CN109646026B

CN109646026B - Breast image de-scattering processing method and system

Info

Publication number: CN109646026B
Application number: CN201811557573.9A
Authority: CN
Inventors: 袁洲; 姚鹏; 张文日; 牛杰; 徐亮
Original assignee: Shanghai United Imaging Healthcare Co Ltd
Current assignee: Shanghai United Imaging Healthcare Co Ltd
Priority date: 2018-12-19
Filing date: 2018-12-19
Publication date: 2022-07-22
Anticipated expiration: 2038-12-19
Also published as: CN109646026A

Abstract

The embodiment of the application discloses a mammary gland image de-scattering processing method, which comprises the following steps: collecting a mammary gland image under a certain compression thickness; segmenting a tissue region and an unorganized region from the mammary gland image; based on the mammary gland image, the first scattering kernels and the second scattering kernels, performing backscatter iterative processing on a tissue area of the mammary gland image by using the first scattering kernels, and performing backscatter iterative processing on a non-tissue area of the mammary gland image by using the second scattering kernels to estimate a first scatter contribution of the tissue area to the scattering image and a second scatter contribution of the non-tissue area to the scattering image, so as to obtain a backscatter mammary gland image.

Description

Breast image de-scattering processing method and system

Technical Field

The application relates to the field of image processing, in particular to a method and a system for processing the backscatter of a mammary image.

Background

Imaging examination is one of the most important examination methods for breast disease diagnosis and breast cancer screening. The imaging techniques commonly used for diagnosing breast diseases mainly include B-mode ultrasound, breast CT tomography, breast MRI tomography, breast X-ray photography, and the like. Whether a breast test image can provide sufficient information for breast diagnosis depends on the quality of the test image. There are many factors that affect the quality of the detected image, and scattered radiation is one of the more important factors. Scattered rays can reduce the contrast and signal-to-noise ratio of a detected image, blur details and seriously affect the diagnostic value of a mammary gland detection image. Scattered radiation is generated by two components: the existing image de-scattering method has poor effect of removing the scattering generated by the latter part of the mammary gland part and the compression plate which is not attached to the mammary gland. A method for effectively rejecting scattered radiation should therefore be provided.

Disclosure of Invention

One of the embodiments of the present application provides a method for processing a breast image by de-scattering, which includes acquiring a breast image under a certain compression thickness; segmenting a tissue region and an unorganized region from the mammary gland image; based on the mammary gland image, the first scattering kernels and the second scattering kernels, performing backscatter iterative processing on an organized area of the mammary gland image by using the first scattering kernels, and performing backscatter iterative processing on an unorganized area of the mammary gland image by using the second scattering kernels so as to estimate a first scatter contribution of the organized area to a scatter image and a second scatter contribution of the unorganized area to the scatter image, and obtaining a backscatter mammary gland image.

In some embodiments, the first scattering kernel is associated with scattering properties of an equivalent phantom of a thickness that approximates the properties of the breast being compressed, wherein the first scattering kernel is iteratively updated in an iterative process.

In some embodiments, the second scattering kernel is associated with a compression paddle at the compression thickness, the second scattering kernel determined from the plurality of second scattering kernels based on the compression thickness.

In some embodiments, the second scattering kernel is associated with scattering properties of an equivalent phantom of a certain thickness having similar properties of a combination of a compression plate and an air layer, and the second scattering kernel is iteratively updated in an iterative process, wherein the air layer refers to an air layer between the compression plate and the detector.

In some embodiments, said estimating a first scatter contribution of said tissue-bearing region to a scatter image and a second scatter contribution of said tissue-free region to a scatter image, obtaining a de-scattered breast image comprises: initializing, and taking the segmented mammary gland image as an initial de-scattering mammary gland image; iteratively: determining a first scatter contribution of an organized region to the breast image based on the organized region and first scatter kernels and a second scatter contribution of an unorganized region to the breast image from the unorganized region and second scatter kernels; determining a de-scattered breast image from the breast image, the first scatter contribution and the second scatter contribution; and judging whether the de-scattering mammary gland image meets a termination condition, if not, continuing iteration, and if so, terminating iteration.

In some embodiments, said determining a first scatter contribution to said breast image from said organized region and a first scatter kernel comprises: estimating the thickness of the equivalent phantom based on an initial image without a compression plate and a mammary gland and the tissue region de-scattering image; based on the thickness of the equivalent phantom, corresponding first scattering kernels are taken from a plurality of first scattering kernels; convolving the descattering image of the organized area with the corresponding first scattering kernel to obtain a first scattering contribution of the organized area to the mammary gland image.

In some embodiments, said determining a second scatter contribution to said breast image from said tissue-free region and a second scatter kernel comprises: calling a corresponding second scattering kernel from the plurality of second scattering kernels based on the certain compression thickness; and convolving the non-tissue area with a corresponding second scattering kernel to obtain a second scattering contribution of the non-tissue area to the mammary gland image.

In some embodiments, said determining a second scatter contribution to said breast image from said tissue free region and a second scatter kernel further comprises: estimating the thickness of the equivalent phantom based on the initial image without the compression plate and the breast and the non-tissue region de-scattering image; calling a corresponding second scattering kernel from a plurality of second scattering kernels based on the thickness of the equivalent phantom; and convolving the non-tissue area with a corresponding second scattering kernel to obtain a second scattering contribution of the non-tissue area to the mammary gland image.

In some embodiments, the reconstruction results in a three-dimensional breast image based on a plurality of said de-scattered breast images.

One embodiment of the present application provides a system for processing breast image de-scattering. The system comprises an image acquisition module, an image segmentation module and a de-scattering module: the image acquisition module is used for acquiring a mammary gland image under a certain compression thickness; the image segmentation module is used for segmenting a tissue region and an unorganized region from the mammary gland image; and the de-scattering module is used for performing de-scattering iterative processing on the organized region of the mammary gland image by using the first scattering kernels and performing de-scattering iterative processing on the unorganized region of the mammary gland image by using the second scattering kernels based on the mammary gland image, the plurality of first scattering kernels and the plurality of second scattering kernels so as to estimate a first scattering contribution of the organized region to the scattering image and a second scattering contribution of the unorganized region to the scattering image, and obtaining the de-scattering mammary gland image.

One of the embodiments of the present application provides a mammary gland image de-scattering processing apparatus, which includes at least one processor and at least one storage medium; the at least one storage medium is configured to store computer instructions; the at least one processor is configured to execute the computer instructions to implement the method for processing breast image backscatter as described in any embodiment of the present application.

One of the embodiments of the present application provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed, the method for processing breast image de-scattering described in any one of the embodiments of the present application is implemented.

Drawings

The present application will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals refer to like structures, wherein:

FIG. 1 is a diagram of an application scenario for an imaging system according to some embodiments of the present application;

FIG. 2 is a block diagram of an exemplary computing device for implementing a dedicated system according to aspects of the subject application;

FIG. 3 is a block diagram of an exemplary mobile device 300 for implementing a dedicated system in accordance with aspects of the subject application;

FIG. 4 is an exemplary block diagram of a processing device 140 according to some embodiments of the present application; and

fig. 5 is an exemplary flow diagram of a method of breast image backscatter processing, shown in accordance with some embodiments of the present application.

Detailed Description

In the following detailed description, specific details of the embodiments are set forth by way of examples in order to provide a thorough understanding of the related inventions. It will be apparent, however, to one skilled in the art that the present application may be practiced without these specific details. In other instances, well-known methods, procedures, systems, components, and/or circuits have been described at a high-level (without detail) in order to avoid unnecessarily obscuring aspects of the present application. Various obvious modifications to the embodiments of the present application will be apparent to those skilled in the art. The general principles in this application may be applied to other embodiments and applications without departing from the spirit and scope of the application. Thus, the present application is not limited to the embodiments shown, but is to be accorded the widest scope consistent with the claims.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and/or groups thereof.

It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to or removed from these processes.

It should be understood that the application scenarios of the system and method of the present application are only examples or embodiments of the present application, and it is obvious for those skilled in the art that the present application can also be applied to other similar scenarios according to the drawings without any creative effort. For example, for assessing the health of other human organs or tissues.

Fig. 1 is a diagram of an application scenario of an imaging system 100 according to some embodiments of the present application.

As shown in fig. 1, the image forming system 100 may include an image forming apparatus 110, a network 120, at least one terminal 130, a processing device 140, and a storage device 150. In some embodiments, imaging system 100 may comprise a mammography system. In some embodiments, the mammography system may include, but is not limited to, Digital Mammography (DM), Full digital mammography (FFDM), Digital Breast Tomography (DBT), and the like. In some embodiments, the imaging apparatus 110, the at least one terminal 130, the processing device 140, and/or the storage device 150 may be connected or in communication with each other by a wired connection, a wireless connection (e.g., the network 120), or any combination thereof. The manner of connection between the components of the imaging system 100 may be variable. By way of example only, the imaging apparatus 110 may be connected to the processing device 140 via the network 120, as shown in fig. 1. As another example, the imaging device 110 may be directly connected to the processing apparatus 140. As another example, storage device 150 may be connected to processing device 140 through network 120 or storage device 150 may be directly connected to processing device 140, as shown in FIG. 1. As an example, terminal 130 may be connected to processing device 140 through network 120 or terminal 130 may be directly connected to processing device 140, as shown in fig. 1.

The imaging device 110 may include a radiation source 111, a compression plate 113, a detector 114, a motor (not shown), and a breast 115 to be detected.

In some embodiments, the radiation source 111 may be fixed, movable (including left, right, up, down movement) above the stationary compressed breast to be detected 115, or the radiation source 111 may rotate with the stationary compressed breast to be detected 115 as a rotation center. In some embodiments, the radiation source 111 may emit soft X-rays (e.g., molybdenum target X-rays of around 30 kV). In some embodiments, the target material of the radiation source 111 may comprise tungsten, molybdenum, copper, rhodium, silver, aluminum, and the like. In some embodiments, the radiation 112 (e.g., X-rays) emitted by the radiation source 111 may be considered a pencil beam matrix. In some embodiments, the compression plate 113 compresses the breast 115 to be detected to regularly reduce the thickness of the breast 115 to be detected, so that the breast 115 to be detected is thin and uniform. The overlapping soft tissues in the breast 115 structure to be examined are isolated. And fixes the breast 115 to be detected to prevent the movement of the breast 115 to be detected from causing image blurring and the like. In some embodiments, the smaller the thickness of the breast 115 to be detected, the less scattered radiation it generates and the higher the contrast of the image. Thus, within the tolerance range of the subject (e.g., tolerance to pain), the greater the compression of the breast 115 to be tested, the better.

In some embodiments, the detector 114 may include an X-ray detector, film, or the like. In some embodiments, the structure of the X-ray detector may include a detector housing (not shown), an image receptor, and the like.

In some embodiments, the use of the imaging device 110 includes: the subject places the breast 115 to be detected above the casing (not shown in the figure) of the detector 114, the lower plane of the compression plate 113 is attached to the upper part of the breast 115 to be detected, and the motor is started to slowly press the compression plate 113 down until a certain compression state is reached, wherein the certain compression state is related to the tolerance range (such as tolerance to pain) of the subject. The radiation source 111 emits radiation 112 to penetrate the compression plate, the compressed breast 115 to be detected (i.e. the breast 115 to be detected under a certain compression thickness), an air layer between the compression plate and the detector (i.e. the air layer under a certain compression thickness), and/or an air layer between a detector housing (not shown in the figure) and the image receiver, and then images on the detector 114. In some embodiments, the source of radiation may be fixed, moved (including left, right, up, down) over the compressed breast, or the source of radiation may be rotated (e.g., -45 ° -45 ° rotation) with the compressed breast as the center of rotation, and then at least one two-dimensional breast image may be acquired directly by the detector. In other embodiments, a three-dimensional breast image may be reconstructed using at least two-dimensional breast images.

Network 120 may include any suitable network that may facilitate the exchange of information and/or data for imaging system 100. In some embodiments, at least one component of imaging system 100 (e.g., imaging apparatus 110, processing device 140, storage device 150, terminal 130) may exchange information and/or data with at least one other component in imaging system 100 via network 120. For example, the processing device 140 may obtain breast images (e.g., two-dimensional breast images) from the imaging apparatus 110 via the network 120. As another example, processing device 140 may obtain user (e.g., physician) instructions from terminal 130 via network 120. Network 120 may be or include a public network (e.g., the internet), a private network (e.g., a Local Area Network (LAN)), a wired network, a wireless network (e.g., an 802.11 network, a Wi-Fi 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 any combination thereof. For example, network 120 may include a wireline network, a wireless network, a fiber optic network, a telecommunications network, an intranet, a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), Bluetooth^TMNetwork and ZigBee^TMA network, a Near Field Communication (NFC) network, the like, or any combination thereof. In some embodiments, network 120 may include at least one network access point. For example, network 120 may include wired and/or wireless network access points, such as base stations and/or internet exchange points, through which at least one component of imaging system 100 may connect to network 120 to exchange data and/or information.

In some embodiments, a user (e.g., a physician, etc.) may operate the imaging 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, and the like. In some embodiments, the terminal 130 may include a mobile device 131, a tablet computer 132, a laptop computer 133, and the like, or any combination thereof. For example, mobile device 131 may include a mobile phone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, a point of sale (POS) device, the like, or any combination thereof. In some embodiments, terminal 130 may include input devices, output devices, and the like. The input devices may include alphanumeric and other keys, and may optionally be a keyboard, touch screen (e.g., with tactile or haptic feedback) input, voice input, eye tracking input, brain monitoring system, or any other similar input mechanism. Input information received via the input device may be transmitted, e.g., via a bus, to the processing device 140 for further processing. Other types of input devices may include cursor control devices such as a mouse, a trackball, or cursor direction keys, among others. Output devices may include a display, speakers, printer, etc., or any combination thereof. In some embodiments, the terminal 130 may comprise a portion of the processing device 140.

Processing device 140 may process data and/or information obtained from imaging apparatus 110, storage device 150, terminal 130, or other components of imaging system 100. For example, the processing device 140 may estimate a scatter image thereof based on a breast image (e.g., a two-dimensional breast image) generated by the imaging apparatus 110, and/or perform a de-scatter process. In some embodiments, the processing device 140 may include a single server or a group of servers. The server groups may include centralized or distributed. In some embodiments, the processing device 140 may comprise local or remote to the imaging system 100. For example, processing device 140 may access information and/or data from imaging apparatus 110, storage device 150, and/or terminal 130 via network 120. As another example, processing device 140 may be directly connected to imaging apparatus 110, terminal 130, and/or storage device 150 to access information and/or data. In some embodiments, the processing device 140 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-tier cloud, and the like, or any combination thereof. In some embodiments, processing device 140 may be executed by a computing device 200 (as described in fig. 2) having one or more components.

Storage device 150 may store data, instructions, and/or any other information. In some embodiments, the storage device 150 may store the a priori data. Wherein the a priori data includes imaging system 100 parameters and scatter nuclear data. In particular, the a priori data may include at least one of: compression paddle 113 material, compression paddle 113 thickness, initial image without compression paddle and without breast, first plurality of scattering nuclei, second plurality of scattering nuclei.

In some embodiments, the first scattering kernel may be associated with scattering properties of an equivalent phantom of a thickness that approximates the properties of the breast being compressed. In particular, due to the influence of the breast inhomogeneity to be detected and other factors, the radiation passing through the breast and the scattered radiation generated cannot be accurately estimated. A Monte Carlo algorithm may be used to simulate a distribution of a ratio of a number of scattered rays (e.g., X-rays) generated by an equivalent phantom with different thicknesses irradiated by rays (e.g., X-rays) from a radiation source to a number of rays (e.g., X-rays) directly penetrating the equivalent phantom, wherein each thickness of the equivalent phantom corresponds to a first scattering kernel. In some embodiments, the equivalent phantom is similar to the breast property to be detected (e.g., material, energy absorption coefficient for radiation, etc.). In some embodiments, the equivalent phantom may comprise a PMMA phantom, or the like. In some embodiments, the thickness of an equivalent phantom may include, but is not limited to: 30mm, 50mm, 60mm, etc. In some embodiments, the monte carlo algorithm may include: EGSnrc, Geant4, ETRAN, EGS4, MCNP, FLUKA, an autonomously developed Monte Carlo algorithm, and the like. In some embodiments, the first scattering kernel may comprise discrete data or a fitted analytical formula.

In some embodiments, the second scattering kernel is determined from the plurality of second scattering kernels based on the compression thickness. Specifically, the second scattering nuclei may be a ratio distribution of the number of scattered rays (e.g., X-rays) generated after the rays 112 (e.g., X-rays) emitted from the radiation source 111 penetrate through the compression plates with different thicknesses and the air layers with different thicknesses between the compression plates and the detector (i.e., the air layers with different compression thicknesses), and the number of directly penetrating rays (e.g., X-rays). Wherein, each compression plate thickness and each air layer thickness correspond to one second scattering core.

In still other embodiments, a Monte Carlo algorithm may be used to simulate a distribution of the number of scattered rays (e.g., X-rays) generated after rays 112 (e.g., X-rays) from the source 111 illuminate equivalent phantoms of different thicknesses, where each thickness of the equivalent phantom corresponds to a second scattering kernel, compared to the number of rays (e.g., X-rays) that directly traverse the equivalent phantom. In some embodiments, the equivalent mold body and the compression plate have similar properties (e.g., energy absorption coefficient for radiation, etc.) to the combination of the compression plate and the air layer, wherein the air layer may refer to the air layer between the compression plate and the detector (i.e., the air layer under a certain compression thickness). In some embodiments, the thickness of an equivalent mold body may include, but is not limited to: 30mm, 50mm, 60mm, etc. In some embodiments, the monte carlo algorithm may comprise: EGSnrc, Geant4, ETRAN, EGS4, MCNP, FLUKA, an autonomously developed Monte Carlo algorithm, and the like. In some embodiments, the second scattering kernel may include discrete data or a fitted analytical formula.

In some embodiments, the storage device 150 may store data obtained from the imaging apparatus 110, the terminal 130, and/or the processing device 140 (e.g., mechanically fed compression thickness data). In some embodiments, storage device 150 may store data and/or instructions that are used by processing device 140 to perform or use to perform the exemplary methods described in this application. In some embodiments, the storage device 150 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read and write memories can include Random Access Memory (RAM). Exemplary RAM may include Dynamic Random Access Memory (DRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Static Random Access Memory (SRAM), thyristor random access memory (T-RAM), zero capacitance random access memory (Z-RAM), and the like. Exemplary read-only memories may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (perrom), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory (dvd-ROM), and the like. In some embodiments, the storage device 150 may be implemented on a cloud platform, as described elsewhere in this application.

In some embodiments, a storage device 150 may be connected to the network 120 to communicate with at least one other component (e.g., processing device 140, terminal 130) in the imaging system 100. At least one component in imaging system 100 may access data or instructions in storage device 150 via network 120. In some embodiments, the storage device 150 may comprise a portion of the processing device 140.

It should be noted that the foregoing is provided for illustrative purposes only, and is not intended to limit the scope of the present application. Many variations and modifications will occur to those skilled in the art in light of the teachings herein. The features, structures, methods, and other features of the example embodiments described herein may be combined in various ways to obtain additional and/or alternative example embodiments. For example, the storage device 150 may include data storage comprising a cloud computing platform, such as a public cloud, a private cloud, a community and hybrid cloud, and so forth. However, variations and modifications may not depart from the scope of the present application.

FIG. 2 is a block diagram of an exemplary computing device for implementing a dedicated system of the subject technology. As shown in FIG. 2, computing device 200 may include a processor 210, memory 220, input/output (I/O)230, and communication ports 240.

The processor 210 may execute computer instructions (e.g., program code) and perform the functions of the processing device 140 according to the methods described herein. The computer instructions may include, for example, conventional methods, procedures, objects, components, data structures, procedures, modules, and functions that perform the particular functions described herein. For example, processor 210 may process data for imaging apparatus 110, terminal 130, storage device 150, and/or any other component in imaging system 100. In some embodiments, processor 210 may include at least one hardware processor, such as a microcontroller, microprocessor, Reduced Instruction Set Computer (RISC), Application Specific Integrated Circuit (ASIC), application specific set of instruction processor (ASIP), Central Processing Unit (CPU), Graphics Processing Unit (GPU), Physical Processing Unit (PPU), microcontroller unit, Digital Signal Processor (DSP), Field Programmable Gate Array (FPGA), high-order RISC machine (ARM), Programmable Logic Device (PLD), any circuit or processor capable of performing at least one function, or the like, or any combination thereof.

For purposes of illustration only, only one processor is depicted in computing device 200. However, it should be noted that the computing device 200 in the present application may also comprise multiple processors, whereby operations and/or method steps described in the present application as being performed by one processor may also be performed by multiple processors, jointly or separately. For example, if in the present application, the processors of computing device 200 perform operations a and B, it should be understood that operations a and B may also be performed by multiple different processors in computing device 200, collectively or individually (e.g., a first processor performing operation a and a second processor performing operation B, or a first processor and a second processor performing operations a and B collectively).

Memory 220 may store data/information obtained from imaging apparatus 110, terminal 130, storage device 150, and/or any other component in imaging system 100. In some embodiments, memory 220 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), the like, or any combination thereof. For example, mass storage may include a magnetic disk, optical disk, solid state disk, and the like. Removable storage may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Volatile read and write memory can include Random Access Memory (RAM). RAM may include Dynamic RAM (DRAM), double-data-rate synchronous dynamic RAM (DDRSDRAM), Static RAM (SRAM), thyristor RAM (T-RAM), zero-capacitance (Z-RAM), and the like. Exemplary read-only memories may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (perrom), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory, and the like. In some embodiments, memory 220 may store at least one program and/or instructions for performing the example methods described herein.

I/O230 may input and/or output signals, data, information, and the like. In some embodiments, I/O230 may enable a user to interact with processing device 140. In some embodiments, I/O230 may include input devices and output devices. Exemplary input devices may include a keyboard, mouse, touch screen, microphone, etc., or any combination thereof. Exemplary output devices may include a display device, speakers, printer, projector, etc., or any combination thereof. Exemplary display devices may include Liquid Crystal Displays (LCDs), Light Emitting Diode (LED) based displays, flat panel displays, curved displays, television devices, cathode ray tubes, and the like, or any combination thereof.

The communication port 240 may be connected to a network (e.g., network 120) to facilitate data communication. The communication port 240 may establish a connection between the processing device 140 and the imaging apparatus 110, the terminal 130, and/or the storage device 150. The connection may include a wired connection, a wireless connection. The wired connection may include, for example, an electrical cable, an optical cable, a telephone line, etc., or any combination thereof. The wireless connection may comprise, for example, Bluetooth^TMLink, Wi-Fi^TMLink, WiMax^TMA link, a WLAN link, a ZigBee link, a mobile network link (e.g., 3G, 4G, 5G, etc.), etc., or any combination thereof. In some embodiments, the communication port 240 may include and/or include a standardized communication port, such as RS232, RS485, and the like. In some embodiments, the communication port 240 may comprise a specially designed communication port. For example, the communication port 240 may be designed in accordance with the digital imaging and communications in medicine (DICOM) protocol.

Fig. 3 is a block diagram of an exemplary mobile device 300 for implementing a dedicated system of the subject technology. As shown in fig. 3, the mobile device 300 may include a display unit 310, a communication unit 320, a Graphics Processor (GPU)330, a Central Processing Unit (CPU)340, an input/output unit 350, a memory 360, an operating system 370, application programs 380, a storage 390, and the like. In some embodiments, operating system 370 (e.g., iOS, Android, windows phone, etc.) and application programs 380 may be loaded into memory 360 for execution by CPU 340. The applications 380 may include a browser or application for receiving imaging, backscatter graphics processing, or other relevant information from the imaging system 100.

FIG. 4 is an exemplary block diagram of an imaging system according to some embodiments of the present application. The imaging system 100 may include an image acquisition module 410, an image segmentation module 420, and a backscatter module 430.

The image acquisition module 410 may acquire an image of the breast at a certain compression thickness. In some embodiments, the source of radiation may be fixed, moved (including left, right, up, down) over the compressed breast, or the source of radiation may be rotated (e.g., -45 ° -45 ° rotation) with the compressed breast as the center of rotation, and then at least one two-dimensional breast image may be acquired directly by the detector. In other embodiments, a three-dimensional breast image may be reconstructed using at least two-dimensional breast images. In some embodiments, the compression thickness may be a distance between the compression paddle and the detector after the breast 115 to be detected is compressed by the compression paddle. In some embodiments, a method of acquiring a breast image comprises: the subject places the breast 115 to be detected above the casing of the detector (not shown in the figure), the lower plane of the compression plate 113 is attached to the upper part of the breast 115 to be detected, and the motor is started to slowly press the compression plate 113 until a certain compression state is reached. The radiation source 111 emits radiation 112 to penetrate through the breast 115 to be detected and then image the breast on the detector 114 (e.g., two-dimensional breast image, three-dimensional breast image, etc.). In some embodiments, the less the compression thickness of the breast 115 to be detected, the less scattered radiation it generates and the higher the contrast of the image. Thus, to further reduce image artifacts, the greater the compression of the breast 115 to be examined, within the tolerance range of the subject (e.g., tolerance to pain).

The image segmentation module 420 may segment the organized and unorganized regions from the breast image. In some embodiments, the image segmentation algorithm may be selected from, but not limited to, a threshold-based segmentation method, an edge-based segmentation method, a region-based segmentation method, a cluster analysis-based image segmentation method, a wavelet transform-based segmentation method, a mathematical morphology-based segmentation method, an artificial neural network-based segmentation method, and the like.

The backscatter module 430 may perform backscatter iterative processing on the organized region and the non-organized region of the breast image with the first scatter kernel and the second scatter kernel respectively based on the breast image, the plurality of first scatter kernels and the plurality of second scatter kernels to estimate a first scatter contribution of the organized region to the scatter image and a second scatter contribution of the non-organized region to the scatter image, so as to obtain a backscatter breast image, wherein the first scatter kernel is updated iteratively in an iterative process.

In some embodiments, the backscatter module 430 may obtain a priori data from the storage module 150. In some embodiments, the a priori data may include at least one of: a compression plate material, a compression plate thickness, an initial image without a compression plate and without a breast, a plurality of first scattering nuclei, a plurality of second scattering nuclei, and the like.

In some embodiments, the compression plate material may comprise a metallic material, a non-metallic material, a polymeric material, or the like. In some embodiments, compression plate thickness may include, but is not limited to, 10mm, 30mm, 50mm, 60mm, and the like. In some embodiments, the initial image without a compression paddle and without tissue may refer to: in the absence of a compression plate and the absence of a breast 115 to be examined in the imaging system 100, the radiation (e.g., X-rays) emitted by the radiation source 111 is imaged (e.g., two-dimensional, three-dimensional) on the detector 114.

In some embodiments, the radiation that ray 112 traverses the breast and the resulting scattered radiation cannot be accurately estimated due to factors such as the heterogeneity of the breast being examined. A Monte Carlo algorithm may be used to simulate the distribution of the number of scattered rays (e.g., X-rays) generated after rays 112 (e.g., X-rays) from the source 111 illuminate equivalent phantoms of different thicknesses, each thickness of the equivalent phantom corresponding to a first scattering kernel, versus the number of rays (e.g., X-rays) that directly traverse the equivalent phantom. In some embodiments, the equivalent phantom is similar to the breast 115 property (e.g., material, energy absorption coefficient for radiation, etc.) to be detected. In some embodiments, the equivalent phantom may comprise a PMMA phantom, or the like. In some embodiments, the thickness of an equivalent mold body may include, but is not limited to: 30mm, 50mm, 60mm, etc. In some embodiments, the monte carlo algorithm may comprise: EGSnrc, Geant4, ETRAN, EGS4, MCNP, FLUKA, an autonomously developed Monte Carlo algorithm, and the like. In some embodiments, the first scattering kernel may include discrete data or a fitted analytical formula.

In some embodiments, a first scattering kernel corresponding to the equivalent thickness may be retrieved from the plurality of first scattering kernels based on the equivalent thickness. Wherein the first scattering kernel is iteratively updated in an iterative process.

In some embodiments, the second scattering nuclei may be a ratio distribution of the number of scattered rays (e.g., X-rays) generated after the rays 112 (e.g., X-rays) emitted from the radiation source 111 penetrate through the compression plate with different thicknesses and the air layer with different thicknesses between the compression plate and the detector (i.e., the air layer with different compression thicknesses), and the number of directly penetrating rays (e.g., X-rays). Wherein, each compression plate thickness and each air layer thickness correspond to one second scattering core.

In some embodiments, the backscatter module 430 may further include a mechanical feedback unit, and the compression thickness of the mechanical feedback may be obtained. In some embodiments, a second scattering kernel corresponding to the compression thickness may be retrieved from the plurality of second scattering kernels based on the compression thickness. Wherein the second scattering kernel is not updated during the iteration process.

In other embodiments, a Monte Carlo algorithm may be used to simulate the distribution of the number of scattered rays (e.g., X-rays) generated after the radiation 112 (e.g., X-rays) from the radiation source 111 irradiates equivalent phantoms of different thicknesses, where each thickness of the equivalent phantom corresponds to a second scattering kernel, and the number of the scattered rays (e.g., X-rays) directly penetrates through the equivalent phantom. In some embodiments, the equivalent mold body and the compression plate have similar properties (e.g., energy absorption coefficient for radiation, etc.) to the combination of the compression plate and the air layer, wherein the air layer may refer to the air layer between the compression plate and the detector (i.e., the air layer under a certain compression thickness). In some embodiments, the thickness of an equivalent phantom may include, but is not limited to: 30mm, 50mm, 60mm, etc. In some embodiments, the monte carlo algorithm may include: EGSnrc, Geant4, ETRAN, EGS4, MCNP, FLUKA, an autonomously developed Monte Carlo algorithm, and the like. In some embodiments, the second scattering kernel may include discrete data or a fitted analytical formula.

In some embodiments, a second scattering kernel corresponding to the equivalent thickness may be retrieved from the plurality of second scattering kernels based on the equivalent thickness. Wherein the second scattering kernel is iteratively updated in an iterative process.

In some embodiments, the step of obtaining the image of the de-scattered breast by iteration may comprise:

and an initialization step, wherein the segmented mammary gland image is used as an initial de-scattering mammary gland image.

An iteration step:

a first scatter contribution of the organized region to the breast image is determined based on the organized region and the first scatter kernel and a second scatter contribution of the unorganized region to the breast image is determined from the unorganized region and the second scatter kernel.

Determining a de-scattered breast image from the breast image, the first scatter contribution and the second scatter contribution.

And judging whether the de-scattering mammary gland image meets a termination condition, if not, continuing iteration, and if so, terminating iteration.

For more description of the method of the breast image de-scatter processing, reference may be made to fig. 5 and its description.

It should be noted that the above description regarding the processing device 140 is provided for illustrative purposes only and is not intended to limit the scope of the present application. Various modifications and changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. In some embodiments, at least one additional module may be added, or multiple modules of the processing device 140 may be combined into one module. For example, the processing device 140 may further include a storage module.

Fig. 5 is an exemplary flowchart 500 of a breast image backscatter processing method shown according to some embodiments of the application.

In some embodiments, at least one operation of process 500 shown in fig. 5 may be implemented by imaging system 100 shown in fig. 1. For example, at least a portion of process 500 shown in fig. 5 may be stored in storage device 150 in the form of instructions and invoked and/or executed by processing device 140 (e.g., processor 210 of a computing device as shown in fig. 2, GPU330 or CPU340 of mobile device 300 as shown in fig. 3).

At 502, the image obtaining module 410 may collect a breast image (e.g., a two-dimensional breast image, a three-dimensional breast image, etc.) of the breast 115 to be detected under a certain compression thickness. In some embodiments, the compression thickness may be a distance between the compression paddle and the detector after the breast 115 to be detected is compressed by the compression paddle. In some embodiments, a method of acquiring a breast image comprises: the subject places the breast 115 to be detected above the casing of the detector (not shown in the figure), the lower plane of the compression plate 113 is attached to the upper part of the breast 115 to be detected, and the motor is started to slowly press the compression plate 113 until a certain compression state is reached. The radiation source 111 emits radiation 112 to penetrate through the breast 115 to be detected and then to be imaged (e.g., two-dimensional breast image, three-dimensional breast image, etc.) on the detector 114. In some embodiments, the less the compression thickness of the breast 115 to be detected, the less scattered radiation it generates and the higher the contrast of the image. Thus, to further reduce image artifacts, the greater the compression on the breast 115 to be examined, within the tolerance range of the subject (e.g., tolerance to pain).

At 504, the image segmentation module 420 can segment the organized region and the unorganized region from the breast image (e.g., a two-dimensional breast image). In some embodiments, the image segmentation algorithm may be selected from, but not limited to, a threshold-based segmentation method, an edge-based segmentation method, a region-based segmentation method, a cluster analysis-based image segmentation method, a wavelet transform-based segmentation method, a mathematical morphology-based segmentation method, an artificial neural network-based segmentation method, and the like.

In 506, the backscatter module 430 may initialize a backscatter breast image. In some embodiments, the initializing step may include treating the segmented breast image as a first backscatter breast image, wherein the first backscatter image may include a first organized region backscatter image and a first unorganized region backscatter image.

In 508, the backscatter module 430 can determine a first scatter contribution of the organized region to the breast image based on the organized region and the first scatter kernel and a second scatter contribution of the unorganized region to the breast image from the unorganized region and the second scatter kernel.

In some embodiments, determining a first scatter contribution of the organized region to the breast image based on the organized region and the first scatter kernel may comprise: convolving the first tissue region de-scattered image with a corresponding first scattering kernel to obtain a first scattering contribution, wherein the first scattering kernel is iteratively updated in an iterative process. In particular, the amount of the solvent to be used,

first, based on a priori data (e.g., initial image without compression plate and without tissue) and a first tissue region backscatter image, an equivalent thickness of a phantom (e.g., PMMA phantom) that approximates the measured breast properties (e.g., material, energy absorption coefficient for radiation, etc.) is estimated, as in equation (1):

T＝log(I/P)/M_U(1)

wherein T represents equivalent thickness, I represents a pre-stored initial image without compression plate and without tissue, P represents a tissue region de-scattering image, and M_UIs the linear attenuation coefficient of the phantom. In some embodiments, T M of the same phantom of different thickness may also be pre-calculated_UCan then be fitted to equation (1) using a fitting equation. In some embodiments, the fitting formula may comprise a polynomial form.

Then, a first scattering kernel corresponding to the equivalent thickness may be retrieved from the plurality of first scattering kernels based on the equivalent thickness. For example, based on the equivalent thickness T, the first scattering kernel of the PMMA phantom at the equivalent thickness T is called (the ratio distribution of the number of scattered rays generated after the radiation source irradiates the PMMA phantom of T thickness to the number of rays directly penetrating the equivalent phantom). In some embodiments, the iterative updating is performed based on the equivalent thickness, and the corresponding first scattering kernel is iteratively updated in the iterative process.

And finally, convolving the first tissue region de-scattering image with the corresponding first scattering kernel to obtain a first scattering contribution. As shown in formula (2):

where S is the estimated first scatter contribution, P represents the tissue region backscatter image, and PSF represents the scatter kernel.

In some embodiments, determining a second scatter contribution of the tissue-free region to the breast image based on the tissue-free region and the second scatter kernel comprises: the first disorganized area backscatter image is convolved with a corresponding second scatter kernel to obtain a second scatter contribution. In particular, the amount of the solvent to be used,

first, the compression thickness of the mechanical feedback is obtained.

Then, a second scattering kernel corresponding to the compression thickness may be retrieved from the plurality of second scattering kernels based on the compression thickness. In some embodiments, the corresponding second scattering kernel is not updated in an iterative process.

And finally, convolving the first tissue free area de-scattering image with the corresponding second scattering kernel to obtain a second scattering contribution. As shown in formula (3):

where S is the estimated second scatter contribution, P represents the first tissue free region backscatter image, and PSF represents the second scatter kernel.

In some further embodiments, determining a second scatter contribution of the tissue-free region to the breast image based on the tissue-free region and the second scatter kernel further comprises: and convolving the first tissue-free region de-scattering image with the corresponding second scattering kernel to obtain a second scattering contribution. In particular, the amount of the solvent to be used,

first, based on a priori data (e.g., initial image without compression plate and without tissue) and the first tissue-free region backscatter image, the equivalent thickness of the phantom with similar properties (e.g., energy absorption coefficient for radiation, etc.) of the combination of the compression plate and the air layer, which may be the air layer between the compression plate and the detector (i.e., the air layer at a certain compression thickness), is estimated, as shown in formula (4):

T＝log(I/P)/M_U (4)

wherein T represents equivalent thickness, I represents a pre-stored initial image without compression plate and without tissue, P represents a de-scattering image of the non-tissue region, and M_UIs the linear attenuation coefficient of the phantom. In some embodiments, T M of the same phantom of different thicknesses may also be pre-calculated_UAnd then fitting equation (4) using the fitting formula. In some embodiments, the fitting formula may comprise a polynomial form.

Then, a second scattering kernel corresponding to the equivalent thickness may be retrieved from the plurality of second scattering kernels based on the equivalent thickness. For example, based on the equivalent thickness T, a second scatter kernel of the phantom at the equivalent thickness T is invoked (the ratio distribution of the number of scattered rays generated after the radiation source irradiates the T-thickness phantom to the number of rays that directly penetrate the compression paddle and the phantom). In some embodiments, the corresponding second scattering kernel is iteratively updated during an iterative process based on the equivalent thickness.

And finally, convolving the first tissue free area de-scattering image with the corresponding second scattering kernel to obtain a second scattering contribution. As shown in formula (3).

In 510, the backscatter module 430 may determine a backscatter breast image from the breast image, the first scatter contribution, and the second scatter contribution. For example, the first and second scatter contributions obtained in step 508 are removed from the breast image.

At 512, the backscatter module 430 may determine whether the backscatter breast image obtained in step 510 satisfies a termination condition. In some embodiments, the termination condition may be that the image similarity of two adjacent de-scattered breast images is within a threshold. In some embodiments, the image similarity of two adjacent scattered breast images can be calculated by using algorithms such as perceptual hash algorithm, scale invariant feature transform matching algorithm, and the like. In some embodiments, the threshold may include a similarity threshold between pixel points of two adjacent images, a distance threshold between image centroids, a distance threshold between image feature vectors, and the like.

If the termination condition is not satisfied, the process returns to step 508. The estimate is made using the de-scattered breast image that does not satisfy the termination condition in step 510 to update the de-scattered breast image. Specifically, the method comprises the following steps:

in some embodiments, determining a first scatter contribution of the organized region to the breast image based on the organized region and the first scatter kernel comprises: and convolving the tissue region de-scattered mammary image which does not meet the termination condition with the corresponding first scattering kernel to obtain a first scattering contribution. In particular, the amount of the solvent to be used,

first, based on prior data (e.g., initial image without compression plate and without tissue) and a de-scattered breast image of a tissue region that does not satisfy termination conditions, the equivalent thickness of a phantom (e.g., PMMA phantom) that is similar to the measured breast properties (e.g., material, energy absorption coefficient for radiation, etc.) is estimated, as in equation (1).

Then, the first scattering kernel corresponding to the equivalent thickness may be recalled from the plurality of first scattering kernels based on the equivalent thickness. For example, based on the equivalent thickness T, the first scattering kernel of the PMMA phantom at the equivalent thickness T is recalled (the ratio distribution of the number of scattered rays generated after the radiation source irradiates the PMMA phantom of T thickness to the number of rays that directly penetrate the equivalent phantom).

And finally, convolving the scattered mammary gland image of the organized area which does not meet the termination condition with the corresponding first scattering kernel to obtain a first scattering contribution. As shown in formula (2).

In some embodiments, determining a second scatter contribution of the tissue-free region to the breast image based on the tissue-free region and the second scatter kernel comprises: and convolving the non-tissue region de-scattering mammary gland image which does not meet the termination condition with the corresponding second scattering kernel to obtain a second scattering contribution. In particular, the amount of the solvent to be used,

first, the second scattering kernel, which is not updated in an iterative process as described above, is used based on the compression thickness of the mechanical feedback.

And finally, convolving the non-tissue area which does not meet the termination condition with the corresponding second scattering kernel to obtain a second scattering contribution. As shown in formula (3).

In some further embodiments, determining a second scatter contribution of the tissue-free region to the breast image based on the tissue-free region and the second scatter kernel further comprises: and convolving the non-tissue area which does not meet the termination condition with the corresponding second scattering kernel to obtain a second scattering contribution. In particular, the amount of the solvent to be used,

first, based on a priori data (e.g., initial image without compression plate and without tissue) and an unstructured region not satisfying the termination condition, an equivalent thickness of the phantom close to the properties of the combination of the compression plate and an air layer (e.g., energy absorption coefficient for radiation, etc.) is estimated, wherein the air layer may refer to an air layer between the compression plate and the detector (i.e., an air layer at a certain compression thickness), as in equation (4).

Then, a second scattering kernel corresponding to the equivalent thickness may be recalled from the plurality of second scattering kernels based on the equivalent thickness. For example, based on the equivalent thickness T, a second scattering kernel of the phantom at the equivalent thickness T is invoked (the ratio distribution of the number of scattered rays generated after the radiation source irradiates the T-thickness phantom to the number of rays that directly traverse the compression paddle and the phantom).

If the termination condition is satisfied, the iteration is ended.

In some embodiments, a three-dimensional breast image may be reconstructed based on a plurality of the de-scattered breast images.

It should be noted that the above description of flow 500 and the description thereof are provided for illustrative purposes only and are not intended to limit the scope of the present application. Various modifications and changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application.

Various modifications to the disclosed embodiments will be apparent to those skilled in the art. The present application is not limited to the described embodiments but should be accorded the widest scope consistent with the claims without departing from the principle and scope of the application.

The image descattering processing method and system disclosed in the present application may bring benefits including but not limited to: (1) the influence of scattering lines generated by a part of compression plates and an air layer in the non-tissue area on the whole mammary gland image is removed, so that the image quality can be improved; (2) and calling a corresponding scattering kernel by using the compression thickness fed back by the machine, and quickly estimating scattered rays generated by a part of the compression plate and the air layer in the non-tissue area by a convolution method.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered as illustrative only and not limiting of the application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific language to describe embodiments of the application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means a feature, structure, or characteristic described in connection with at least one embodiment of the application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics may be combined as suitable in one or more embodiments of the application.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, and the like, or any suitable combination. A computer storage medium may include any computer-readable medium except computer-readable storage media, which can be used to communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visualbasic, Fortran2003, Perl, COBOL2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While certain presently contemplated useful embodiments have been discussed in the foregoing disclosure by way of examples, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of the disclosure.

Similarly, it should be noted that in the foregoing description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single disclosed embodiment.

Claims

1. A method for processing the backscatter of a mammary image is characterized by comprising the following steps:

collecting a mammary gland image under a certain compression thickness;

segmenting a tissue area and an unorganized area from the mammary gland image;

based on the mammary gland image, a plurality of first scattering kernels and a plurality of second scattering kernels, performing scattering iteration processing on an organized region of the mammary gland image by using the first scattering kernels, and performing scattering iteration processing on an unorganized region of the mammary gland image by using the second scattering kernels to estimate a first scattering contribution of the organized region to the scattering image and a second scattering contribution of the unorganized region to the scattering image, so as to obtain a scattering mammary gland image, wherein the second scattering kernels are related to scattering characteristics of an equivalent phantom with a certain thickness and with similar properties of a combination of a compression plate and an air layer.

2. The method of claim 1, wherein the first scattering kernel is associated with scattering properties of an equivalent phantom of a thickness similar to the properties of the compressed breast, and wherein the first scattering kernel is iteratively updated in an iterative process.

3. The breast image backscatter processing method of claim 1, wherein the second scatter kernel is associated with a compression paddle at the compression thickness, the second scatter kernel being determined from the plurality of second scatter kernels based on the compression thickness.

4. The method for processing mammary image backscatter according to claim 1, wherein the second scattering kernel is updated iteratively during an iterative process, and the layer of air is an air layer between the compression plate and the detector.

5. The method for processing breast image backscatter according to claim 1, wherein the estimating a first scatter contribution of the organized region to a scatter image and a second scatter contribution of the unorganized region to a scatter image, and obtaining the backscatter breast image comprises:

initializing, and taking the segmented mammary gland image as an initial de-scattering mammary gland image;

iteratively:

determining the first scatter contribution of the organized region to the breast image based on the organized region and the first scatter kernel and the second scatter contribution of the unorganized region to the breast image from the unorganized region and the second scatter kernel;

determining the de-scattered breast image from the breast image, the first scatter contribution and the second scatter contribution;

6. The breast image backscatter processing method of claim 2 or 5, wherein the determining the first scatter contribution to the breast image from the organized region and the first scatter kernel comprises:

estimating the thickness of the equivalent phantom based on an initial image without a compression plate and a mammary gland and the tissue region de-scattering image;

retrieving a corresponding first scattering kernel from the plurality of first scattering kernels based on the thickness of the equivalent phantom;

convolving the de-scattered image of the organized region with the corresponding first scattering kernel to obtain the first scattering contribution of the organized region to the breast image.

7. The breast image backscatter processing method of claim 3 or 5, wherein the determining the second scatter contribution to the breast image from the tissue-free region and the second scatter kernel comprises:

calling a corresponding second scattering kernel from the plurality of second scattering kernels based on the certain compression thickness;

convolving the non-tissue region with the corresponding second scattering kernel to obtain the second scattering contribution of the non-tissue region to the breast image.

8. The breast image backscatter processing method of claim 4 or 5, wherein the determining the second scatter contribution to the breast image from the tissue-free region and the second scatter kernel further comprises:

estimating the thickness of the equivalent phantom based on an initial image without a compression plate and a mammary gland and the tissue-free region de-scattering image;

calling a corresponding second scattering kernel from the plurality of second scattering kernels based on the thickness of the equivalent phantom;

9. The method for processing mammary image de-scattering of claim 1, wherein a three-dimensional mammary image is reconstructed based on a plurality of the de-scattered mammary images.

10. A breast image backscatter processing system, the system comprising an image acquisition module, an image segmentation module, and a backscatter module:

the image acquisition module is used for acquiring a mammary gland image under a certain compression thickness;

the image segmentation module is used for segmenting a tissue area and an unorganized area from the mammary gland image; and

the de-scattering module is used for performing de-scattering iterative processing on the organized area of the mammary gland image by using the first scattering kernel and performing de-scattering iterative processing on the unorganized area of the mammary gland image by using the second scattering kernel based on the mammary gland image, the plurality of first scattering kernels and the plurality of second scattering kernels so as to estimate a first scattering contribution of the organized area to the scattering image and a second scattering contribution of the unorganized area to the scattering image and obtain a de-scattering mammary gland image, wherein the second scattering kernel is related to the scattering characteristics of an equivalent phantom with a certain thickness and similar to the composition property of a compression plate and an air layer.

11. An image backscatter processing apparatus, the apparatus comprising at least one processor and at least one storage medium:

the at least one storage medium is configured to store computer instructions;

the at least one processor is configured to execute the computer instructions to implement the method of backscatter processing for a breast image according to any one of claims 1 to 8.

12. A non-transitory computer-readable storage medium storing at least one set of computer instructions which, when executed, implement the method of breast image backscatter processing of any one of claims 1 to 8.