, step S12 may include: obtaining a first spatial area circumscribing the lesion area; expanding the first spatial area according to a preset expansion coefficient to obtain an expanded second Spatial area; in the second spatial area, a spatial area that belongs to the organ area and does not belong to the lesion area is determined as the abnormal sub-area.

For example, FIG. 2 shows a schematic diagram of an abnormal sub-region according to an embodiment of the present disclosure. As shown in FIG. 2, the first spatial area circumscribed by the lesion area (the aneurysm area shown in FIG. 2 ), that is, the area of the dashed frame A1 shown in FIG. 2 is obtained. Then, the geometric center of the circumscribed first space area is calculated, and the geometric center is taken as the center, and the first space area is expanded according to the preset expansion coefficient to obtain the expanded second space area, which is shown in Figure 2. A2 area shown in the dashed frame.

As shown in Figure 2, in the second spatial region (A2 in Figure 2), the spatial region that belongs to the organ region (the blood vessel region in Figure 2) and does not belong to the lesion region (the aneurysm region in Figure 2) is determined as The abnormal sub-area is the gray area in FIG. 2.

The first spatial region circumscribed by the lesion area may be a rectangular parallelepiped, a sphere, an ellipsoid, or other three-dimensional geometric figures, and the present disclosure does not limit the specific shape of the first spatial region. The preset expansion coefficient is a positive real number greater than 1, which can be set according to the experience of the clinician. The present disclosure does not limit the value of the specific expansion coefficient.

It should be understood that the lesion area may include one or more connected areas, and each connected area may correspond to a lesion. In the case where the lesion area includes multiple lesions, the image processing method of the present disclosure can process each connected area in the lesion area in parallel according to the method in step S12 to obtain an abnormal sub-region corresponding to each connected area.

In this way, according to the position of the organ area and the lesion area, the abnormal sub-area can be determined from the organ area, which can eliminate the overlap between the abnormal sub-area and the lesion area, which not only reduces the amount of processing to be processed, improves the calculation efficiency, but also benefits Improve the accuracy of the lesion interface in the subsequent steps.

After the abnormal subregion is obtained in step S12, the lesion interface can be determined according to the abnormal subregion and the lesion region in step S13.

In a possible implementation manner, step S13 may include: determining from the first pixel point and the second pixel point according to the distance between the first pixel point and the second pixel point Demarcation reference points; according to the number of demarcation reference points in a plurality of preset reference planes, a lesion interface is determined from the plurality of reference planes, wherein the plurality of reference planes are respectively perpendicular to the image to be processed Each coordinate axis of the image coordinate system.

For example, according to the distance between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area, from the first pixel point and the second pixel point, the first pixel point and the second pixel point Each pixel with a distance less than or equal to the distance threshold is determined as the demarcation reference point. Among them, the distance threshold can be set according to the clinician's experience, which is not limited in the present disclosure.

After the demarcation reference points are obtained, the number of demarcation reference points in each of the multiple preset reference planes can be detected, the reference plane containing the most demarcation reference points can be determined, and the demarcation reference points in the reference plane can be formed The area is determined to be the boundary of the lesion.

Wherein, a plurality of preset reference planes are respectively perpendicular to each coordinate axis of the image coordinate system of the image to be processed. For example, suppose that the image coordinate system of the image to be processed is an xyz rectangular coordinate system, and each coordinate axis is an x-axis, a y-axis, and a z-axis. The reference plane may include planes perpendicular to the x-axis (that is, parallel to the yoz plane), the y-axis (that is, parallel to the xoz plane), and the z-axis (that is, parallel to the xoy plane).

It should be understood that in actual clinical diagnosis, doctors can determine the interface of the lesion based on the coronal, sagittal or axial two-dimensional slice images. The reference plane preset in the present disclosure can represent the coronal, sagittal Each two-dimensional slice image on the position or axis position.

In this way, it is possible to highly simulate the process of clinicians determining the lesion interface, improve the accuracy of the lesion interface, and help improve the accuracy of the morphological analysis results of the lesion in the subsequent steps.

In a possible implementation manner, in step S13, according to the distance between the first pixel and the second pixel, a boundary reference is determined from the first pixel and the second pixel. Points, including:

For any first pixel, determine the first distance between the first pixel and each second pixel in the lesion area; if there is a first distance less than or equal to the distance threshold, change The first pixel point is determined as a demarcation reference point;

For any second pixel, determine the second distance between the second pixel and each first pixel in the abnormal sub-region; in the case where there is a second distance less than or equal to the distance threshold Next, the second pixel point is determined as the demarcation reference point.

For example, suppose that the abnormal sub-region includes N1 first pixel points P _i , where i=1, 2, ..., N1, N1 is a positive integer; the lesion area includes N2 second pixel points Q _j , where j =1, 2,..., N2, N2 are positive integers, and the values of N2 and N1 may be equal or unequal, which is not limited in the present disclosure.

For any of the first pixel P _i, P _i is determined first pixel and the second pixel each Q _j (i.e., _{_{Q 1, Q 2, ...,}} Q N2) between the first distance L _ij = | P _i -Q _j |.

For example: the first distance L _i1 between the first pixel point P _i and the second pixel point Q ₁ =|P _i -Q ₁ |;

The first distance _Li2 between the first pixel point P _i and the second pixel point Q ₂ = |P _i -Q ₂ |;

By analogy, the first distance L _iN2 between the first pixel point P _i and the second pixel point Q _N2 = |P _i -Q _N2 |;

In the case where the first distance _L _i1 ~ L iN2 present in less than or equal to a first threshold distance of the first pixel point P _i is determined as a boundary reference point. Among them, the distance threshold can be set according to the experience of the clinician, which is not limited in the present disclosure.

Similarly, for any second pixel point Q _j , determine the second distance L _ji between the second pixel point Q _j and each first pixel point P _i (that is, P ₁ , P ₂ ,..., P _N1) |Q _j -P _i |.

For example: the second distance L _j1 between the second pixel point Q _j and the first pixel point P ₁ = |Q _j -P ₁ |;

The second distance L _j2 between the second pixel point Q _j and the first pixel point P ₂ = |Q _j -P ₂ |;

By analogy, the second distance L _jN1 between the second pixel point Q _j and the first pixel point P _N1 = |Q _j -P _N1 |;

In the case where there is a second distance less than or equal to the distance threshold in the second distances L _j1 _{˜L jN1} _{, the second pixel point Q j is} determined as the demarcation reference point.

It should be understood that in the process of determining a first pixel P _i and the pixel _j from the second point Q can be calculated by the Euclidean distance between the two pixels (Euclidean Distance), Mahalanobis distance (Mahalanobis Distance), Manhattan distance (Manhattan Distance) or other distance measurement methods, the present disclosure does not limit the specific distance measurement methods.

In this way, without manual interaction, the demarcation reference point can be automatically determined according to the distance between the first pixel and the second pixel. This method is simple and convenient, easy to implement, and is beneficial to the rapid determination of the subsequent lesion interface.

After the lesion interface is obtained in step S13, the morphological analysis result of the lesion can be determined according to the lesion interface and the lesion area in step S14.

In a possible implementation, the morphological analysis result of the lesion includes morphological parameters of the lesion, and the morphological parameters include a reference diameter, a maximum diameter, a width, and a height. Step S14 may include:

Among the demarcation reference points included in the lesion interface, the distance between the two demarcation reference points with the largest distance is determined as the reference diameter of the lesion;

Among the second pixels included in the lesion area, determining the maximum distance between the second pixel and the geometric center of the interface of the lesion as the maximum diameter of the lesion;

In the second pixel points included in the lesion area, in a direction perpendicular to the maximum diameter, the distance between the two second pixel points with the largest distance is determined as the width of the lesion;

Among the second pixels included in the lesion area, the maximum distance between the second pixel and the interface of the lesion is determined as the height of the lesion.

For example, FIG. 3 shows a schematic diagram of a morphological analysis result of a lesion according to an embodiment of the present disclosure. As shown in FIG. The distance between points M2 is the largest. The distance between the demarcation reference point M1 and the demarcation reference point M2 can be determined as the reference diameter of the lesion, that is, the tumor neck shown in FIG. 3.

Among the second pixel points included in the lesion area, the distance between the second pixel point M3 and the geometric center M0 of the interface of the lesion is the largest. The distance between the second pixel point M3 and the geometric center M0 of the interface of the lesion can be determined as the maximum diameter of the lesion.

Among the second pixel points included in the lesion area, in the direction of the vertical maximum diameter, the distance between the second pixel point M4 and the second pixel point M5 is the largest, and the second pixel point M4 and the second pixel point M5 can be separated The distance between them is determined as the width of the lesion, that is, the width of the tumor as shown in Figure 3.

The direction of the largest diameter is the direction of the straight line determined by the geometric center M0 of the interface between the second pixel point M3 and the lesion.

Among the second pixel points included in the lesion area, the distance between the second pixel point M3 and the plane where the lesion interface is located is the largest, and the vertical foot from the second pixel point M3 to the plane where the lesion interface is located is M6. The distance between the point M3 and the plane where the interface of the lesion is located is determined as the height of the lesion, that is, the height of the tumor as shown in FIG. 3.

In this way, the morphological analysis result of the lesion is determined according to the lesion interface and the area of the lesion, and the morphological analysis result of the lesion can be determined automatically and accurately without the assistance of the doctor, which reduces the workload of the doctor and improves The efficiency of the doctor’s diagnosis and treatment.

Therefore, according to the image processing method of the embodiment of the present disclosure, the organ area and the lesion area can be determined by segmentation of the image to be processed, and the lesion interface can be determined according to the positional relationship between the organ area and the lesion area; finally according to the lesion interface As well as the area of the lesion, the morphological analysis result of the lesion is determined. This method can automatically and accurately determine the morphological analysis result of the lesion in the image, thereby reducing the workload of medical staff and improving the work efficiency of medical staff.

It can be understood that, without violating the principle logic, the various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment, which is limited in length and will not be repeated in this disclosure. Those skilled in the art can understand that, in the above-mentioned method of the specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

In addition, the present disclosure also provides image processing devices, electronic equipment, computer-readable storage media, and programs, all of which can be used to implement any image processing method provided in the present disclosure. For the corresponding technical solutions and descriptions, refer to the corresponding records in the method section. ,No longer.

Fig. 4 shows a block diagram of an image processing device according to an embodiment of the present disclosure. As shown in Fig. 4, the device includes:

The segmentation module 41 is configured to perform segmentation processing on the image to be processed, and determine the organ area corresponding to the target organ in the image to be processed, and the lesion area corresponding to the lesion on the target organ;

The abnormal sub-region determination module 42 is configured to determine an abnormal sub-region from the organ region according to the positions of the organ region and the lesion region, and the abnormal sub-region corresponds to the part of the organ that carries the lesion;

The lesion interface determination module 43 is configured to determine the difference between the abnormal sub-region and the lesion area according to the positional relationship between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area The interface between the lesions;

The lesion analysis module 44 is configured to determine the morphological analysis result of the lesion according to the interface of the lesion and the area of the lesion.

In a possible implementation, the segmentation module 41 includes: a preprocessing sub-module 411: used to normalize the image to be processed to obtain the processed first image; the first segmentation sub-module 412: used to Perform a first segmentation process on the first image to determine the organ region in the first image; a second segmentation sub-module 413: perform a second segmentation process on the first image to determine the organ region in the first image The lesion area.

In a possible implementation manner, the first segmentation submodule 412 is configured to: cut the first image according to a first preset size to obtain a first sampled image block; and input the first sampled image block Perform segmentation in the first segmentation network to obtain a segmentation result of the first sampled image block; fuse the segmentation results of a plurality of first sampled image blocks to obtain the organ region in the first image;

Wherein, the second segmentation submodule 413 is configured to: cut the first image according to a second preset size to obtain a second sampled image block; input the second sampled image block into a second segmentation network for segmentation , Obtain the segmentation result of the second sampled image block; fuse the segmentation results of multiple second sampled image blocks to obtain the lesion area in the first image.

In a possible implementation, the abnormal sub-region determination module 42 is configured to: obtain a first spatial region circumscribed to the lesion area; expand the first spatial region according to a preset expansion coefficient to obtain the expansion The second spatial area after the second spatial area; in the second spatial area, a spatial area that belongs to the organ area and does not belong to the lesion area is determined as the abnormal sub-area.

In a possible implementation, the lesion interface determination module 43 is configured to: according to the distance between the first pixel point and the second pixel point, from the first pixel point and the second pixel point The demarcation reference point is determined from the points; and the lesion demarcation interface is determined from the multiple reference planes according to the number of the demarcation reference points in the preset multiple reference planes, wherein the multiple reference planes are respectively perpendicular to the Each coordinate axis of the image coordinate system of the image to be processed.

In a possible implementation manner, the morphological analysis result of the lesion includes morphological parameters of the lesion, and the morphological parameters include a reference diameter, a maximum diameter, a width, and a height, wherein the lesion analysis module 44 is configured to : Among the demarcation reference points included in the lesion interface, the distance between the two demarcation reference points with the largest distance is determined as the reference diameter of the lesion; among the second pixel points included in the lesion area, the The maximum distance between the second pixel point and the geometric center of the interface of the lesion is determined as the maximum diameter of the lesion; among the second pixel points included in the lesion area, in the direction perpendicular to the maximum diameter, The distance between the two second pixels with the largest distance is determined as the width of the lesion; among the second pixels included in the lesion area, the maximum distance between the second pixel and the interface of the lesion is determined Is the height of the lesion.

In some embodiments, the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. For specific implementation, refer to the description of the above method embodiments. For brevity, here No longer.

The embodiments of the present disclosure also provide a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above-mentioned method when executed by a processor. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

An embodiment of the present disclosure also proposes an electronic device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above method.

The electronic device can be provided as a terminal, server or other form of device.

FIG. 5 shows a block diagram of an electronic device 800 according to an embodiment of the present disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and other terminals.

5, the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 , And communication component 816.

The processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the foregoing method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations in the electronic device 800. Examples of these data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable and Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic Disk or Optical Disk.

The power supply component 806 provides power for various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with the generation, management, and distribution of power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure related to the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module. The above-mentioned peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

The sensor component 814 includes one or more sensors for providing the electronic device 800 with various aspects of state evaluation. For example, the sensor component 814 can detect the on/off status of the electronic device 800 and the relative positioning of the components. For example, the component is the display and the keypad of the electronic device 800. The sensor component 814 can also detect the electronic device 800 or the electronic device 800. The position of the component changes, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor component 814 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact. The sensor component 814 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on communication standards, such as wireless network (WiFi), second-generation mobile communication technology (2G), third-generation mobile communication technology (3G), fourth-generation mobile communication technology (4G) or The fifth-generation mobile communication technology (5G), or a combination of them. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field-available A programmable gate array (FPGA), controller, microcontroller, microprocessor, or other electronic components are implemented to implement the above methods.

In an exemplary embodiment, there is also provided a non-volatile computer-readable storage medium, such as a memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to complete the foregoing method.

FIG. 6 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server. 6, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application program stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above-mentioned method.

The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 . The electronic device 1900 can operate based on the operating system stored in the memory 1932, such as the Microsoft Server Operating System (Windows ServerTM), the graphical user interface operating system (Mac OS XTM) launched by Apple, and the multi-user and multi-process computer operating system (UnixTM) ), free and open source Unix-like operating system (LinuxTM), open source Unix-like operating system (FreeBSDTM) or similar.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as the memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to complete the foregoing method.

The present disclosure may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for enabling a processor to implement various aspects of the present disclosure.

The computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a printer with instructions stored thereon The protruding structure in the hole card or the groove, and any suitable combination of the above. The computer-readable storage medium used here is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.

The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .

The computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or in one or more programming languages. Source code or object code written in any combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages. Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as a stand-alone software package, partly on the user's computer and partly executed on a remote computer, or entirely on the remote computer or server implement. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect to the user's computer) connect). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be personalized by using the status information of the computer-readable program instructions. The computer-readable program instructions are executed to realize various aspects of the present disclosure.

Here, various aspects of the present disclosure are described with reference to flowcharts and/or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and/or block diagrams, and combinations of blocks in the flowcharts and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine that makes these instructions when executed by the processor of the computer or other programmable data processing device , A device that implements the functions/actions specified in one or more blocks in the flowchart and/or block diagram is produced. It is also possible to store these computer-readable program instructions in a computer-readable storage medium. These instructions make computers, programmable data processing apparatuses, and/or other devices work in a specific manner, so that the computer-readable medium storing the instructions includes An article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

It is also possible to load computer-readable program instructions onto a computer, other programmable data processing device, or other equipment, so that a series of operation steps are executed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process , So that the instructions executed on the computer, other programmable data processing apparatus, or other equipment realize the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

The flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions, and operations of the system, method, and computer program product according to multiple embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction contains one or more components for realizing the specified logical function. Executable instructions. In some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions Or it can be realized by a combination of dedicated hardware and computer instructions.

The computer program product can be specifically implemented by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium. In another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc. Wait.

The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Without departing from the scope and spirit of the described embodiments, many modifications and changes are obvious to those of ordinary skill in the art. The choice of terms used herein is intended to best explain the principles, practical applications, or improvements to the technology in the market for each embodiment, or to enable those of ordinary skill in the art to understand the various embodiments disclosed herein.

Claims

An image processing method, characterized in that the method includes:

Performing segmentation processing on the image to be processed, and determining the organ area corresponding to the target organ in the image to be processed, and the lesion area corresponding to the lesion on the target organ;

Determining an abnormal sub-area from the organ area according to the positions of the organ area and the lesion area, the abnormal sub-area corresponding to the part of the organ bearing the lesion;

Determine the lesion interface between the abnormal sub-region and the lesion area according to the positional relationship between the first pixel in the abnormal sub-region and the second pixel in the lesion area;

Determine the morphological analysis result of the lesion according to the interface of the lesion and the area of the lesion.
The method according to claim 1, characterized in that, according to the positional relationship between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area, the abnormal sub-region and the second pixel point are determined Describes the lesion interface between the lesion areas, including:

Determining a demarcation reference point from the first pixel and the second pixel according to the distance between the first pixel and the second pixel;

According to the number of demarcation reference points in the preset multiple reference planes, the lesion interface is determined from the multiple reference planes, wherein the multiple reference planes are respectively perpendicular to the image coordinate system of the image to be processed Each coordinate axis.
The method according to claim 2, wherein the boundary is determined from the first pixel point and the second pixel point according to the distance between the first pixel point and the second pixel point Reference points, including:

For any first pixel, determine the first distance between the first pixel and each second pixel in the lesion area;

In a case where there is a first distance less than or equal to the distance threshold, determining the first pixel point as a demarcation reference point;

For any second pixel, determine a second distance between the second pixel and each first pixel in the abnormal sub-region;

In a case where there is a second distance less than or equal to the distance threshold, the second pixel point is determined as a demarcation reference point.
The method according to claim 1, wherein the determining an abnormal sub-area from the organ area according to the positions of the organ area and the lesion area comprises:

Acquiring a first spatial area circumscribing the lesion area;

Expand the first spatial area according to a preset expansion coefficient to obtain an expanded second spatial area;

In the second spatial region, a spatial region that belongs to the organ region and does not belong to the lesion region is determined as the abnormal subregion.
The method according to claim 1, wherein the morphological analysis result of the lesion includes morphological parameters of the lesion, and the morphological parameters include a reference diameter, a maximum diameter, a width, and a height,

Wherein, the determining the morphological analysis result of the lesion according to the interface of the lesion and the area of the lesion includes:

Among the demarcation reference points included in the lesion interface, the distance between the two demarcation reference points with the largest distance is determined as the reference diameter of the lesion;

Among the second pixels included in the lesion area, determining the maximum distance between the second pixel and the geometric center of the interface of the lesion as the maximum diameter of the lesion;

In the second pixel points included in the lesion area, in a direction perpendicular to the maximum diameter, the distance between the two second pixel points with the largest distance is determined as the width of the lesion;

Among the second pixels included in the lesion area, the maximum distance between the second pixel and the interface of the lesion is determined as the height of the lesion.
The method according to claim 1, wherein the segmentation process is performed on the image to be processed, the organ area corresponding to the target organ in the image to be processed is determined, and the lesion area corresponding to the lesion on the target organ is determined, include:

Perform normalization processing on the image to be processed to obtain the processed first image;

Performing a first segmentation process on the first image to determine the organ region in the first image;

Performing a second segmentation process on the first image to determine a lesion area in the first image.
The method according to claim 6, wherein performing a first segmentation process on the first image to determine the organ region in the first image comprises:

Cutting the first image according to a first preset size to obtain a first sampled image block;

Inputting the first sampled image block into a first segmentation network for segmentation to obtain a segmentation result of the first sampled image block;

Fusing the segmentation results of the multiple first sampled image blocks to obtain the organ region in the first image;

Wherein, performing a second segmentation process on the first image to determine the lesion area in the first image includes:

Cutting the first image according to the second preset size to obtain a second sampled image block;

Inputting the second sampled image block into a second segmentation network for segmentation to obtain a segmentation result of the second sampled image block;

The segmentation results of the multiple second sampling image blocks are merged to obtain the lesion area in the first image.
The method according to any one of claims 1-7, wherein the image to be processed comprises a three-dimensional angiographic image, the target organ comprises a blood vessel, the lesion on the target organ comprises an aneurysm, and The abnormal sub-region includes the tumor-bearing artery region, and the lesion interface includes the tumor neck plane of the aneurysm.
An image processing device, characterized in that it comprises:

A segmentation module, configured to perform segmentation processing on the image to be processed, and determine the organ area corresponding to the target organ in the image to be processed, and the lesion area corresponding to the lesion on the target organ;

An abnormal subregion determining module, configured to determine an abnormal subregion from the organ region according to the positions of the organ region and the lesion region, the abnormal subregion corresponding to the part of the organ bearing the lesion;

The lesion interface determination module is configured to determine the relationship between the abnormal sub-region and the lesion area according to the positional relationship between the first pixel point in the abnormal sub-region and the second pixel point in the lesion area The interface of the lesion;

The lesion analysis module is configured to determine the morphological analysis result of the lesion based on the lesion interface and the lesion area.
An electronic device, characterized in that it comprises:

processor;

A memory for storing processor executable instructions;

Wherein, the processor is configured to call instructions stored in the memory to execute the method according to any one of claims 1 to 8.
A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the method according to any one of claims 1 to 8 when the computer program instructions are executed by a processor.