Medical image processing system, device and computer-readable storage medium

Abstract

The embodiment of the present application discloses a medical image processing system, device and computer-readable storage medium. The system includes: a sample data acquisition module for acquiring multiple sample images and age information; a test data acquisition module for acquiring the test image and age information of the test subject; an image segmentation module for segmenting at least a first sub-region from the sample image, and at least a first sub-region to be tested from the test image; a morphological feature acquisition module for acquiring the morphological features of the first sub-region in the image; and an analysis module for determining the condition of the corresponding organ or tissue of the test subject based on the age information corresponding to at least part of the sample images, the morphological features of the first sub-region in each of the at least part of the sample images, the age information of the test subject and the morphological features of the first sub-region to be tested in the test image.

Description

[0001] Description of the case

[0002] This case is a divisional application of the Chinese patent application entitled “A medical image processing system, device and computer-readable storage medium” filed on September 26, 2018, with application number 201811125405.2. Technical Field

[0003] The present application relates to the field of medical image processing, and in particular to an evaluation system for organ or tissue structure. Background Art

[0004] At present, the global population aging problem is serious. The aging process is accompanied by a series of changes in organs or tissues, such as brain function, which is mainly manifested by brain atrophy. The manifestations on brain imaging are reduced brain tissue structure volume, reduced brain parenchyma, reduced brain weight, reduced number of cells, flattened gyri, widened and deepened cerebral sulci, enlarged ventricles, cisterns and subarachnoid spaces, mild gliosis and varying degrees of degenerative lesions in cerebral arteries. The main clinical manifestations are memory loss, emotional instability, decreased thinking ability, inability to concentrate, and in severe cases, dementia, and eventually intellectual loss as its clinical characteristics. The cause of the disease is quite complicated and has not been fully understood yet, which has greatly affected the quality of life and family life of the elderly.

[0005] Alzheimer's disease (AD) is also known as senile dementia. In the clinical diagnosis process, if the patient's brain atrophy reaches a certain degree and is diagnosed as Alzheimer's disease by scale, most of them have reached the untreatable stage. If Alzheimer's disease can be diagnosed early, drug treatment can be used to delay the time of its conversion to Alzheimer's disease.

[0006] In the traditional assessment and diagnosis of brain atrophy in the elderly, the following steps are mainly used: (1) data collection, (2) preprocessing, (3) doctor experience identification, (4) scale test, and (5) diagnosis results. Data collection refers to the process of collecting brain images through imaging equipment. Preprocessing refers to a series of operations such as resampling, adjusting direction, removing skull, and grayscale correction to remove the impact of the working conditions of the imaging equipment on the quality of brain images, so as to provide high-quality images for subsequent analysis. Doctor experience identification is the doctor's preliminary diagnosis of brain atrophy, white matter deformation, and cerebral infarction based on brain images. Scale testing is a multi-scale cognitive assessment of patients based on the preliminary diagnostic results of images. It is mainly done by asking questions and takes about 2 to 3 hours. The final diagnosis result is given based on the scale score combined with the preliminary diagnosis of images.

[0007] Traditional methods have achieved certain results in the diagnosis of elderly organ or tissue abnormalities such as brain atrophy and other related diseases, but there are the following problems: First, the diagnosis process mainly relies on the doctor's subjective judgment, which mainly includes three aspects: family description, patient cognitive assessment (scale test) and the attending physician's observation of relevant organ or tissue images. This method lacks quantitative indicators to participate in decision-making and is too dependent on the doctor's prior knowledge level. Secondly, in the observation and diagnosis of organ or tissue images, if relevant quantitative morphological features can be obtained, there is no data standard that can be referred to the normal people of the corresponding age group, and it still depends on the experience accumulation of the attending physician. Finally, with the development of medical equipment, the acquisition of many organ or tissue images has become more convenient. It is difficult to quantify the data comparison of patients' images at different time periods, and the follow-up data of their images cannot be effectively used, making it difficult to compare the trend of organ or tissue changes.

[0008] Therefore, it is desirable to provide a medical image processing system, device, and computer-readable storage medium, which can, on the one hand, quantitatively evaluate the condition of a patient's related organs or tissues based on the organ or tissue images of a normal person, and on the other hand, can evaluate the development trend of the patient's related organs or tissues based on the follow-up data of the patient's organ or tissue images. Summary of the invention

[0009] The present application collects a large number of images of organs or tissues of normal people, segments sub-regions from these images, and segments the same sub-regions from the images of the subject to be tested, and evaluates the condition of the organ or tissue of the subject to be tested by comparing the morphological features of the sub-regions of normal people with those of the subject to be tested.

[0010] One aspect of the present application provides a medical image processing system. The system includes: a sample data acquisition module, which is used to acquire multiple sample images and age information corresponding to each sample image; a test data acquisition module, which is used to acquire the test image of a subject and the age information of the subject; an image segmentation module, which is used to segment at least a first sub-region from each sample image, and at least a first sub-region to be tested from the test image; a morphological feature acquisition module, which is used to acquire the morphological features of the first sub-region in each sample image, and acquire the morphological features of the first sub-region to be tested in the test image; and an analysis module, which is used to determine the condition of the corresponding organ or tissue of the subject according to the age information corresponding to at least part of the sample images, the morphological features of the first sub-region in each of the at least part of the sample images, the age information of the subject, and the morphological features of the first sub-region to be tested in the test image.

[0011] In some embodiments, determining the condition of the corresponding organ or tissue of the subject includes: determining the ranking result of the morphological characteristics of the first sub-region to be tested of the subject among peers based on age information corresponding to at least part of the sample images, morphological characteristics of the first sub-region in each of the at least part of the sample images, the age information of the subject and the morphological characteristics of the first sub-region to be tested in the image to be tested; and determining the condition of the corresponding organ or tissue of the subject based on the ranking result among peers.

[0012] In some embodiments, determining the condition of the corresponding organ or tissue of the subject includes: sorting the morphological features of the first sub-region in the sample images of each age according to the age information corresponding to each sample image and the morphological features of the first sub-region in each sample image according to the numerical value, and determining at least one percentile of the morphological features of the first sub-region corresponding to each age; determining the ranking result of the morphological features of the first sub-region to be tested of the subject among peers according to the at least one percentile; and determining the condition of the corresponding organ or tissue of the subject according to the ranking result among peers.

[0013] In some embodiments, determining the condition of the organ or tissue of the subject includes: taking age as the independent variable and at least one percentile of the morphological features of the first sub-region in the sample image corresponding to each age as the dependent variable, fitting a curve showing that the morphological features of the first sub-region in the sample image change with age; comparing the age information of the subject and the morphological features of the first sub-region to be tested of the subject with the fitted curve, and determining the percentile of the morphological features of the first sub-region to be tested of the subject among people of the same age.

[0014] In some embodiments, the fitting adopts at least one of the following methods: Loess local weighted regression, polynomial regression, ridge regression, and lasso regression.

[0015] In some embodiments, the sample data acquisition module is also used to obtain the gender information corresponding to each sample image; the test data acquisition module is also used to obtain the gender information of the subject; the analysis module is also used to determine the ranking results of the morphological characteristics of the first sub-area to be tested of the subject among people of the same age and gender, and determine the condition of the corresponding organ or tissue of the subject based on the ranking results among people of the same age and gender.

[0016] In some embodiments, the test data acquisition module is also used to acquire at least two images to be tested of the subject, each image to be tested corresponding to a different age; the image segmentation module is used to segment at least a first sub-region to be tested from each image to be tested; the morphological feature acquisition module is used to acquire at least the morphological features of the first sub-region to be tested in each image to be tested; the analysis module is used to determine the changing trend of the morphological features of the first sub-region to be tested of the subject with age based on the morphological features of the first sub-region to be tested at each age of the subject; it is also used to determine the normal changing trend of the morphological features of the first sub-region based on at least the age information corresponding to some sample images and the morphological features of the first sub-region in each of the at least some sample images; it is also used to determine the condition of the corresponding organ or tissue of the subject by comparing the changing trend of the first sub-region to be tested of the subject with the normal changing trend.

[0017] In some embodiments, the image segmentation module is also used to segment a second sub-region from each sample image, and to segment a second sub-region to be tested from the image to be tested; the morphological feature acquisition module is also used to acquire the morphological features of the second sub-region in each sample image, and to acquire the morphological features of the second sub-region to be tested in the image to be tested; the analysis module is also used to determine the condition of the corresponding organ or tissue of the subject to be tested based on the age information corresponding to each sample image, the morphological features of the second sub-region in each sample image, the age information of the subject to be tested, and the morphological features of the second sub-region to be tested in the image to be tested.

[0018] In some embodiments, the image segmentation module uses a deep learning model and / or a template registration and matching segmentation method to segment at least the first sub-region from each sample image and / or to segment at least the first sub-region to be tested from the image to be tested.

[0019] In some embodiments, the deep learning model may be a three-dimensional convolutional neural network, which can process images of entire organs or tissues.

[0020] In some embodiments, the organ may be a brain, and the three-dimensional convolutional neural network may segment a plurality of brain regions from a brain image.

[0021] In some embodiments, the organ may be a brain, and the morphological characteristics of the brain include at least one of the following characteristics: volume, cortical thickness, cortical area, and gyrality index.

[0022] Another aspect of the present application provides a medical image processing device, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the following operations: obtain multiple sample images and age information corresponding to each sample image; segment at least a first sub-region from each sample image; obtain morphological features of the first sub-region in each sample image; obtain a test image of a subject and the age information of the subject; segment at least the first sub-region to be tested from the image to be tested; obtain the morphological features of the first sub-region to be tested in the image to be tested; determine the condition of the corresponding organ or tissue of the subject according to the age information corresponding to at least part of the sample images, the morphological features of the first sub-region in each of the at least part of the sample images, the age information of the subject and the morphological features of the first sub-region to be tested in the image to be tested.

[0023] Another aspect of the present application provides a computer-readable storage medium for medical image processing, characterized in that the storage medium stores computer instructions, and when the computer instructions are executed by a processor, the following operations are implemented: obtaining multiple sample images and age information corresponding to each sample image; segmenting at least a first sub-region from each sample image; obtaining morphological features of the first sub-region in each sample image; obtaining a test image of a subject and the age information of the subject; segmenting at least the first sub-region to be tested from the image to be tested; obtaining the morphological features of the first sub-region to be tested in the image to be tested; and determining the condition of the corresponding organ or tissue of the subject according to the age information corresponding to at least part of the sample images, the morphological features of the first sub-region in each of the at least part of the sample images, the age information of the subject and the morphological features of the first sub-region to be tested in the image to be tested. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The present application will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0025] Figure 1 This is an application scenario diagram of a medical image processing system according to some embodiments of the present application;

[0026] Figure 2 A block diagram of an exemplary computing device for a dedicated system for implementing the technical solution of the present application;

[0027] Figure 3 A block diagram of an exemplary mobile device 300 for implementing a dedicated system of the technical solution of the present application;

[0028] Figure 4 is an exemplary module diagram of a medical image processing system according to some embodiments of the present application;

[0029] Figure 5 is an exemplary flow chart of a medical image processing method according to some embodiments of the present application;

[0030] Figure 6 An exemplary flow chart of a method for determining the ranking result of the morphological features of the first sub-region of a subject among peers according to some embodiments of the present application;

[0031] Figure 7 An exemplary flow chart of a method for determining the condition of a corresponding organ or tissue of a subject according to a change trend of morphological features of a sub-region of the subject as shown in some embodiments of the present application;

[0032] Figure 8 This is an example of a cross-sectional view of segmenting a brain image into multiple brain sub-regions according to some embodiments of the present application;

[0033] Fig. 9 This is a sagittal example diagram of segmenting a brain image into multiple brain sub-regions according to some embodiments of the present application;

[0034] Fig.10 This is a coronal example diagram of segmenting a brain image into multiple brain sub-regions according to some embodiments of the present application;

[0035] Fig.11 is a curve showing the change of percentile of whole brain volume with age according to some embodiments of the present application;

[0036] Fig.12 This is an example diagram comparing the change trend of the gray matter volume of the brain of the subject to be tested with the normal change trend according to some embodiments of the present application;

[0037] Fig.13 This is an example diagram comparing the change trend of the brain white matter volume of the subject to be tested with the normal change trend according to some embodiments of the present application;

[0038] Fig.14 This is an example diagram comparing the change trend of the putamen volume of the subject's brain with the normal change trend according to some embodiments of the present application;

[0039] Fig.15 and Fig.16 is a schematic diagram of a medical image processing software interface according to some embodiments of the present application;

[0040] Fig.17It is a schematic diagram of a diagnostic report according to some embodiments of the present application. DETAILED DESCRIPTION

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0042] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0043] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0044] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0045] It should be understood that the application scenarios of the system and method of the present application are merely some examples or embodiments of the present application. For ordinary technicians in this field, without paying any creative work, they can also apply the present application to other similar scenarios based on these drawings.

[0046] Figure 1 FIG. 1 is an application scenario diagram of an image processing system according to some embodiments of the present application. Figure 1 As shown, the image processing system 100 may include a scanner 110 , a network 120 , a terminal 130 , a processing device 140 , and a storage device 150 .

[0047] The scanner 110 can scan an object in the detection area to obtain scan data of the object. The scanned object can be a part of an organ or tissue of a human body, such as a head. In some embodiments, the scanner 110 can be a magnetic resonance (MR) scanner. An MR scanner can include a magnet (e.g., a superconducting magnet), a gradient coil, and a radio frequency (RF) coil (not shown in the figure). In some embodiments, the MR scanner can be a closed-bore scanner, an open-bore scanner, etc.

[0048] The network 120 may include any suitable network that facilitates the image processing system 100 to exchange information and / or data. In some embodiments, one or more other components of the image processing system 100 (e.g., the scanner 110, the terminal 130, the processing device 140, the storage device 150, etc.) may exchange information and / or data with each other through the network 120. For example, the processing device 140 may obtain image data from the scanner 110 through the network 120. For another example, the processing device 140 may obtain a user instruction from the terminal 130 through the network 120. The network 120 may be and / or include a public network (e.g., the Internet), a private network (e.g., a local area network (LAN), a wide area network (WAN), etc.), a wired network (e.g., Ethernet), a wireless network (e.g., an 802.11 network, a Wi-Fi network, etc.), a cellular network (e.g., an LTE network), a frame relay network, a virtual private network (“VPN”), a satellite network, a telephone network, a router, a hub, a switch, a server computer, and / or a combination of one or more thereof. For example, the network 120 may include a combination of one or more of a cable network, a wired network, an optical fiber network, a telecommunication network, a local area network, a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth™ network, a ZigBee™ network, a near field communication network (NFC), etc. In some embodiments, the network 120 may include one or more network access points. For example, the network 120 may include a wired and / or wireless network access point, such as a base station and / or a network switching point, through which one or more components of the image processing system 100 may access the network 120 for data and / or information exchange.

[0049] In some embodiments, the user may operate the image processing system 100 through the terminal 130. The terminal 130 may include a combination of one or more of a mobile device 131, a tablet computer 132, a laptop computer 133, etc. In some embodiments, the mobile device 131 may include a combination of one or more of a smart home device, a wearable device, a mobile device, a virtual reality device, an augmented reality device, etc. In some embodiments, the smart home device may include a combination of one or more of a smart lighting device, a smart appliance control device, a smart monitoring device, a smart TV, a smart camera, an intercom, etc. In some embodiments, the wearable device may include a combination of one or more of a bracelet, shoes and socks, glasses, a helmet, a watch, clothing, a backpack, a smart accessory, etc. In some embodiments, the mobile device may include a combination of one or more of a mobile phone, a personal digital assistant (PDA), a gaming device, a navigation device, a point of sale (POS) device, a laptop computer, a tablet computer, a desktop computer, etc. In some embodiments, the virtual reality device and / or the augmented reality device may include a combination of one or more of a virtual reality helmet, virtual reality glasses, virtual reality goggles, an augmented reality helmet, augmented reality glasses, augmented reality goggles, etc. For example, the virtual reality device and / or the augmented reality device may include Google Glass™, Oculus Rift™, Hololens™, Gear VR™, etc. In some embodiments, terminal 130 may be part of processing device 140 .

[0050] The processing device 140 can process the data and / or information obtained from the scanner 110, the terminal 130 and / or the storage device 150. For example, the processing device 140 can process the image to be tested and evaluate the condition of the corresponding organ or tissue of the subject to be tested. In some embodiments, the processing device 140 can be a server or a server group. The server group can be centralized or distributed. In some embodiments, the processing device 140 can be local or remote. For example, the processing device 140 can access the information and / or data stored in the scanner 110, the terminal 130 and / or the storage device 150 through the network 120. For example, the processing device 140 can be directly connected to the scanner 110, the terminal 130 and / or the storage device 150 to access the information and / or data stored therein. In some embodiments, the processing device 140 can be executed on a cloud platform. For example, the cloud platform can include a combination of one or more of a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an interconnected cloud, a multiple cloud, etc. In some embodiments, the processing device 140 can be provided by a computing device 200 (such as Figure 2 as described) is executed.

[0051] The storage device 150 may store data, instructions, and / or other information. In some embodiments, the storage device 150 may store data obtained from the terminal 130 and / or the processing device 140. In some embodiments, the storage device 150 may store data and / or instructions executed or used by the processing device 140 to perform the exemplary methods described in this application. In some embodiments, the storage device 150 may include a combination of one or more of a mass storage, a removable storage, a volatile read-write memory, a read-only memory (ROM), and the like. Exemplary mass storage may include a magnetic disk, an optical disk, a solid-state drive, and the like. Exemplary removable storage may include a flash drive, a floppy disk, an optical disk, a memory card, a zipper disk, a magnetic tape, and the like. Exemplary volatile read-write memory may include a random access memory (RAM). Exemplary random access memory RAM may include a dynamic random access memory (DRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), a static random access memory (SRAM), a thyristor random access memory (T-RAM), and a zero capacitance random access memory (Z-RAM), and the like. Exemplary read-only memories (ROMs) may include mask read-only memories (MROMs), programmable read-only memories (PROMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), compact disk read-only memories (CD-ROMs), and digital versatile disks, etc. In some embodiments, the storage device 150 may be executed on a cloud platform. For example, the cloud platform may include a combination of one or more of a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an interconnected cloud, a multi-cloud, etc.

[0052] In some embodiments, the storage device 150 may be connected to the network 120 to communicate with one or more other components (e.g., the processing device 140, the terminal 130, etc.) in the image processing system 100. One or more components in the image processing system 100 may access data or instructions stored in the storage device 150 through the network 120. In some embodiments, the storage device 150 may be directly connected or communicated with one or more other components (e.g., the processing device 140, the terminal 130, etc.) in the image processing system 100. In some embodiments, the storage device 150 may be part of the processing device 140.

[0053] Figure 2 It is a block diagram of an exemplary computing device of a dedicated system for implementing the technical solution of the present application.

[0054] like Figure 2 As shown, computing device 200 may include processor 210 , memory 220 , input / output interface 230 , and communication port 240 .

[0055] The processor 210 can execute computing instructions (program code) and perform the functions of the image processing system 100 described in this application. The computing instructions may include programs, objects, components, data structures, processes, modules and functions (the functions refer to specific functions described in this application). For example, the processor 210 can process image data obtained from any component of the image processing system 100. In some embodiments, the processor 210 may include a microcontroller, a microprocessor, a reduced instruction set computer (RISC), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a central processing unit (CPU), a graphics processing unit (GPU), a physical processing unit (PPU), a microcontroller unit, a digital signal processor (DSP), a field programmable gate array (FPGA), an advanced RISC machine (ARM), a programmable logic device, and any circuits and processors capable of performing one or more functions, etc., or any combination thereof. For illustration only, Figure 2 The computing device 200 in the embodiment only describes one processor, but it should be noted that the computing device 200 in the present application may also include multiple processors.

[0056] The memory 220 may store data / information obtained from any other component of the image processing system 100. In some embodiments, the memory 220 may include a mass storage, a removable storage, a volatile read and write storage, and a read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage may include a magnetic disk, an optical disk, and a solid-state drive, etc. The removable storage may include a flash drive, a floppy disk, an optical disk, a memory card, a compact disk, and a tape, etc. The volatile read and write storage may include a random access memory (RAM). The RAM may include a dynamic RAM (DRAM), a double rate synchronous dynamic RAM (DDR SDRAM), a static RAM (SRAM), a thyristor RAM (T-RAM), and a zero capacitance (Z-RAM), etc. The ROM may include a mask ROM (MROM), a programmable ROM (PROM), an erasable programmable ROM (PEROM), an electrically erasable programmable ROM (EEPROM), a compact disk ROM (CD-ROM), and a digital versatile disk ROM, etc.

[0057] The input / output interface 230 may be used to input or output signals, data or information. In some embodiments, the input / output interface 230 may allow a user to communicate with the image processing system 100. In some embodiments, the input / output interface 230 may include an input device and an output device. Exemplary input devices may include one or more combinations of a keyboard, a mouse, a touch screen, and a microphone. Exemplary output devices may include a display device, a speaker, a printer, a projector, or the like, or any combination thereof. Exemplary display devices may include one or more combinations of a liquid crystal display (LCD), a display based on a light emitting diode (LED), a flat panel display, a curved display, a television device, a cathode ray tube (CRT), or the like. The communication port 240 may be connected to a network for data communication. The connection may be a wired connection, a wireless connection, or a combination of both. The wired connection may include a cable, an optical cable, or a telephone line, or the like, or any combination thereof. The wireless connection may include one or more combinations of Bluetooth, Wi-Fi, WiMax, WLAN, ZigBee, a mobile network (e.g., 3G, 4G, or 5G, etc.), or the like. In some embodiments, the communication port 240 may be a standardized port, such as RS232, RS485, etc. In some embodiments, the communication port 240 may be a specially designed port. For example, the communication port 240 may be designed according to the Digital Imaging and Medical Communications Protocol (DICOM).

[0058] Figure 3 It is a block diagram of an exemplary mobile device 300 of a dedicated system for implementing the technical solution of the present application.

[0059] like Figure 3 As shown, the mobile device 300 may include a communication unit 310, a display unit 320, a graphics processing unit (GPU) 330, a central processing unit (CPU) 340, an input / output unit 350, a memory 360, a storage unit 370, etc. In some embodiments, an operating system 361 (e.g., iOS, Android, Windows Phone, etc.) and an application 362 may be loaded from the storage unit 370 into the memory 360 so as to be executed by the CPU 340. The application 362 may include a browser or an application for receiving imaging, graphics processing, or other related information from the image processing system 100.

[0060] Figure 4 The medical image processing system 400 is an exemplary module diagram according to some embodiments of the present application. In some embodiments, the medical image processing system 400 may include a sample data acquisition module 402 , a test data acquisition module 404 , an image segmentation module 406 , a morphological feature acquisition module 408 , and an analysis module 410 .

[0061] The sample data acquisition module 402 can acquire sample data. The sample data includes sample images. In some embodiments, the sample data acquisition module 402 can acquire multiple sets of sample data, including multiple sample images. In some embodiments, the multiple sample images can be three-dimensional images and / or two-dimensional images. In some embodiments, the multiple sample images include images of at least one organ or tissue. The organs include but are not limited to the brain, lungs, heart, kidneys, liver, etc. The tissues include but are not limited to epithelial tissue, connective tissue, nerve tissue, muscle tissue, etc. In some embodiments, the multiple sample images can be images of the same type, for example, all MR images, CT images, PET-CT images, PET-MR images, etc. In some embodiments, the multiple images can be images of different types. Taking the brain MR sample image as an example, it includes but is not limited to T1-weighted images, T2-weighted images, FLAIR sequence images, etc. of the brain. The sample data acquisition module 402 can also acquire age information corresponding to each sample image. In some embodiments, the age information can be an integer age, such as 50 years old, 60 years old, 61 years old, etc. In some embodiments, the age information can be accurate to at least one decimal place, such as 60.1, 60.5 years old, etc. In some embodiments, the sample data acquisition module 402 may also acquire gender information corresponding to each sample image.

[0062] The test data acquisition module 404 can acquire the test data, including the test image of the test subject and the age information of the test subject. The test image can be an image of a certain organ or tissue. In some embodiments, when multiple sample images are images of the same organ or tissue, the test image can also be an image of the organ or tissue. In some embodiments, when multiple sample images are images of different types of organs or tissues, the organ or tissue in the test image can be the same type as the organ or tissue in at least some of the sample images. For example, the sample image can include images of at least two organs of the brain, lungs, heart, kidneys, liver, etc., and the test image can be an image of any one of the at least two organs. In some embodiments, when multiple sample images are images of the same type, the test image can be an image of the type. In some embodiments, when multiple sample images are images of different types, the test image can be the same type as at least some of the sample images. For example, the sample image can include at least two types of MR images, CT images, PET-CT images, PET-MR images, etc., and the test image can be any one of the at least two types. In some embodiments, the test data acquisition module 404 can acquire the follow-up data of the test subject, and the follow-up data includes multiple images of the test subject, each image is collected when the test subject is at a different age. In some embodiments, the test data acquisition module 404 can also acquire the gender information of the test subject.

[0063] The image segmentation module 406 can segment the image into at least one sub-region. For example, for organs, each organ is composed of different partitions. In some embodiments, the image segmentation module 406 can segment the organ image into at least one sub-region according to the partitions of each organ. The image segmentation module 406 can segment the image using at least one image segmentation method. The image segmentation method includes but is not limited to a method of a deep learning model, a method of template registration and matching, and the like. In some embodiments, the deep learning model can be a three-dimensional convolutional neural network, and the three-dimensional convolutional neural network can process the image of the entire organ or tissue. The template registration and matching method can include a single template registration and matching method, a multi-template registration and matching method, and the like.

[0064] Taking a brain image as an example, in some embodiments, the image segmentation module 406 can segment each brain image into multiple brain sub-regions. For example, the brain sub-regions can include the whole brain, gray matter, white matter, amygdala, putamen, hippocampus, globus pallidus, putamen, thalamus, anterior cingulate gyrus, middle cingulate gyrus, posterior cingulate gyrus, insula, superior temporal gyrus, middle temporal gyrus, temporal pole, etc. Figures 8 to 10 An example diagram of segmenting a brain image into multiple brain sub-regions, where Figure 8 is a transverse image. Fig. 9 is a sagittal image, Fig.10 Coronal image.

[0065] The morphological feature acquisition module 408 can acquire the morphological features of each sub-region. In some embodiments, the morphological features of each sub-region can be acquired by at least one morphometric method. For example, the morphometric method can include a voxel-based morphometric method, a tensor-based morphometric method, a deformation-based morphometric method, etc. Taking the brain image as an example, the morphological features include but are not limited to volume, cortical thickness, cortical area, gyrus index, etc.

[0066] The analysis module 410 can determine the condition of the corresponding organ or tissue of the subject to be tested based on the sample data and the data to be tested. In some embodiments, the analysis module 410 can determine the condition of the corresponding organ or tissue of the subject to be tested based on the age information corresponding to at least part of the sample images, the morphological features of the specific sub-regions in each of the at least part of the sample images, the age information of the subject to be tested, and the morphological features of the specific sub-regions in the images to be tested. In some embodiments, the analysis module 410 can determine the ranking result of the morphological features of the specific sub-regions of the subject to be tested among peers, and determine the condition of the corresponding organ or tissue of the subject to be tested based on the ranking result.

[0067] In some embodiments, the analysis module 410 can sort the morphological features of the specific sub-regions in the sample images of each age according to the age information corresponding to each sample image and the morphological features of the specific sub-regions in each sample image according to the numerical values, and determine at least one percentile of the morphological features of the specific sub-regions corresponding to each age; use age as the independent variable and at least one percentile of the morphological features of the specific sub-regions corresponding to each age as the dependent variable to fit a curve showing how the morphological features of the specific sub-regions change with age; compare the age information of the subject and the morphological features of the specific sub-regions of the subject with the fitted curve to determine the percentile of the morphological features of the specific sub-regions of the subject among peers. For more information on determining the percentile of the subject's ranking among peers by curve fitting, see Figure 6 and its description.

[0068] In some embodiments, the analysis module 410 can also determine the ranking results of the morphological features of a specific sub-region of the subject to be tested among people of the same age and gender, and determine the condition of the corresponding organ or tissue of the subject to be tested based on the ranking results. In some embodiments, the analysis module 410 can also determine the trend of the morphological features of a specific sub-region of the subject to be tested changing with age based on the follow-up data of the subject to be tested; determine the trend of the morphological features of the specific sub-region of a normal person changing with age based on the sample image and the corresponding age information; compare the changing trend of the subject to be tested with the changing trend of a normal person to determine the condition of the corresponding organ or tissue of the subject to be tested. For more information on determining the condition of the corresponding organ or tissue of the subject to be tested by comparing the changing trend of the morphological features of the sub-region of the subject to be tested with the normal changing trend, please refer to Figure 7 , Figures 12 to 14 and its description.

[0069] It can be understood that the above medical image processing system 400 can be used to evaluate the conditions of the corresponding organs or tissues of the subject, thereby assisting doctors in diagnosis and improving diagnosis efficiency, but the system itself cannot directly output diagnosis results.

[0070] It should be noted that the above description of the medical image processing system modules is only for convenience of description and does not limit the present application to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various modules or form a subsystem to connect with other modules without deviating from this principle. For example, in some embodiments, the sample data acquisition module 402, the test data acquisition module 404, the image segmentation module 406, the morphological feature acquisition module 408 and the analysis module 410 can be different modules in one system, or one module can realize the functions of two or more of the above modules. In some embodiments, the principles of the present system can be applied to other image processing systems.

[0071] Figure 5 FIG. 5 is an exemplary flow chart of a medical image processing method according to some embodiments of the present application. In some embodiments, the medical image processing method 500 may be executed by the medical image processing system 400 .

[0072] Step 501 , obtaining a plurality of sample images and age information corresponding to each sample image. In some embodiments, step 501 may be performed by the sample data acquisition module 402 .

[0073] In some embodiments, images of multiple normal people can be collected as the sample images, and the age information of each person can be obtained. For example, volunteers can be selected by at least one hospital, and the specific organ or tissue images and ages of these volunteers can be obtained. In some embodiments, specific organ or tissue images of people in a specific age group can be obtained as the sample images. For example, specific organ or tissue images of people in the age group of 20 to 90 years old can be obtained as the sample images. In some embodiments, gender information corresponding to each sample image can also be obtained. In some embodiments, specific organ or tissue images of people of a specific gender can also be obtained as the sample images. Taking brain images as an example, in some embodiments, multiple MR brain images can be obtained as brain sample images. For example, one or any combination of T1-weighted images, T2-weighted images, FLAIR sequence images, etc. of the brain can be obtained.

[0074] Step 503 , segmenting at least a first sub-region from each sample image. In some embodiments, step 503 may be performed by the image segmentation module 406 .

[0075] In some embodiments, at least one image segmentation method may be used to segment the sample image. In some embodiments, a deep learning model method may be used to segment the sample image. In some embodiments, the deep learning model may be a three-dimensional convolutional neural network, which may process images of entire organs or tissues. In some embodiments, a template registration and matching method may be used to segment the sample image. The template registration and matching method may include a single template registration and matching method, a multi-template registration and matching method, and the like.

[0076] Taking a brain image as an example, in some embodiments, each brain sample image may be segmented into at least one brain sub-region. For example, the at least one brain sub-region may include the whole brain, gray matter, white matter, amygdala, putamen, hippocampus, globus pallidus, putamen, thalamus, anterior cingulate gyrus, middle cingulate gyrus, posterior cingulate gyrus, insula, superior temporal gyrus, middle temporal gyrus, temporal pole, etc.

[0077] Step 505 , obtaining the morphological features of the first sub-region in each sample image. In some embodiments, step 505 is performed by the morphological feature obtaining module 408 .

[0078] In some embodiments, at least one morphological feature of the first sub-region may be obtained. In some embodiments, the morphological feature of the first sub-region may be obtained by at least one morphometric method. For example, the morphometric method may include a voxel-based morphometric method, a tensor-based morphometric method, a deformation-based morphometric method, etc. Taking a brain image as an example, the at least one morphological feature includes but is not limited to volume, cortical thickness, cortical area, gyrality index, etc.

[0079] Step 507 , obtaining the image of the subject to be tested and the age information of the subject to be tested. In some embodiments, step 507 may be executed by the test data acquisition module 404 .

[0080] In some embodiments, when multiple sample images are of the same type, the image to be tested may be an image of that type. In some embodiments, when multiple sample images are of different types, the image to be tested may be of the same type as at least some of the sample images. In some embodiments, the accuracy of the age information of the subject to be tested is consistent with the accuracy of the age information corresponding to the sample images, for example, both are integers or accurate to one decimal place. In some embodiments, follow-up data of the subject to be tested may be obtained, and the follow-up includes multiple images of the subject to be tested, each image being collected at a different age of the subject to be tested.

[0081] Step 509 , segmenting at least a first sub-region to be measured from the image to be measured. In some embodiments, step 509 may be performed by the image segmentation module 406 .

[0082] In some embodiments, the sub-region segmented from the image to be tested by the image segmentation module 406 is of the same type as the sub-region segmented from the sample image. For example, taking the brain image as an example, the image segmentation module 406 can segment the whole brain, gray matter, white matter, amygdala, putamen, hippocampus, globus pallidus, putamen, thalamus, anterior cingulate gyrus, middle cingulate gyrus, posterior cingulate gyrus, insula, superior temporal gyrus, middle temporal gyrus, temporal pole and other sub-regions from both the image to be tested and the sample image. Step 509 is similar to step 503 and will not be repeated here.

[0083] Step 511 , obtaining the morphological features of the first sub-region to be tested in the image to be tested. In some embodiments, step 511 is performed by the morphological feature obtaining module 408 .

[0084] In some embodiments, the type of morphological features acquired by the morphological feature acquisition module 408 for the first sub-region in the image to be tested is the same as the type of morphological features acquired for the first sub-region in the sample image. Step 511 is similar to step 505 and will not be described in detail here.

[0085] Step 513, determining the condition of the corresponding organ or tissue of the subject according to the age information corresponding to at least part of the sample images, the morphological features of the first sub-region in each of the at least part of the sample images, the age information of the subject, and the morphological features of the first sub-region to be tested in the image to be tested. In some embodiments, step 513 can be performed by the analysis module 410.

[0086] In some embodiments, the ranking result of the morphological features of the first sub-region of the subject to be tested among peers can be determined, and the brain atrophy of the subject to be tested can be determined according to the ranking result. In some embodiments, the same age refers to the same or similar age, and can specifically refer to any age within a certain age range. For example, 60 years old can refer to any age between 59.5 and 60.5 years old. In some embodiments, the ranking of the morphological features of the first sub-region of the subject to be tested among peers can be determined. For example, sample images of the subject's peers can be extracted from all sample images, and the numerical values ​​of the morphological features of the first sub-region in these sample images and the image of the subject to be tested (from large to small or from small to large) are sorted to determine the ranking of the morphological features of the first sub-region of the subject to be tested among peers. In some embodiments, the ranking range of the morphological features of the first sub-region of the subject to be tested among peers can be determined. For example, the ranking of the subject to be tested can be divided by the total number of sample images of the peers to obtain the ranking percentile of the subject to be tested among peers.

[0087] The smaller the value of the morphological feature of some sub-regions, the worse the condition of the corresponding human organ or tissue; the larger the value of the morphological feature of another sub-region, the worse the condition of the corresponding human organ or tissue. Taking the brain as an example, the smaller the value of the morphological feature of some brain sub-regions, the more serious the degree of brain atrophy may be. When the morphological feature of the first brain sub-region is of this type, the morphological feature value of the first brain sub-region of the subject to be tested is smaller than that of more peers, indicating that the risk of brain atrophy of the subject to be tested may be greater. If the order is sorted from large to small, the later the subject to be tested is ranked, the greater the risk of brain atrophy may be; if the order is sorted from small to large, the higher the subject to be tested is ranked, the greater the risk of brain atrophy may be. The larger the value of the morphological feature of some brain sub-regions, the more serious the degree of brain atrophy may be. When the morphological feature of the first brain sub-region is of this type, the morphological feature value of the first brain sub-region of the subject to be tested is larger than that of more peers, indicating that the risk of brain atrophy of the subject to be tested may be greater. Similarly, the risk level of brain atrophy in the subject can be determined based on the sorting rules and the sorting results of the subject.

[0088] In some embodiments, the trend of the morphological features of the first sub-region of a normal person changing with age can be fitted according to the sample image and the corresponding age information, and the percentile of the subject to be tested among the peers can be determined according to the fitted curve. For more information on determining the percentile of the subject to be tested among the peers by curve fitting, please refer to Figure 6 and its description.

[0089] In some embodiments, the ranking results of the morphological features of a specific sub-region of the subject to be tested among people of the same age and gender may also be determined, and the conditions of the corresponding organs or tissues of the subject to be tested may be determined based on the ranking results.

[0090] In some embodiments, the trend of the morphological features of the first sub-region of the subject being tested changing with age can also be determined based on the follow-up data of the subject being tested; the trend of the morphological features of the first sub-region of a normal person changing with age can be determined based on the sample image and the corresponding age information; the changing trend of the subject being tested is compared with the changing trend of the normal person to determine the condition of the corresponding organ or tissue of the subject being tested. For more information on determining the condition of the corresponding organ or tissue of the subject being tested by comparing the changing trend of the morphological features of the sub-region of the subject being tested with the normal changing trend, please refer to Figure 7 , Figures 12 to 14 and its description.

[0091] It should be noted that the above description of the medical image processing method 500 is only for the convenience of description, and the present application cannot be limited to the scope of the embodiments cited. It can be understood that for those skilled in the art, after understanding the principle of the method, it is possible to arbitrarily combine the various steps without deviating from this principle, or to add or delete any steps, or to apply the principle of the present method to other image processing. For example, in some embodiments, the morphological features of other sub-regions in the corresponding organs or tissues of the subject to be tested can also be obtained, and the ranking results among the peers can be determined. Finally, the ranking results of each sub-region are combined to evaluate the status of the corresponding organs or tissues of the subject to be tested. In particular, when comprehensively evaluating, special attention can be paid to the sub-regions with relatively abnormal ranking results.

[0092] In some embodiments, the medical image processing system 400 may be implemented by an image processing device. The device may include at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the following. Figure 5 The medical image processing method.

[0093] In some embodiments, the medical image processing system 400 may be implemented by a computer-readable storage medium, wherein the storage medium stores computer instructions, and when the computer instructions are executed by a processor, the medical image processing system 400 may be implemented by a computer-readable storage medium, wherein the computer instructions are stored in the computer-readable storage medium, and when the computer instructions are executed by a processor, the computer-readable storage medium may be implemented by a computer-readable storage medium, and ... Figure 5 The medical image processing method.

[0094] Figure 6 This is an exemplary flow chart of a method for determining the ranking results of the morphological features of the first sub-region of a subject among peers according to some embodiments of the present application.

[0095] Step 601, according to the age information corresponding to each sample image and the morphological features of the first sub-region in each sample image, the morphological features of the first sub-region in the sample images of each age are sorted according to the numerical value, and at least one percentile of the morphological features of the first sub-region corresponding to each age is determined. In some embodiments, for sample images of the same age, the numerical values ​​of the morphological features of the first sub-regions in these sample images can be sorted from large to small, and the corresponding percentiles can be calculated. The specific numerical value of the morphological features corresponding to a percentile is called the percentile of this percentile. For example, taking the brain sample images as an example, the total brain volume (Total Intracranial Volume, TIV) of the 60-year-old brain sample images are sorted from large to small, wherein the TIV of a certain sample image is larger than the TIV of 95% of the sample images, then the TIV of the sample image is the 95th percentile of the TIV of the 60-year-old population. In some embodiments, for each age, multiple percentiles of the morphological features of the first sub-region can be determined. For example, the 5th percentile, the 25th percentile, the 50th percentile, the 75th percentile, the 95th percentile, etc. In some embodiments, the same age refers to the same or similar age, and specifically can refer to any age within a certain age range. For example, 60 years old can refer to any age between 59.5 and 60.5 years old.

[0096] Step 603, using age as an independent variable and at least one percentile of the morphological features of the first sub-region corresponding to each age as a dependent variable, a curve of the morphological features of the first sub-region changing with age is fitted. In some embodiments, at least one regression analysis method can be used for curve fitting, including but not limited to Loess local weighted regression, polynomial regression, ridge regression, lasso regression, etc. For the convenience of description, the process of curve fitting is explained below using Loess local weighted regression as an example.

[0097] For Loess local weighted regression, the definition formula (1) is the error function, and the fitting parameters Minimize the error function value to obtain the parameter ;

[0098] (1)

[0099] in is the total error between the predicted and true values ​​of the percentiles of the morphological features of the first sub-region for all ages; m is the total number of ages; For the i The weight of each age reflects the contribution of this age to the total error; For the iThe true value of the percentile of the morphological characteristics of the first sub-region at each age; For the i Age; For the i The predicted value of the percentile of the morphological characteristics of the first sub-region at each age. is the horizontal axis, Is the vertical axis.

[0100] Weight The calculation formula is as follows:

[0101] (2)

[0102] in x is the dependent variable, and the age to be predicted is x The percentile of the morphological features of the first sub-region at ; For the i Age; k is the bandwidth parameter, controlling (Bell-shaped function). It can be understood that the distance dependent variable x The closer the age, the greater the contribution to the total error, and the closer the dependent variable x The older the age, the smaller the contribution to the total error. In some embodiments, it can be determined empirically k size.

[0103] Fig.11 The curve of the percentile of the whole brain volume of a normal female fitted according to the sample image and the change with age according to some embodiments of the present application is shown in the figure. As shown in the figure, the dependent variable (abscissa) is age, and the independent variable (ordinate) is the whole brain volume. 1102 is a curve showing how the 95th percentile of TIV of normal females varies with age. The 95th percentile indicates that among sample images of the same age, 95% of the sample images have TIVs less than this value. 1104 is a curve showing how the 75th percentile of TIV of normal females varies with age. The 75th percentile indicates that among sample images of the same age, 75% of the sample images have TIVs less than this value. 1106 is a curve showing how the 50th percentile of TIV of normal females varies with age. The 50th percentile indicates that among sample images of the same age, 50% of the sample images have TIVs less than this value. 1108 is a curve showing how the 25th percentile of TIV of normal females varies with age. The 25th percentile indicates that among sample images of the same age, 25% of the sample images have TIVs less than this value. 1110 is the 5th percentile of TIV of normal females. The 5th percentile indicates that among sample images of the same age, 5% of the sample images have TIVs less than this value. As can be seen from the figure, the percentiles of women's whole brain volume generally show a downward trend with age.

[0104] Step 605 , comparing the age of the subject, the morphological features of the first sub-region of the subject and the fitted curve, and determining the percentile of the morphological features of the first sub-region of the subject among people of the same age.

[0105] In some embodiments, the percentile range of the morphological features of the first sub-region of the subject to be tested among peers can be determined. For example, by placing the age of the subject to be tested, the morphological features of the first sub-region of the subject to be tested and the fitted curve in the same coordinate system, the percentile of the morphological features of the first sub-region of the subject to be tested among peers can be intuitively obtained. In some embodiments, the specific numerical value of the percentile of the morphological features of the first sub-region of the subject to be tested among peers can be determined. Specifically, the morphological features of the first sub-region of the subject to be tested and the peers in the sample image can be sorted according to the numerical value, and the specific numerical value of the percentile of the morphological features of the first sub-region of the subject to be tested among peers is determined according to the sorting result.

[0106] Step 607, determining the condition of the corresponding organ or tissue of the subject according to the percentile.

[0107] The smaller the value of the morphological feature of some sub-regions, the worse the condition of the corresponding human organ or tissue; the larger the value of the morphological feature of another sub-region, the worse the condition of the corresponding human organ or tissue. Taking brain images as an example, the smaller the value of the morphological feature of some brain sub-regions, the more severe the degree of brain atrophy may be. For example, the smaller the whole brain volume, the more severe the degree of brain atrophy may be. When the morphological feature of the first brain sub-region is of this type, if the morphological feature of the first brain sub-region of the subject is smaller than a certain proportion of peers, it indicates that the risk of brain atrophy of the subject may be greater. In some embodiments, for the morphological characteristics of such brain sub-regions, when the percentile of the measured value of the subject to be tested among the peers is less than or equal to 5%, that is, only 5% of the peers have a smaller value than the measured value of the subject to be tested, the risk of brain atrophy of the subject to be tested is considered to be high; when the percentile of the measured value of the subject to be tested among the peers is greater than 5% and less than or equal to 25%, the risk of brain atrophy of the subject to be tested is considered to be medium; when the percentile of the measured value of the subject to be tested among the peers is greater than 25%, the risk of brain atrophy of the subject to be tested is considered to be low. The larger the value of the morphological characteristics of some brain sub-regions, the more severe the degree of brain atrophy may be, for example, the larger the volume of the ventricle, the more severe the degree of brain atrophy may be. When the morphological characteristics of the first brain sub-region are of this type, if the morphological characteristics of the first brain sub-region of the subject to be tested are greater than a certain proportion of peers, it indicates that the risk of brain atrophy of the subject to be tested may be greater. In some embodiments, for the morphological characteristics of such brain sub-regions, when the percentile of the measured value of the subject among their peers is greater than or equal to 95%, that is, only 5% of the peers have values ​​larger than the subject, and the values ​​of the other 95% are smaller than the subject, then the subject is considered to have a high risk of brain atrophy; when the percentile of the measured value of the subject among their peers is less than 95% and greater than or equal to 75%, the subject is considered to have a medium risk of brain atrophy; when the percentile of the measured value of the subject among their peers is less than 75%, the subject is considered to have a low risk of brain atrophy.

[0108] Figure 7 This is an exemplary flow chart of a method for determining the condition of a corresponding organ or tissue of a subject according to a change trend of morphological features of a sub-region of the subject as shown in some embodiments of the present application.

[0109] Step 701, obtaining follow-up data of the subject to be tested, wherein the follow-up data includes at least two images to be tested of the subject to be tested, each image to be tested corresponding to a different age. The precision of the age can be an integer, or it can be accurate to at least one decimal place. In some embodiments, the image of the subject to be tested can be collected once at the same interval (for example, every six months, every year, every one and a half years, every two years, etc.).

[0110] Step 703, segmenting a first sub-region from each image to be tested. Figure 5 The process is similar to step 503 in , and will not be described again here.

[0111] Step 705: Acquire the morphological features of the first sub-region in each image to be tested. Figure 5 The process is similar to step 505 in , and will not be described again here.

[0112] Step 707: determining the changing trend of the morphological features of the first sub-region of the subject under test with age according to the morphological features of the first sub-region of the subject under test at different ages.

[0113] In some embodiments, the changing trend of the morphological features of the first sub-region of the subject to be tested with age can be qualitatively determined. For example, it decreases with age, or increases with age. In some embodiments, the changing trend of the morphological features of the first sub-region of the subject to be tested with age can be quantitatively determined. For example, the rate of change of the morphological features of the first sub-region of the subject to be tested with age can be determined. Specifically, a curve can be drawn with the age of the subject to be tested as the horizontal coordinate and the morphological features of the first sub-region of the subject to be tested as the vertical coordinate, and the slope of the curve is determined as the rate of change of the morphological features of the first sub-region of the subject to be tested with age. For another example, a straight line can be fitted to show that the morphological features of the first sub-region of the subject to be tested change with age within the age range corresponding to the follow-up data of the subject to be tested.

[0114] Step 709: Determine a normal change trend of the morphological features of the first sub-region based on at least the age information corresponding to the partial sample images and the morphological features of the first sub-region in each of the at least partial sample images.

[0115] In some embodiments, the normal change trend of the morphological features of the first sub-region can be qualitatively determined. In some embodiments, the change trend of the morphological features of the first sub-region with age can be quantitatively determined. In some embodiments, the change rate of the morphological features of the first sub-region with age can be determined. In some embodiments, the normal change rate of each percentile of the morphological features of the first sub-region with age can be determined. For example, Figure 12 to Figure 14 The curves in represent the normal changes of the corresponding percentiles of gray matter volume, white matter volume and putamen volume with age, respectively, and the slopes of the curves can represent the normal change rates of the corresponding percentiles of gray matter volume, white matter volume and putamen volume with age. In some embodiments, a straight line showing the changes of the morphological features of the first brain sub-region with age under normal circumstances within the age range corresponding to the follow-up data of the subject can be fitted based on some brain sample images.

[0116] Step 711, determining the condition of the corresponding organ or tissue of the subject by comparing the change trend of the first sub-region of the subject with the normal change trend.

[0117] In some embodiments, the change trend of the first sub-region of the subject to be tested can be qualitatively compared with the normal change trend to determine the condition of the corresponding organ or tissue of the subject to be tested. For example, for normal people, the morphological characteristics of some sub-regions do not change significantly with age, while the morphological characteristics of the corresponding sub-region of the subject to be tested change significantly with age, then it can be considered that there is a risk in the condition of the corresponding organ or tissue of the subject to be tested. In some embodiments, the change trend of the first sub-region of the subject to be tested can be quantitatively compared with the normal change trend to determine the condition of the corresponding organ or tissue of the subject to be tested. For example, the change rate of the morphological characteristics of the first sub-region of the subject to be tested can be compared with the normal change rate of the morphological characteristics of the first sub-region of the subject to be tested, and the condition of the corresponding organ or tissue of the subject to be tested can be determined according to the difference between the change rate of the subject to be tested and the normal change rate. In some embodiments, at least one threshold value, such as a first threshold value and a second threshold value, can be set for the difference between the change rate of the subject to be tested and the normal change rate, and the first threshold value is greater than the second threshold value. If the difference between the change rate of the subject to be tested and the normal change rate is greater than the first threshold, it is considered that the corresponding organ or tissue of the subject to be tested has a higher risk; if the difference between the change rate of the subject to be tested and the normal change rate is greater than the second threshold but not greater than the first threshold, it is considered that the corresponding organ or tissue of the subject to be tested has a medium risk; if the difference between the change rate of the subject to be tested and the normal change rate is not greater than the second threshold, it is considered that the corresponding organ or tissue of the subject to be tested has a lower risk. In some embodiments, the angle between the straight line of the morphological characteristics of the first sub-region of the subject to be tested that changes with age and the straight line of the morphological characteristics of the first sub-region of the subject to be tested that changes with age under normal circumstances can be determined, and the condition of the corresponding organ or tissue of the subject to be tested is determined according to the angle. It can be understood that the smaller the angle, the closer the change trend of the morphological characteristics of the first sub-region of the subject to be tested is to the change trend of normal people within the age range corresponding to the follow-up data of the subject to be tested, and the more normal the corresponding organ or tissue of the subject to be tested is; conversely, the larger the angle, the greater the risk of the corresponding organ or tissue of the subject to be tested. In some embodiments, the risk level of the corresponding organ or tissue of the subject to be tested can be quantified according to the size of the angle. For example, when the angle is zero, the risk of the corresponding organ or tissue of the subject being tested is the lowest, and when the angle is 90°, the risk of the corresponding organ or tissue of the subject being tested is the highest.

[0118] It is to be understood that although the above embodiments are provided for determining the condition of the corresponding organ or tissue of the subject to be tested according to the change trend of the morphological characteristics of the first sub-region of the subject to be tested, these embodiments are not intended to limit the present application. In some embodiments, the change trend of the morphological characteristics of other sub-regions of the subject to be tested can also be determined and compared with the normal change trend. Ultimately, the change trend of each sub-region is combined to assess the condition of the corresponding organ or tissue of the subject to be tested.

[0119] Figure 12 to Figure 14 This is an example diagram comparing the change trend of morphological features of multiple sub-regions in the subject's brain image with the normal change trend according to some embodiments of the present application. The subject's brain images were collected at the age of 60, 61 and 62 to form follow-up data. Fig.12 It is a comparison between the change trend of the gray matter volume of the subject's brain with age and the normal change trend, the horizontal axis is age, the vertical axis is gray matter volume, wherein 1202, 1204, 1206, 1208, 1210 are the 95th percentile, 75th percentile, 50th percentile, 25th percentile, and 5th percentile change curves of the gray matter volume of normal people fitted according to the sample image with age; 1212 is the change curve of the gray matter volume of the subject's brain from 60 to 62 years old, and the three points on the curve represent the gray matter volume of the subject at the ages of 60, 61, and 62, respectively. Fig.13 It is a comparison between the change trend of the white matter volume of the brain of the subject with age and the normal change trend, the horizontal axis is age, the vertical axis is white matter volume, wherein 1302, 1304, 1306, 1308, 1310 are respectively the 95th percentile, 75th percentile, 50th percentile, 25th percentile, 5th percentile change curves of the white matter volume of normal people with age fitted according to the sample image; 1312 is the change curve of the white matter volume of the brain of the subject from 60 to 62 years old, and the three points on the curve represent the white matter volume of the subject at the ages of 60, 61 and 62 respectively. Fig.14 Figure 1 is a comparison of the change trend of the putamen volume of the subject's brain with age and the normal change trend. The horizontal axis is age and the vertical axis is the putamen volume. 1402, 1404, 1406, 1408, and 1410 are the 95th percentile, 75th percentile, 50th percentile, 25th percentile, and 5th percentile of the putamen volume of normal people fitted according to the sample image. 1412 is the change curve of the putamen volume of the subject's brain from 60 to 62 years old. The three points on the curve represent the putamen volume of the subject at the ages of 60, 61, and 62. It can be seen that the shrinkage rate of the gray matter, white matter, and putamen of the subject's brain is significantly greater than the shrinkage rate of the three sub-regions of the normal brain, and the percentiles of the putamen volume of the subject at the ages of 60, 61, and 62 are all less than 5%, indicating that the putamen volume of the subject is significantly smaller than that of peers, and the subject has a higher risk of brain atrophy.

[0120] Fig.15 and Fig.16 Schematic diagram of a medical image processing software interface according to some embodiments of the present application.

[0121] At least part of the functions of this application can be implemented by a software. Fig.15 (or Fig.16 ), in some embodiments, the software interface includes a control area 1502 (or 1602), and the user (such as a doctor) can import a single set of test data of the corresponding organ or tissue of the subject or follow-up data including multiple sets of test data into the software by clicking relevant buttons (such as the "Import Image" button) in the control area 1502 (or 1602). The user can also control the software to analyze the imported data by clicking relevant buttons (such as the "Brain Region Segmentation" button) in the control area 1502 (or 1602). In some embodiments, the software interface also includes a segmentation result display area 1504 (or 1604), which is used to display the segmentation results of the corresponding organs or tissues of the subject (such as the brain regions segmented from the brain image). Fig.15 As shown, in some embodiments, the segmentation result display area 1504 may also display image segmentation time-consuming information 1508. Fig.16 As shown, in some embodiments, when the data imported into the software is the follow-up data of the subject, the user can click on the analysis result of a sub-region (such as the analysis result of the "putamen") in the analysis result display area 1606, and the segmentation result display area 1604 will then display a comparison 1608 of the curve of the change of the morphological characteristics of the sub-region of the subject with the age and the curve of the change of the percentile of the morphological characteristics of the sub-region of the normal person with the age (1608 and Figure 12 to Figure 14 similar).

[0122] In some embodiments, the software interface may also include an analysis result display area 1506 (or 1606), which is used to display the analysis results of at least one sub-region of the corresponding organ or tissue of the subject to be tested, and the analysis results of each sub-region include the name of the sub-region, the morphological characteristics of the sub-region of the subject to be tested, the range of normal morphological characteristics of the sub-region among the subject's peers, the percentile of the morphological characteristics of the sub-region of the subject to be tested among peers, etc.

[0123] In some embodiments, the analysis result display area 1506 (or 1606) can display sub-areas with different risk levels. Fig.15 and 16The image is black and white, but the actual software interface can be in color. In some embodiments, the analysis results of the high-risk sub-regions can be displayed in a first color, the analysis results of the medium-risk sub-regions can be displayed in a second color, and the analysis results of the low-risk sub-regions can be displayed in a third color. For example, if the volume of the hippocampus and putamen of the subject is less than 5% of the percentile of the same age group, which is a high-risk sub-region, the hippocampus analysis result 15062 and the putamen analysis result 15063 (or 16062 and 16063) can be displayed in red; if the volume of the amygdala of the subject is between 5% and 25% of the percentile of the same age group, which is a medium-risk sub-region, the amygdala analysis result 15061 (or 16061) is displayed in yellow; if the volume of the anterior cingulate gyrus and the middle cingulate gyrus of the subject is greater than 25% of the percentile of the same age group, which is a low-risk sub-region, the anterior cingulate gyrus analysis result 15064 and the middle cingulate gyrus analysis result 15065 (or 16064 and 16065) are displayed in white. By distinguishing the display, users (such as doctors) can be prompted to pay attention to abnormal sub-regions.

[0124] In some embodiments, the software interface also includes a recommended diagnostic result display area 1510 (or 1610) for displaying recommended diagnostic results. The recommended diagnostic results are automatically generated by the software based on the analysis results of each sub-area. The user can make a diagnostic report with reference to the recommended diagnostic results. For example, the user can copy and paste the text in the recommended diagnostic result display area 1510 (or 1610) into the final diagnostic report; or, the user can click the corresponding button to import the text into the final diagnostic report.

[0125] Fig.17 It is a schematic diagram of a diagnostic report according to some embodiments of the present application.

[0126] In some embodiments, the diagnosis report may include the subject information 1702. The subject information includes but is not limited to the subject's serial number, name, gender, age, contact number, diagnosis physician, examination date, and other information.

[0127] In some embodiments, the diagnosis report may include the image segmentation result 1704 of the subject to be tested. The image segmentation result to be tested may include one or any combination of a transverse segmentation map, a sagittal segmentation map, and a coronal segmentation map.

[0128] In some embodiments, the diagnostic report may include morphological feature information 1706 of the corresponding organ or tissue of the subject to be tested, including the analysis result of at least one sub-region in the corresponding organ or tissue of the subject to be tested. The analysis result of each sub-region includes the name of the sub-region, the morphological feature of the sub-region of the subject to be tested, the range of normal morphological features of the sub-region among the subjects of the same age, the percentile of the morphological features of the sub-region of the subject to be tested among the subjects of the same age, etc. In some embodiments, only the analysis results of the sub-regions with higher risks of the subject to be tested may be displayed in the diagnostic report.

[0129] In some embodiments, the diagnosis report may include a comparison chart 1708 of the morphological features of at least one sub-region of the corresponding organ or tissue of the subject and that of a normal person. In some embodiments, the diagnosis report may only display a comparison chart of the morphological features of the sub-region with a higher risk of the subject and that of a normal person.

[0130] In some embodiments, the diagnostic report may further include a diagnostic result 1710. In some embodiments, the diagnostic result may be a recommended diagnostic result automatically generated by software.

[0131] In some embodiments, the diagnostic report can be completely automatically generated by software. In some embodiments, at least part of the content in the diagnostic report can be manually input by the user. For example, the user can Fig.15 (or Fig.16 ) into the image segmentation result 1704 of the diagnostic report. For another example, the user can Fig.16 The comparison chart 1608 of the high-risk sub-areas of the tested person and the normal person is imported into the diagnosis report 1708. For another example, the user can Fig.15 (or Fig.16 ) in the analysis result display area 1506 (1606) into the diagnostic report 1706. For another example, the user can Fig.15 (or Fig.16 ) in the recommended diagnosis result display area 1510 (or 1610) or copy and paste or import it into the diagnosis result 1710 of the diagnosis report; or, the user can manually input the final diagnosis result with reference to the recommended diagnosis result.

[0132] The beneficial effects that may be brought about by the embodiments of the present application include but are not limited to: (1) using a three-dimensional convolutional neural network for the segmentation of brain substructures for the first time, thereby obtaining the morphological characteristics of brain regions; (2) segmenting a medical image into several sub-regions, and comprehensively evaluating the conditions of the corresponding organs or tissues of the subject by comparing the morphological characteristics of each sub-region; (3) quantifying the risk level of the corresponding organs or tissues of the subject by comparing the specific values ​​of the morphological characteristics of the corresponding organs or tissues of a normal person with the morphological characteristics of the corresponding organs or tissues of the subject; (4) determining the change trend of the morphological characteristics of the corresponding organs or tissues of the subject based on the follow-up data of the subject, and determining the risk level of the corresponding organs or tissues of the subject by comparing with the change trend of the normal person. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0133] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0134] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0135] In addition, it will be understood by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0136] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0137] The computer program codes required for the operation of each part of the present application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0138] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0139] Similarly, it should be noted that in order to simplify the description disclosed in this application and thus help understand one or more embodiments, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

Claims

1. A medical image processing system, characterized in that: include: A test data acquisition module is used to acquire the test image of the test subject; A morphological feature determination module, used to determine the morphological features of a first sub-region to be measured in the image to be measured, wherein the first sub-region to be measured in the image to be measured corresponds to a sub-region of an organ or tissue of a subject to be measured; An analysis module, configured to determine, based on percentile values ​​of morphological features of sample areas in a first portion of sample images of a plurality of sample objects, a target percentile value of the morphological features corresponding to the subject to be tested among the morphological features of the sample areas corresponding to the plurality of sample objects, and determine the condition of the corresponding organ or tissue of the subject to be tested according to the target percentile; wherein the plurality of sample objects are of the same or similar age to the subject to be tested, the sample areas correspond to sub-areas of the organs or tissues; and the morphological features include at least one of volume, cortical thickness, cortical area, and gyrality index; The method of determining a target percentile value of the morphological feature corresponding to the subject among the morphological features of the sample areas corresponding to the multiple sample objects based on the percentile values ​​of the morphological features of the sample areas in the first part of the sample images of the multiple sample objects comprises: According to the age information corresponding to each of the sample images and the morphological features of the sample area in the first part of each of the sample images, the morphological features of the sample area in the sample images of each age are sorted according to numerical values, and at least one percentile of the morphological features of the sample area corresponding to each age is determined; Taking age as an independent variable and at least one percentile of the morphological characteristics of the sample area corresponding to each age as a dependent variable, fitting a curve of the morphological characteristics of the sample area changing with age; The age of the subject to be tested and the morphological features of the first sub-region of the subject to be tested are compared with the curve to determine the percentile of the morphological features of the first sub-region of the subject to be tested among people of the same age, so as to determine the target percentile value.

2. The medical image processing system according to claim 1, characterized in that: The multiple sample objects have the same gender as the subject.

3. The medical image processing system according to claim 1, characterized in that: The morphological features of the sample regions in the first part of the sample images of the plurality of sample objects include at least one of the volume of the organ or tissue, the volume of the sub-region, the thickness of the sub-region, or the surface area of ​​the sub-region.

4. The medical image processing system according to claim 1, characterized in that: The organ or tissue comprises the brain, and the morphological feature comprises at least one of brain volume, gray matter volume, white matter volume, putamen volume, cortical thickness, or cortical area.

5. The medical image processing system according to claim 1, characterized in that: The determining of the morphological features of the first sub-region to be tested in the image to be tested comprises: The first sub-region to be tested is segmented from the image to be tested using a deep learning model, wherein the training process of the deep learning model includes: Acquire a plurality of training images associated with a second sample organ or tissue of a second portion of the sample images of the plurality of sample objects, the second sample organ or tissue being of the same type as the organ or tissue of the subject; Obtain an initial deep learning model; determining a target deep learning model by training the initial deep learning model using the plurality of training images; and One or more morphometric methods are used to determine the morphological features of the first sub-region to be measured.

6. The medical image processing system according to claim 1, further comprising: arranging the morphological features corresponding to the first portion of the plurality of sample objects in descending order; as well as A percentile value of a morphological feature corresponding to a first portion of the plurality of sample objects is determined based on the ranking.

7. The medical image processing system according to claim 1, characterized in that: Determining the target percentile value corresponding to the morphological feature of the subject comprises: determining a relationship between the morphological features corresponding to the plurality of sample objects and the age of each of the plurality of sample objects; Determining the morphological features corresponding to the first sub-region to be tested according to the age of the subject to be tested; and Among the morphological features corresponding to the first part of the plurality of sample images of the plurality of sample objects, a target percentile value of the morphological feature corresponding to the subject is determined.

8. The medical image processing system according to claim 7, characterized in that: Also includes: A curve is fitted, wherein the curve represents a relationship between the morphological features corresponding to the plurality of sample objects and the age of each of the plurality of sample objects.

9. A medical image processing device, characterized in that: The apparatus comprises at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the following operations: Acquire a test image of the person to be tested; Determining the morphological features of a first sub-region to be tested in the image to be tested, wherein the first sub-region to be tested in the image to be tested corresponds to a sub-region of an organ or tissue of a subject to be tested; Based on the percentile values ​​of the morphological features of the sample areas in the first part of the sample images of the plurality of sample objects, a target percentile value of the morphological features corresponding to the subject is determined among the morphological features of the sample areas corresponding to the plurality of sample objects, and the condition of the corresponding organ or tissue of the subject is determined according to the target percentile; wherein the plurality of sample objects are the same or similar in age to the subject, and the sample areas correspond to sub-areas of the organs or tissues; The method of determining a target percentile value of the morphological feature corresponding to the subject among the morphological features of the sample areas corresponding to the multiple sample objects based on the percentile values ​​of the morphological features of the sample areas in the first part of the sample images of the multiple sample objects comprises: According to the age information corresponding to each of the sample images and the morphological features of the sample area in the first part of each of the sample images, the morphological features of the sample area in the sample images of each age are sorted according to numerical values, and at least one percentile of the morphological features of the sample area corresponding to each age is determined; Taking age as an independent variable and at least one percentile of the morphological characteristics of the sample area corresponding to each age as a dependent variable, fitting a curve of the morphological characteristics of the sample area changing with age; The age of the subject to be tested and the morphological features of the first sub-region of the subject to be tested are compared with the curve to determine the percentile of the morphological features of the first sub-region of the subject to be tested among people of the same age, so as to determine the target percentile value.

10. A computer-readable storage medium for medical image processing, characterized in that: The storage medium stores computer instructions, which, when executed by a processor, implement the following operations: Acquire a test image of the person to be tested; Determining the morphological features of a first sub-region to be tested in the image to be tested, wherein the first sub-region to be tested in the image to be tested corresponds to a sub-region of an organ or tissue of a subject to be tested; Based on the percentile values ​​of the morphological features of the sample areas in the first part of the sample images of the plurality of sample objects, a target percentile value of the morphological features corresponding to the subject is determined among the morphological features of the sample areas corresponding to the plurality of sample objects, and the condition of the corresponding organ or tissue of the subject is determined according to the target percentile; wherein the plurality of sample objects are the same or similar in age to the subject, and the sample areas correspond to sub-areas of the organs or tissues; The method of determining a target percentile value of the morphological feature corresponding to the subject among the morphological features of the sample areas corresponding to the multiple sample objects based on the percentile values ​​of the morphological features of the sample areas in the first part of the sample images of the multiple sample objects comprises: According to the age information corresponding to each of the sample images and the morphological features of the sample area in the first part of each of the sample images, the morphological features of the sample area in the sample images of each age are sorted according to numerical values, and at least one percentile of the morphological features of the sample area corresponding to each age is determined; Taking age as an independent variable and at least one percentile of the morphological characteristics of the sample area corresponding to each age as a dependent variable, fitting a curve of the morphological characteristics of the sample area changing with age; The age of the subject to be tested and the morphological features of the first sub-region of the subject to be tested are compared with the curve to determine the percentile of the morphological features of the first sub-region of the subject to be tested among people of the same age, so as to determine the target percentile value.

Images