A medical image processing method, system, device and storage medium

Abstract

Embodiments of the present specification provide a medical image processing method, system, device and storage medium, the method comprising: acquiring a medical image; segmenting a target structure set in the medical image to obtain a fat-free mask; determining a first intersection of a target organ mask and the fat-free mask within a preset range, adjusting the regions of the target organ mask and the fat-free mask based on the first intersection; performing connected domain processing on the adjusted fat-free mask; and obtaining a processed fat-free mask based on the fat-free mask subjected to the connected domain processing.

Description

Technical Field

[0001] This specification relates to the field of image processing technology, and in particular to a medical image processing method, system, device, and storage medium. Background Technology

[0002] In image-guided interventional surgical workflows, puncture paths need to be planned in advance to avoid dangerous areas in the chest and abdomen, such as vital organs, blood vessels, and bones, thus ensuring the safety of the interventional procedure. Previous techniques typically involved segmenting the organs and tissues within the thoracic or abdominal cavity and planning the puncture path based on the segmentation results. While this method can achieve relatively complete and accurate puncture path planning, it is also time-consuming, resulting in low segmentation efficiency and hindering puncture planning and clinical application. Alternatively, a method might be used that only segments the target organ and non-puncture areas in the thoracic or abdominal cavity. While this method improves segmentation efficiency, when fusing the segmentation results of the non-puncture area with those of the target organ, a mask of the non-puncture area may adhere to the surface of the target organ mask, severely affecting puncture path planning. Therefore, providing a more complete, efficient image processing workflow with better fusion of segmentation results is crucial. Summary of the Invention

[0003] One embodiment of this specification provides a medical image processing method, comprising: acquiring a medical image; segmenting a set of target structures in the medical image to obtain a de-lipiding mask; determining a first intersection between a target organ mask and the de-lipiding mask within a preset range; adjusting the regions of the target organ mask and the de-lipiding mask based on the first intersection; performing connected component processing on the adjusted de-lipiding mask; and obtaining a processed de-lipiding mask based on the processed de-lipiding mask.

[0004] One embodiment of this specification provides a medical image processing system, comprising: an acquisition module for acquiring medical images; a segmentation module for segmenting a set of target structures in the medical images to obtain a de-lipiding mask; a first modification module for determining a first intersection between a target organ mask and the de-lipiding mask within a preset range, and adjusting the regions of the target organ mask and the de-lipiding mask based on the first intersection; a connected component processing module for performing connected component processing on the adjusted de-lipiding mask; and a second modification module for obtaining a processed de-lipiding mask based on the de-lipiding mask after connected component processing.

[0005] One embodiment of this specification provides a medical image processing apparatus, including a processor, which is used to execute the medical image processing method described in any embodiment of this specification.

[0006] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the medical image processing method described in any embodiment of this specification. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 These are schematic diagrams illustrating application scenarios of a medical image processing system according to some embodiments of this specification;

[0009] Figure 2 This is an exemplary flowchart of a medical image processing method according to some embodiments of this specification;

[0010] Figure 3A This is an exemplary flowchart of a mask fusion algorithm according to some embodiments of this specification;

[0011] Figure 3B This is an exemplary flowchart illustrating the determination of a first intersection and the adjustment of the element mask based on the first intersection, according to some embodiments of this specification;

[0012] Figure 4 This is an exemplary flowchart illustrating connected component processing of a degreasing mask according to some embodiments of this specification;

[0013] Figure 5 This is an exemplary flowchart illustrating the process of obtaining a processed degreasing mask based on a degreasing mask processed by connected components, according to some embodiments of this specification.

[0014] Figure 6 These are exemplary comparison diagrams showing the effects of fusing a delipidated mask with a target organ mask according to some embodiments of this specification;

[0015] Figure 7 This is an exemplary flowchart illustrating the combination of precise segmentation and rapid segmentation according to some embodiments of this specification;

[0016] Figure 8 This is an exemplary comparison diagram showing the effect of fusing a target organ mask with a fast segmentation result mask according to some embodiments of this specification;

[0017] Figure 9 This is an exemplary structural block diagram of a medical image processing system according to some embodiments of this specification. Detailed Implementation

[0018] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0019] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0020] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0021] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0022] Figure 1 This is a schematic diagram illustrating the application scenarios of a medical image processing system according to some embodiments of this specification.

[0023] In some embodiments, the medical image processing system 100 can be used to segment a set of target structures in a medical image, such as target organs, blood vessels, fat, thoracic region, and abdominal region within the target organ. In some embodiments, the medical image processing system 100 can also be used to perform fusion processing on the segmentation results of the set of target structures in the medical image, for example, fusing a target organ mask with a defatting mask (and / or a thoracic and abdominal mask).

[0024] Medical image processing system 100 may include medical scanning equipment 110, network 120, one or more terminals 130, processing equipment 140, and storage device 150. The connections between the components in medical image processing system 100 can be variable. For example... Figure 1As shown, medical scanning device 110 can be connected to processing device 140 via network 120. Alternatively, medical scanning device 110 can be directly connected to processing device 140, as indicated by the dashed double-headed arrow connecting medical scanning device 110 and processing device 140. As another example, storage device 150 can be connected to processing device 140 directly or via network 120. As an example, terminal 130 can be directly connected to processing device 140 (as indicated by the dashed arrow connecting terminal 130 and processing device 140) or connected to processing device 140 via network 120.

[0025] Medical scanning device 110 can be configured to scan a subject using high-energy rays (such as X-rays, gamma rays, etc.) to collect scan data related to the subject. The scan data can be used to generate one or more images of the subject. In some embodiments, medical scanning device 110 may include an ultrasound imaging (US) device, a computed tomography (CT) scanner, a digital radiography (DR) scanner (e.g., moving digital radiography), a digital subtraction angiography (DSA) scanner, a dynamic spatial reconstruction (DSR) scanner, an X-ray microscopy scanner, a multimodal scanner, etc., or combinations thereof. In some embodiments, a multimodal scanner may include a computed tomography-positron emission tomography (CT-PET) scanner, a computed tomography-magnetic resonance imaging (CT-MRI) scanner, etc. The subject can be biological or non-biological. By way of example only, the subject may include a patient, an artificial object (e.g., a phantom), etc. As another example, the subject may include a specific site, organ, and / or tissue of a patient.

[0026] like Figure 1 As shown, the medical scanning device 110 may include a rack 111, a detector 112, a detection area 113, a worktable 114, and a radiation source 115. The rack 111 can support the detector 112 and the radiation source 115. A scanned object can be placed on the worktable 114 for scanning. The radiation source 115 can emit radiation towards the scanned object. The detector 112 can detect the radiation emitted from the radiation source 115 (e.g., X-rays). In some embodiments, the detector 112 may include one or more detector units. Detector units may include scintillation detectors (e.g., cesium iodide detectors), gas detectors, etc. Detector units may include single-row detectors and / or multi-row detectors.

[0027] Network 120 may include any suitable network that can facilitate the exchange of information and / or data between the medical image processing system 100. In some embodiments, components of one or more medical image processing systems 100 (e.g., medical scanning device 110, terminal 130, processing device 140, storage device 150) may exchange information and / or data with each other via network 120. For example, processing device 140 may obtain image data from medical scanning device 110 via network 120. As another example, processing device 140 may obtain user instructions from terminal 130 via network 120.

[0028] Network 120 may be and / or include public networks (e.g., the Internet), private networks (e.g., local area networks (LANs), wide area networks (WANs), etc.), wired networks (e.g., Ethernet networks, wireless networks (e.g., 802.11 networks, Wi-Fi networks, etc.), cellular networks (e.g., LTE networks), Frame Relay networks, virtual private networks (“VPNs”), satellite networks, telephone networks, routers, hubs, switches, server computers, and / or any combination thereof. By way of example only, network 120 may include cable networks, wired networks, fiber optic networks, telecommunications networks, intranets, wireless local area networks (WLANs), metropolitan area networks (MANs), public switched telephone networks (PSTNs), Bluetooth, etc. TM Network, ZigBee TM A network, a near field communication (NFC) network, or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired and / or wireless network access points such as base stations and / or internet exchange points, through which one or more components of the medical image processing system 100 may connect to network 120 to exchange data and / or information.

[0029] Terminal 130 may include mobile device 131, tablet computer 132, laptop computer 133, etc., or any combination thereof. In some embodiments, mobile device 131 may include smart home devices, wearable devices, mobile devices, virtual reality devices, augmented reality devices, etc., or any combination thereof. In some embodiments, smart home devices may include smart lighting devices, smart electrical device control devices, smart monitoring devices, smart TVs, smart cameras, walkie-talkies, etc., or any combination thereof. In some embodiments, mobile devices may include mobile phones, personal digital assistants (PDAs), gaming devices, navigation devices, point-of-sale (POS) devices, laptops, tablets, desktop computers, etc., or any combination thereof. In some embodiments, virtual reality devices and / or augmented reality devices include virtual reality headsets, virtual reality glasses, virtual reality goggles, augmented reality headsets, augmented reality glasses, augmented reality goggles, etc., or any combination thereof. For example, virtual reality devices and / or augmented reality devices may include Google Glass. TM Oculus Rift TM HoloLens TM Gear VR TM In some embodiments, terminal 130 may be part of processing device 140.

[0030] Processing device 140 can process data and / or information obtained from medical scanning device 110, terminal 130, and / or storage device 150. For example, processing device 140 can acquire data acquired by medical scanning device 110, use this data to generate medical images, and segment the medical images. As another example, processing device 140 can acquire medical images and / or scanning protocols from terminal 130.

[0031] In some embodiments, processing device 140 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processing device 140 may be local or remote. For example, processing device 140 may access information and / or data stored in medical scanning device 110, terminal 130, and / or storage device 150 via network 120. As another example, processing device 140 may be directly connected to medical scanning device 110, terminal 130, and / or storage device 150 to access stored information and / or data. In some embodiments, processing device 140 may be implemented on a cloud platform. By way of example only, a cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, etc., or any combination thereof.

[0032] Storage device 150 can store data, instructions, and / or any other information. In some embodiments, storage device 150 can store data obtained from medical scanning device 110, terminal 130, and / or processing device 140. For example, storage device 150 can store medical image data and / or positioning information data obtained from medical scanning device 110. As another example, storage device 150 can store medical images and / or scanning protocols input from terminal 130. As yet another example, storage device 150 can store data generated by processing device 140 (e.g., medical image data, element mask data, segmentation result data, etc.).

[0033] In some embodiments, storage device 150 may store data and / or instructions that are executed by or used by processing device 140 to perform the exemplary methods described herein. In some embodiments, storage device 150 includes mass storage devices, removable storage devices, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage devices may include disks, optical disks, solid-state drives, etc. Exemplary removable storage devices may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tapes, etc. Exemplary volatile read-write memory may include random access memory (RAM). Exemplary RAM may include dynamic random access memory (DRAM), double data rate synchronous dynamic access memory (DDR SDRAM), static random access memory (SRAM), thyristor random access memory (T-RAM), and zero capacitance random access memory (Z-RAM), etc. Exemplary ROM may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), optical disc read-only memory (CD-ROM), and digital multifunction disk reallocation memory, etc. In some embodiments, the storage device 150 may be implemented on a cloud platform.

[0034] In some embodiments, storage device 150 may be connected to network 120 to communicate with one or more other components of medical image processing system 100 (e.g., processing device 140, terminal 130). One or more components of medical image processing system 100 may access data or instructions stored in storage device 150 via network 120. In some embodiments, storage device 150 may be directly connected to or communicate with one or more other components of medical image processing system 100 (e.g., processing device 140, terminal 130). In some embodiments, storage device 150 may be part of processing device 140.

[0035] The description of the medical image processing system 100 is intended to be illustrative and not to limit the scope of this specification. Many alternatives, modifications, and variations will be apparent to those skilled in the art. It will be understood that those skilled in the art, upon understanding the principles of the system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. In some embodiments, Figure 9 The acquisition module 410, segmentation module 420, first modification module 430, connected component processing module 440, and second modification module 450 can be different modules in a system, or a single module can implement the functions of two or more of the above modules. For example, the modules can share a storage module, or each module can have its own storage module. The features, structures, methods, and other features of the exemplary embodiments described in this specification can be combined in various ways to obtain other and / or alternative exemplary embodiments. For example, the processing device 140 and the medical scanning device 110 can be integrated into a single device. Such variations are all within the scope of protection of this specification.

[0036] Figure 2 This is an exemplary flowchart of a medical image processing method according to some embodiments of this specification. Figure 2 As shown, process 200 may include:

[0037] Step 210: Acquire medical images. In some embodiments, step 210 may be performed by the acquisition module 410 or the medical scanning device 110.

[0038] Medical images refer to medical images generated based on various imaging mechanisms. In some embodiments, medical images can be three-dimensional medical images. In some embodiments, medical images can also be two-dimensional medical images. In some embodiments, medical images can include CT images, PET-CT images, US images, or MR images.

[0039] In some embodiments, medical images of the scanned object can be acquired. In some embodiments, medical images of the scanned object, such as CT images, can be acquired from a medical scanning device 110. In some embodiments, medical images of the scanned object, such as MR images, can be acquired from a terminal 130, a processing device 140, and a storage device 150.

[0040] In some embodiments, the scanned object may include a biological scanned object or a non-biological scanned object. In some embodiments, a biological scanned object may include a patient, a specific site of the patient, an organ, and / or tissue, such as the abdomen, chest, or tumor tissue. In some embodiments, a non-biological scanned object may include an artificial object, such as a phantom.

[0041] It should be noted that in other embodiments, medical images can also be acquired by any other feasible means. For example, medical images can be acquired from a cloud server and / or a medical system (such as a hospital's medical system center) via network 120. The embodiments in this specification do not impose any particular limitation.

[0042] Step 220 involves segmenting the target structure set in the medical image to obtain a delipidated mask. In some embodiments, step 220 may be performed by the segmentation module 420.

[0043] The target structure set can be a region, organ, and / or tissue to be segmented in a medical image. In some embodiments, the target structure set may include multiple elements, such as one or more of the following: target organ, blood vessels within the target organ, fat, thoracic / abdominal cavity, etc. In some embodiments, the target organ may include the lung, liver, spleen, kidney, or any other possible organ tissue, such as the thyroid gland.

[0044] In some embodiments, segmenting the target structure set in a medical image can yield element masks corresponding to each element in the target structure set. In some embodiments, segmenting the target structure set in a medical image can yield one or more of the following: target organ mask, blood vessel mask within the target organ, fat mask, thoracic / abdominal cavity mask, etc. In some embodiments, the thoracic / abdominal cavity can be collectively referred to as the thoracic-abdominal region, and the corresponding thoracic / abdominal cavity mask is called the thoracic-abdominal mask.

[0045] Element masks can be pixel-level classification labels. Taking abdominal medical images as an example, element masks represent the classification of each pixel in the medical image. For example, they can be divided into background, liver, spleen, kidney, etc. The summary area of ​​a specific category is represented by the corresponding label value. For example, all pixels classified as liver are summarized, and the summary area is represented by the label value corresponding to liver. The label value here can be set according to the specific segmentation task.

[0046] In some embodiments, after acquiring the medical image via step 210, the medical image can be preprocessed, and each element in the target structure set in the preprocessed image can be segmented to obtain an element mask. In some embodiments, preprocessing may include image preprocessing operations. In some embodiments, image preprocessing operations may include normalization processing and / or background removal processing.

[0047] In some embodiments, image segmentation methods may include threshold segmentation, region growing, or level set methods. In some embodiments, segmentation based on the threshold segmentation method can be implemented as follows: by setting multiple different pixel threshold ranges, pixels in the medical image are classified according to the pixel values ​​of the input medical image, and pixels with pixel values ​​within the same threshold range are segmented into the same region. In some embodiments, segmentation based on the region growing method can be implemented as follows: based on known pixels or predetermined regions composed of pixels in the medical image, a similarity discrimination condition is preset according to requirements, and based on the preset similarity discrimination condition, pixels are compared with their surrounding pixels, or predetermined regions are compared with their surrounding regions, merging pixels or regions with high similarity until the above process cannot be repeated, at which point merging stops, completing the segmentation process. In some embodiments, the preset similarity discrimination condition can be determined based on preset image features, exemplarily, such as grayscale, texture, or other image features. In some embodiments, segmentation based on the level set method can be implemented as follows: the target contour of the medical image is set as the zero level set of a high-dimensional function, the function is differentiated, the zero level set is extracted from the output to obtain the target contour, and then the pixel region within the contour range is segmented.

[0048] In some embodiments, a method based on deep learning convolutional networks can be used to segment a set of target structures in medical images. In some embodiments, the deep learning convolutional network-based method may include segmentation methods based on fully convolutional networks, such as UNet. In some embodiments, segmentation based on deep learning convolutional networks can be implemented as follows: the encoder of the convolutional neural network extracts features from the medical image through convolution; then, the decoder of the convolutional neural network restores the features into a pixel-level segmentation probability map, which represents the probability that each pixel in the image belongs to a specific category; finally, the segmentation probability map is output as a segmentation mask, thereby completing the segmentation.

[0049] In some embodiments, after segmenting the target structure set in the medical image to obtain a fat mask and a thoracic / abdominal mask, a de-liposuction mask can be further obtained based on the fat mask and the thoracic / abdominal mask. In some embodiments, the thoracic / abdominal mask can be subtracted from the fat mask, i.e., the fat mask is removed from the thoracic / abdominal mask, thereby obtaining a de-liposuction mask for the thoracic / abdominal region. In some embodiments, since the target organ is located within the thoracic / abdominal region, the target organ mask will also be located within the thoracic / abdominal mask region, and the area of ​​the de-liposuction mask obtained based on the thoracic / abdominal mask and the fat mask may include the target organ mask. In some embodiments, the area of ​​the de-liposuction mask obtained based on the thoracic / abdominal mask and the fat mask may also exclude the target organ mask. For example, the thoracic / abdominal mask can be subtracted from the target organ mask (i.e., the target organ mask is removed from the thoracic / abdominal mask) to obtain a thoracic / abdominal target-removed mask, and then the de-liposuction mask can be obtained based on the thoracic / abdominal target-removed mask and the fat mask. In interventional surgery, the fat region in the thoracic / abdominal region can be considered an interventional region; the de-liposuction mask region is a non-interventional region. Non-invasive regions refer to areas that the interventional path of an interventional procedure must avoid, such as areas that cannot be penetrated. In some embodiments, non-invasive regions may include, but are not limited to, organs, blood vessels, and bones. In some embodiments, the process of segmenting a set of target structures in a medical image to obtain a delipidation mask can be a rapid segmentation process.

[0050] In some embodiments, the degreasing mask and the target organ mask can be fused to obtain a processed degreasing mask. In some embodiments, morphological erosion and dilation operations can be used to fuse the degreasing mask and the target organ mask. In some embodiments, the erosion and dilation operations can be implemented based on convolution processing of the medical image and a filter. In some embodiments, the erosion operation can be performed by convolving the filter with the medical image and then finding a local minimum based on a predetermined erosion range, thereby reducing the outline of the medical image to a desired range and shrinking the target highlight area by a certain range in the initial image of the medical image display. In some embodiments, the dilation operation can be performed by convolving the filter with the medical image and then finding a local maximum based on a predetermined erosion range, thereby expanding the outline of the medical image to a desired range and shrinking the target highlight area by a certain range in the initial image of the medical image display.

[0051] In some embodiments, when fusing the delipidation mask and the target organ mask, to ensure that the delipidation mask does not deform, reduce false positive areas, avoid over-segmentation of the target organ mask, and prevent the delipidation mask from adhering to the surface of the target organ mask, a mask fusion algorithm can be used to fuse the delipidation mask and the target organ mask, thereby obtaining a processed delipidation mask. See details below. Figures 3A-6 , and its related descriptions.

[0052] Figure 3A This is an exemplary flowchart of a mask fusion algorithm according to some embodiments of this specification. Figure 3AThe mask fusion algorithm shown can be implemented according to the methods described in steps 230, 240 and 250.

[0053] Step 230: Determine the first intersection of the target organ mask and the degreasing mask within a preset range, and adjust the regions of the target organ mask and the degreasing mask based on the first intersection. In some embodiments, step 230 may be performed by the first modification module 430.

[0054] The preset range can be the detection range of an element mask (e.g., a target organ mask, a deliposuction mask). In some embodiments, the preset range can include the edge range of the target organ mask. The edge range of the target organ mask can be the mask region that meets the boundary of the target organ mask. For example, if the target organ mask is located within the region of the deliposuction mask, the edge range of the target organ mask can be a portion of the deliposuction mask that meets the boundary of the target organ mask. Within the preset range, the regions of the target organ mask and the deliposuction mask can be adjusted. Adjustment of the mask region can include expanding and shrinking the mask region. The first intersection refers to the mask value of the overlapping portion of the target organ mask and the deliposuction mask within the preset range. Figure 3B This is an exemplary flowchart illustrating the determination of a first intersection and the adjustment of an element mask based on the first intersection, according to some embodiments of this specification. In some embodiments, combined with Figure 3A and Figure 3B Step 230 may include the following sub-steps:

[0055] Sub-step 231 involves detecting the target organ mask.

[0056] Detecting a target organ mask can involve edge detection. For example, detecting the boundary of the target organ mask. The boundary of the target organ mask can include edge point information. In some embodiments, the edges of the target organ mask can be detected to determine the edge points (e.g., ...). Figure 3A (Edge detection is performed on the target organ mask). Specifically, pixels of the target organ mask can be detected. If a pixel within the target organ mask's region (e.g., a preset range) has a null value in any of the six directions in three-dimensional space, then that pixel can be determined as an edge point. This is because the target organ mask is a geometric mask composed of pixels with the same value; in the case of an edge, the adjacent regions of the edge pixel are null values.

[0057] Sub-step 232: Based on the detection results, determine the first intersection of the target organ mask and the degreasing mask within a first preset range, wherein the first preset range is determined according to the first preset parameter.

[0058] The first preset range can be a first detection range of an element mask (e.g., a target organ mask, a degreasing mask). Pixels within the first preset range of the target organ mask can be detected to determine whether they are edge points. In some embodiments, it can be determined whether a degreasing mask value exists at the edge point of the target organ mask within the first preset range; if so, the degreasing mask value is recorded. Similarly, all edge points of the target organ mask can be assessed, and all degreasing mask values ​​that meet the conditions can be recorded. Further, a first intersection between the edge point of the target organ mask and the degreasing mask within the first preset range is determined based on the recorded degreasing mask values. The first intersection can be the region formed by all recorded degreasing mask values ​​and the edge point of the target organ mask corresponding to each degreasing mask value. In some embodiments, the region of the first intersection can be understood as the degreasing mask being attached to the surface of the target organ mask. In some embodiments, determining the first intersection between the edge of the target organ mask and the degreasing mask within the first preset range can be... Figure 3A The image shows an "edge perimeter search" of the target organ mask and the degreasing mask.

[0059] In some embodiments, the first preset range can be determined based on a first preset parameter. In some embodiments, the adjustment range of the target organ mask based on the first intersection can be adjusted by adjusting the first preset parameter. For example, setting the first preset parameter to a small value (e.g., 3 pixels) can result in a smaller adjustment range for the target organ mask region. In some embodiments, the first preset parameter can be a constant value obtained through experimental observation. As an example only, the first preset parameter can be 3 to 4 pixels. In some embodiments, the first preset parameter can also be reasonably set based on machine learning and / or big data, without further limitation. In some embodiments, the value of the first preset parameter can also be adjusted based on patient information (e.g., gender, age, physical condition, etc.) and different organs of the same patient to adapt to clinical situations.

[0060] Sub-step 233: Based on the first intersection, the regions of the target organ mask and the delipidation mask are adjusted for the first time.

[0061] The first adjustment to the target organ mask region may be to expand the target organ mask region. The first adjustment to the delipidation mask region may be to shrink the delipidation mask region. In some embodiments, the regions of the target organ mask and the delipidation mask may be adjusted based on the edge of a first intersection. In some embodiments, the region of the target organ mask may be expanded based on the edge of a first intersection formed by all recorded delipidation mask values; and the region of the delipidation mask may be shrunk based on the edge of a first intersection formed by the edge points of the target organ mask corresponding to each recorded delipidation mask value. In some embodiments, the first adjustment to the regions of the target organ mask and the delipidation mask based on the first intersection may be localized. For example, only the edge regions of the target organ mask may be expanded, and the edge regions of the delipidation mask may be shrunk, while the main bodies of the target organ mask and the main body of the delipidation mask remain unchanged.

[0062] In some embodiments, by expanding the area of ​​the target organ mask and shrinking the area of ​​the deliposurgical mask, the connection between most false positive areas and the mask body (e.g., the deliposurgical mask body, the target organ mask body) can be broken, while the oversegmentation of the deliposurgical mask can be normalized.

[0063] Sub-step 234: Determine the second intersection of the first adjusted target organ mask and the first adjusted fat removal mask within a second preset range, wherein the second preset range is determined according to the second preset parameters.

[0064] The second preset range can be the second detection range of the element mask (e.g., target organ mask, delipidation mask). In some embodiments, it can be determined whether the edge points of the target organ mask after the first adjustment (e.g., expansion) exist within the second preset range as determined by the delipidation mask value after the first adjustment (e.g., contraction). If so, the delipidation mask value is recorded. Similarly, all edge points of the target organ mask after the first adjustment (e.g., expansion) are determined, and all delipidation mask values ​​that meet the conditions are recorded. Further, based on the recorded delipidation mask values, a second intersection between the target organ mask after the first adjustment and the delipidation mask after the first adjustment (e.g., contraction) within the second preset range is determined. The second intersection can be all recorded delipidation mask values ​​and the region formed by the edge points of the target organ mask after the first adjustment corresponding to each delipidation mask value.

[0065] In some embodiments, the second preset range can be determined based on a second preset parameter. In some embodiments, the adjustment magnitude of the fat removal mask based on the second intersection can be adjusted by adjusting the second preset parameter. For example, setting the second preset parameter to a smaller value (e.g., 1 pixel) can result in a smaller adjustment magnitude for the fat removal mask region. In some embodiments, the second preset parameter can be less than or equal to the first preset parameter. Correspondingly, the second preset range is less than or equal to the first preset range. In some embodiments, the second preset parameter can be a constant value obtained through experimental observation. As an example only, the second preset parameter can be 1-2 pixels. In some embodiments, the second preset parameter can also be reasonably set based on machine learning and / or big data, without further limitation. In some embodiments, the value of the second preset parameter can also be adjusted based on patient information (e.g., gender, age, physical condition, etc.) and different organs of the same patient to adapt to clinical situations.

[0066] Sub-step 235: Based on the second intersection, perform a second adjustment on the regions of the first adjusted target organ mask and the first adjusted fat removal mask.

[0067] A second adjustment to the region of the target organ mask after the first adjustment can be a second expansion of the region of the target organ mask after the first adjustment. A second adjustment to the region of the fat-reducing mask after the first adjustment can be a second contraction of the region of the fat-reducing mask after the first adjustment. In some embodiments, the regions of the target organ mask and the fat-reducing mask after the first adjustment can be adjusted a second time, with the edge of the second intersection formed by all recorded fat-reducing mask values ​​as the boundary. In some embodiments, the region of the expanded target organ mask can be expanded a second time, with the edge of the second intersection formed by the edge points of the expanded target organ mask corresponding to each recorded fat-reducing mask value as the boundary, and the contracted fat-reducing mask can be contracted a second time. In some embodiments, the second adjustment to the regions of the target organ mask and the fat-reducing mask after the first adjustment based on the second intersection can be global. For example, the target organ mask after the first expansion is expanded a second time, and the fat-reducing mask after the first contraction is contracted a second time. It is understood that a global adjustment of the element mask (e.g., the target organ mask, the fat-reducing mask) will change the main region of the element mask. In some embodiments, the operations described in sub-steps 234 and 235 can be considered as Figure 3A The "opening operation" in the process involves a second expansion of the target organ mask area after the first expansion, and a second contraction of the degreased mask after the first contraction. This can further disconnect the remaining false positive area in sub-step 233 from the mask body (e.g., the degreased mask body, the target organ mask body).

[0068] In some embodiments, the adjustment range of the mask region can affect other structures within the mask. For example, shrinking the deliposurgical mask region may affect blood vessels within the mask; if the shrinkage is too large, it may result in the absence of blood vessels in the shrunken mask. Therefore, the adjustment range of the target organ mask and the deliposurgical mask region can be controlled by reasonably setting the first and second preset parameters, thereby reducing the impact on other structures within the mask. As an example, the first preset parameter can be set to 3 pixels and the second preset parameter to 1 pixel. This setting ensures that the adjustment range of the target organ mask and the deliposurgical mask region is small, reducing the impact on other structures within the mask (e.g., blood vessels), while also disconnecting the false positive area from the mask body and reducing noise areas.

[0069] Step 240 involves performing connected component processing on the adjusted degreasing mask. In some embodiments, step 240 may be performed by the connected component processing module 440.

[0070] In some embodiments, after the regions of the target organ mask and the deliposurgical mask are adjusted for the first time and / or the second time (i.e., after the region of the target organ mask is expanded for the first time and / or the second time, and the region of the deliposurgical mask is contracted for the first time and / or the second time), the connection between the false positive region and the mask body (e.g., the deliposurgical mask body, the target organ mask body) is broken. However, this also results in more noisy regions between the deliposurgical mask and the target organ mask, which require further processing to remove the noisy regions.

[0071] In some embodiments, the connected regions surrounding the adjusted degreasing mask and the adjusted target organ mask can be evaluated. If a connected region is a valid connected region, it is retained; otherwise, it is discarded, thereby clearing the noise region. A connected region, or connected area, generally refers to an image region composed of foreground pixels with the same pixel value and adjacent positions. Figure 4 This is an exemplary flowchart illustrating connected component processing of a degreasing mask according to some embodiments of this specification. It is understood that... Figure 4 The fat-removal mask mentioned herein can refer to an adjusted fat-removal mask, such as a shrunken one, while the target organ mask refers to an adjusted target organ mask, such as an expanded one. In some embodiments, combined with Figure 3A and Figure 4 Step 240 may include the following sub-steps:

[0072] Sub-step 241: Determine whether the location information of the target organ mask overlaps with the location information of the pseudo-lipid-removed connected region;

[0073] Sub-step 242: When the judgment result is non-overlapping, the pseudo-de-liquid connected component is marked as belonging to the de-liquidation mask;

[0074] Sub-step 243: When the judgment result is overlap, determine whether the pseudo-de-liquid connected region should belong to the de-liquidation mask based on the relationship between the area of ​​the pseudo-de-liquid connected region and the preset area threshold.

[0075] Pseudo-fat-removal connected regions refer to connected regions within the periphery of the target organ mask (e.g., a predetermined range). In some embodiments, the fat-removal mask region may not be a single, interconnected connected region, but rather a region composed of multiple unconnected connected regions. Some of these unconnected connected regions may be distributed within the periphery of the target organ mask region; these connected regions can be referred to as pseudo-fat-removal connected regions.

[0076] Positioning information can include the bounding rectangle of the element mask (i.e. Figure 3A The bounding box (bounding box) contains location information. For example, the coordinates of the bounding rectangle's border lines. In some embodiments, the bounding rectangle of the element mask covers the element's positioning area. In some embodiments, the bounding rectangle may be displayed in the medical image as a bounding box. In three-dimensional space, the bounding rectangle outlines the element mask in the form of a bounding cube. In some embodiments, the bounding rectangle may be constructed based on the bottom edges of connected regions in the element at various locations, for example, the bottom edges of connected regions in six directions in three-dimensional space, relative to the element mask.

[0077] In some embodiments, the location information (e.g., bounding box) of each connected component in the pseudo-de-lipidation connected component can be used to determine whether the location information of the corresponding connected component (i.e., one connected component in the pseudo-de-lipidation connected component) overlaps with the location information of the target organ mask. In some embodiments, when the bounding box of the target organ mask does not overlap with the bounding box of the pseudo-de-lipidation connected component, the pseudo-de-lipidation connected component can be considered not a noise region. In this case, the pseudo-de-lipidation connected component can be identified as belonging to the de-lipidation mask. When the bounding box of the target organ mask overlaps with the bounding box of the pseudo-de-lipidation connected component, the pseudo-de-lipidation connected component can be considered a noise region. In this case, the relationship between the area of ​​the pseudo-de-lipidation connected component and a preset area threshold can be used to determine whether the pseudo-de-lipidation connected component should belong to the de-lipidation mask. It is understood that the area of ​​the pseudo-de-lipidation connected component refers to the area of ​​a single connected component. In some embodiments, when the area of ​​the pseudo-de-lipidation connected component is greater than the preset area threshold, the pseudo-de-lipidation connected component can be identified as belonging to the de-lipidation mask; when the area of ​​the pseudo-de-lipidation connected component is less than or equal to the preset area threshold, the pseudo-de-lipidation connected component can be identified as not belonging to the de-lipidation mask. In some embodiments, connected regions identified as not belonging to the deliposuction mask can be determined as false positive regions (i.e., noise regions). In some embodiments, the preset area threshold can be a constant value obtained through experimental observation. In some embodiments, when the medical image is a three-dimensional medical image, the preset area threshold can be in the range of 10,000 voxels to 1,000,000 voxels. As an example only, the preset area threshold can be 20,000 voxels, 50,000 voxels, 100,000 voxels, etc. In some embodiments, when the medical image is a two-dimensional medical image, the preset area threshold can be in the range of 100 pixels to 10,000 pixels. As an example only, the preset area threshold can be 300 pixels, 1,000 pixels, 5,000 pixels, etc. In some embodiments, the preset area threshold can be reasonably set according to the size of the target organ mask and / or the deliposuction mask. In some embodiments, the preset area threshold can also be reasonably set according to machine learning and / or big data, without further limitation.

[0078] In some embodiments, pseudo-de-lipidized connected regions can be processed based on the identification results. The identification results may include retention identifiers and / or discard identifiers. Retention identifiers may indicate pseudo-de-lipidized connected regions belonging to the de-lipidization mask. Pseudo-de-lipidized connected regions belonging to the de-lipidization mask can be retained. Discard identifiers may indicate pseudo-de-lipidized connected regions not belonging to the de-lipidization mask. Pseudo-de-lipidized connected regions not belonging to the de-lipidization mask can be discarded. In some embodiments, the identification results of pseudo-de-lipidized connected regions can also be manually adjusted. For example, a physician can adjust the identification of pseudo-de-lipidized connected regions based on clinical experience. As an example only, if a physician, based on clinical experience, determines that a pseudo-de-lipidized connected region identified as belonging to the de-lipidization mask is a false positive region, it can be manually adjusted to discard the pseudo-de-lipidized connected region.

[0079] In some embodiments, when the target organ mask overlaps with the pseudo-de-lipidation connected region and the area of ​​the overlapping region is very small, the pseudo-de-lipidation connected region can be discarded directly without considering the relationship between the area of ​​the pseudo-de-lipidation connected region and the preset area threshold.

[0080] It should be noted that, Figure 4 The target organ mask mentioned above refers to the expanded target organ mask, and correspondingly, the bounding box of the target organ mask refers to the bounding box of the expanded target organ mask.

[0081] By performing connected component processing on the fat removal mask, the main area of ​​the fat removal mask and the effective connected regions around the target organ mask (e.g., connected regions with an area greater than a preset area threshold) can be preserved, while noise regions (e.g., connected regions with an area less than or equal to a preset area threshold) can be removed, resulting in a preserved fat removal mask.

[0082] Step 250: Based on the degreasing mask processed by connected component processing, obtain the processed degreasing mask. In some embodiments, step 250 may be performed by the second modification module 450.

[0083] In some embodiments, after the fat removal mask has undergone steps 230 and 240, the connection between the fat removal mask and the target organ mask has been disconnected and the noise area has been cleared. However, what is obtained at this time is an adjusted (e.g., shrunken) fat removal mask. Therefore, in order to ensure that the main area of ​​the fat removal mask can be restored to its original shape, the fat removal mask area can be adjusted a third time to obtain the processed fat removal mask. Figure 5 This is an exemplary flowchart illustrating the process of obtaining a processed degreasing mask based on a degreasing mask that has undergone connected component processing, according to some embodiments of this specification. (Combined with...) Figure 3A and Figure 5 As shown, step 250 may include the following sub-steps:

[0084] Sub-step 251 involves detecting the edge of the adjusted target organ mask.

[0085] Sub-step 252: Based on the detection results, determine the adjacent boundaries between the delipidated mask and the target organ mask after connected component processing.

[0086] Sub-step 253: Based on the adjacent boundaries, the degreasing mask after connected component processing is adjusted for the third time to obtain the processed degreasing mask.

[0087] Figure 5The target organ mask described herein refers to the target organ mask after the first and / or second adjustment, simply referred to as the expanded target organ mask; the de-fat mask refers to the de-fat mask after the first and / or second adjustment, and connected component processing, simply referred to as the de-fat mask after connected component processing. In some embodiments, when detecting the expanded target organ mask, if a pixel within the expanded target organ mask range has a null value in any of the six directions in three-dimensional space, then the pixel can be determined as an edge point. Further descriptions of edge detection can be found above and will not be repeated here.

[0088] In some embodiments, the detection results may include edge point information of the expanded target organ mask. Adjacent boundaries may be the boundaries between the de-lipid mask processed by connected component analysis and the expanded target organ mask. In some embodiments, adjacent boundaries can be determined based on the detection results of the expanded target organ mask and the detection results of the initial target organ mask (the unadjusted target organ mask). In some embodiments, the difference between the detection results of the expanded target organ mask (e.g., edge point information) and the detection results of the initial target organ mask can be calculated to determine adjacent boundaries. A third adjustment to the de-lipid mask processed by connected component analysis based on adjacent boundaries yields a processed de-lipid mask (also known as a non-invasive region mask). In some embodiments, the third adjustment to the de-lipid mask processed by connected component analysis may be an expansion of the de-lipid mask processed by connected component analysis. The third adjustment process of the de-lipid mask processed by connected component analysis can also be called the de-lipid mask restoration process. Expanding the de-lipid mask processed by connected component analysis yields the processed de-lipid mask. The processed fat removal mask can be a fat removal mask with the same shape as the initial fat removal mask (the unadjusted fat removal mask), which is not connected to the initial target organ mask and has no noise areas.

[0089] The processed fat-removing mask is obtained by fusing the fat-removing mask and the target organ mask. Compared with morphological erosion and dilation operations, the processed fat-removing mask obtained by the mask fusion algorithm can ensure that the processed fat-removing mask is not deformed, reduce false positive areas, and avoid over-segmentation of the target organ mask, thus obtaining a more accurate processed fat-removing mask. In some embodiments, the processed fat-removing mask, the initial target organ mask, and the vascular mask within the target organ obtained by the mask fusion algorithm can be used as a fast segmentation result.

[0090] It should be noted that the mask fusion algorithm can also be used to fuse the thoracic and abdominal mask with the target organ mask. That is, the thoracic and abdominal mask is not degreased and is directly used to fuse with the target organ mask. The specific processing method of mask fusion is described above and will not be repeated here.

[0091] Figure 6 These are exemplary comparison diagrams illustrating the fusion of a delipidated mask and a target organ mask according to some embodiments of this specification. Figure 6 As shown, the top and bottom left images are cross-sectional and stereoscopic medical images without the mask fusion algorithm, while the top and bottom right images are cross-sectional and stereoscopic medical images with the mask fusion algorithm. The comparison reveals that fusing the fat-removing mask and the target organ mask using the mask fusion algorithm removes the false positive areas outlined in the box in the left image (compare the top left and top right images), while also preventing deformation of the fat-removing mask (compare the bottom left and bottom right images).

[0092] It should be noted that the above description of process 200 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to process 200 under the guidance of this specification; for example, step 230 can be split into two steps. However, these modifications and changes are still within the scope of this specification.

[0093] In some embodiments, to improve the accuracy of segmentation results in medical images, target organs in the medical images can be segmented to obtain target organ masks, and these target organ masks can be fused with the aforementioned fast segmentation result masks. In some embodiments, the process of segmenting target organs in medical images to obtain target organ masks can be referred to as a precise segmentation process. Figure 7 This is an exemplary flowchart illustrating the combination of precise and rapid segmentation according to some embodiments of this specification. Figure 7 As shown, process 300 may include:

[0094] Step 310: Obtain operation instructions. In some embodiments, step 310 may be performed by the acquisition module 410.

[0095] Operational instructions can include mode instructions and data instructions. Mode instructions can refer to the input indicating whether precise segmentation is required, i.e., whether the target organ in the medical image needs to be segmented. The target organ can be an important organ / tissue in the medical image, such as blood vessels or bones. In some embodiments, when the mode instruction indicates that precise segmentation is not required, the medical image processing system outputs a fast segmentation result. In some embodiments, when the mode instruction indicates that precise segmentation is required, the medical image processing system outputs a fusion result of the fast segmentation result and the precise segmentation result. In some embodiments, when the target organ in the medical image needs to be segmented, the organ to be segmented (i.e., the target organ) can be selected through data instructions.

[0096] Step 320: Segment at least one target organ in the medical image according to the operation instructions to obtain at least one target organ mask. In some embodiments, step 320 may be performed by the segmentation module 420.

[0097] In some embodiments, at least one target organ can be selected, and the segmentation module 420 segments the selected target organ to obtain a target organ mask. In some embodiments, the segmentation method for segmenting the target organ is the same as the image segmentation method for fast segmentation, for example, it may include a thresholding method, a region growing method, or a level set method, or it may utilize a method based on a deep learning convolutional network. For a more detailed description of the segmentation method, please refer to the segmentation methods involved in fast segmentation, which will not be repeated here.

[0098] Understandably, the main difference between rapid segmentation and precise segmentation lies in the different organs and / or tissues segmented and the resulting segmentation outcomes. Precise segmentation can segment all organs in a medical image, obtaining individual organ masks, resulting in more detailed and accurate image content. Rapid segmentation, on the other hand, only segments the non-invasive regions as a whole, obtaining non-invasive region masks, thus achieving higher segmentation efficiency. Therefore, combining rapid and precise segmentation can improve both efficiency and accuracy while maintaining sufficient segmentation efficiency.

[0099] Step 330 involves determining a third intersection between at least one target organ mask and a fast segmentation result mask within a first preset range, and adjusting the regions of the at least one target organ mask and the fast segmentation result mask based on the third intersection, wherein the fast segmentation result includes at least the processed de-lipidized mask. In some embodiments, step 330 may be performed by a first modification module 430.

[0100] In some embodiments, the method for determining the third intersection is similar to the method for determining the first intersection. For example, in some embodiments, a target organ mask may be detected; based on the detection results, a third intersection of the target organ mask and the fast segmentation result mask within a first preset range may be determined; and based on the third intersection, the regions of the target organ mask and the fast segmentation result mask may be adjusted for the first time. For example, the region of the target organ mask may be expanded and the region of the fast segmentation result mask may be contracted based on the third intersection. The first adjustment to the regions of the target organ mask and the fast segmentation result mask may be local. In some embodiments, similar to the first intersection, the third intersection may be the region consisting of all recorded fast segmentation result mask values ​​and the edge points of the target organ mask corresponding to each fast segmentation result mask value. For more details on the method for determining the third intersection, please refer to the foregoing description (e.g., Figure 2 (Step 220 and its related description).

[0101] After the target organ mask is expanded and the rapid segmentation result mask is contracted, the connection between the false positive region and the mask body (e.g., the rapid segmentation result mask body, the target organ mask body) can be broken.

[0102] Step 340: Perform connected component processing on the adjusted fast segmentation result mask. In some embodiments, step 340 may be performed by the connected component processing module 440.

[0103] In some embodiments, connected component processing is performed on the adjusted fast segmentation result mask. Figure 2 The method for processing the connected components of the adjusted fat removal mask described in step 240 is essentially the same. In some embodiments, processing the connected components of the adjusted fast segmentation result mask can be performed as follows: determining whether the location information of the target organ mask overlaps with the location information of the connected components of the pseudo-fast segmentation result; when the determination result is that they do not overlap, the connected components of the pseudo-fast segmentation result are identified as belonging to the fast segmentation result mask; when the determination result is that they overlap, determining whether the connected components of the pseudo-fast segmentation result should belong to the fast segmentation result mask is based on the relationship between the area of ​​the connected components of the pseudo-fast segmentation result and a preset area threshold. If the area of ​​the connected components of the pseudo-fast segmentation result is greater than the preset area threshold, the connected components of the pseudo-fast segmentation result are identified as belonging to the fast segmentation result mask and retained; when the area of ​​the connected components of the pseudo-fast segmentation result is less than or equal to the preset area threshold, the connected components of the pseudo-fast segmentation result are identified as false positive regions (i.e., noise regions) and discarded. In some embodiments, when the target organ mask overlaps with the connected regions of the pseudo-fast segmentation result, and the area of ​​the overlapping region is very small, the pseudo-fast segmentation result connected region can be discarded regardless of its area relative to a preset area threshold. The pseudo-fast segmentation result connected region refers to the connected region within the periphery of the target organ mask (e.g., a first preset range). In some embodiments, the fast segmentation result mask region may not be a single, interconnected connected region, but rather a region composed of multiple unconnected connected regions. Some of these unconnected connected regions may be distributed around the periphery of the target organ mask region; these connected regions can be referred to as pseudo-fast segmentation result connected regions.

[0104] By performing connected component processing on the fast segmentation result mask, the main region of the fast segmentation result mask and the effective connected components around the target organ mask (i.e., connected components with an area greater than a preset area threshold) can be preserved, while noise regions (i.e., connected components with an area less than or equal to a preset area threshold) can be removed.

[0105] Step 350: Based on the fast segmentation result mask after connected component processing, obtain the processed fast segmentation result mask. In some embodiments, step 350 may be performed by the second modification module 450.

[0106] The process of obtaining a processed fast segmentation result mask after connected component processing can be implemented as follows: Detect the expanded target organ mask; based on the detection results, determine the adjacent boundaries between the connected component processed fast segmentation result mask and the target organ mask; adjust the connected component processed fast segmentation result mask based on the adjacent boundaries to obtain the processed fast segmentation result mask. For example, the connected component processed fast segmentation result mask can be expanded (i.e., restored) so that it can be restored to its original shape.

[0107] It is understandable that the mask fusion method between the target organ mask and the fast segmentation result mask (i.e., the mask fusion method between the accurate segmentation result and the fast segmentation result) and... Figure 2 The mask fusion method between the target organ mask and the fat removal mask is largely the same. The difference lies in that when fusing the target organ mask with the fast segmentation result mask, the fast segmentation result mask only undergoes one contraction, omitting the "opening operation" process. This is because, during the fusion of the target organ mask and the fast segmentation result mask, changes to the fast segmentation result mask are not allowed, while the "opening operation" might cause changes. In some embodiments, to ensure that the fast segmentation result mask does not change, the first preset parameter can be set to 4 pixels during the determination of the third intersection. More information on mask fusion between the target organ mask and the fast segmentation result mask can be found in [reference needed]. Figure 2 The details and related descriptions will not be repeated here.

[0108] Figure 8 These are exemplary comparison diagrams showing the fusion of a precise segmentation result mask and a fast segmentation result mask, as illustrated in some embodiments of this specification. Figure 8As shown, the top and bottom left images are cross-sectional and stereoscopic medical images with and without mask fusion algorithms, respectively. The top and bottom right images are cross-sectional and stereoscopic medical images with and without mask fusion algorithms, respectively. Referring to the top left image, there is a connection between the periphery of the masks for the two target organs (the two organs outlined in the boxes) and the fast segmentation result mask. Comparing the top left and top right images, it can be seen that the result of fusing the fast segmentation result mask and the precise segmentation result mask (such as the target organ mask) using the mask fusion algorithm can disconnect the connection between the target organ mask and the fast segmentation result mask. Referring to the bottom left image, the masks for the two target organs (the two organs outlined in the boxes) are covered by the fast segmentation result mask. Comparing the bottom left and bottom right images, it can be seen that the result of fusing the fast segmentation result mask and the precise segmentation result mask (such as the target organ mask) using the mask fusion algorithm can avoid the target organ mask being covered by the fast segmentation result mask.

[0109] It should be noted that the above description of process 300 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to process 300 under the guidance of this specification; however, such modifications and changes are still within the scope of protection of this specification.

[0110] Figure 9 These are exemplary structural block diagrams of a medical image processing system according to some embodiments of this specification. Figure 9 As shown, the medical image processing system 400 may include an acquisition module 410, a segmentation module 420, a first modification module 430, a connected component processing module 440, and a second modification module 450. The acquisition module 410 is used to acquire medical images; the segmentation module 420 is used to segment the target structure set in the medical image to obtain a de-lipiding mask; the first modification module 430 is used to determine the first intersection between the target organ mask and the de-lipiding mask within a preset range, and adjust the regions of the target organ mask and the de-lipiding mask based on the first intersection; the connected component processing module 440 is used to perform connected component processing on the adjusted de-lipiding mask; and the second modification module 450 is used to obtain a processed de-lipiding mask based on the de-lipiding mask after connected component processing.

[0111] In some embodiments, the acquisition module 410 can be used to acquire operation instructions; the segmentation module 420 can be used to segment at least one target organ in a medical image according to the operation instructions to obtain at least one target organ mask; the first modification module 430 can be used to determine the third intersection of the at least one target organ mask and the fast segmentation result mask within a first preset range, and adjust the regions of the at least one target organ mask and the fast segmentation result mask based on the third intersection, wherein the fast segmentation result mask includes at least the processed degreasing mask; the connected component processing module 440 can be used to perform connected component processing on the adjusted fast segmentation result mask; and the second modification module 450 can be used to obtain the processed fast segmentation result mask based on the fast segmentation result mask processed by the connected component processing.

[0112] It should be noted that for more technical details regarding the execution of corresponding processes or functions by the acquisition module 410, segmentation module 420, first modification module 430, connected component processing block 440, and second modification module 450 to achieve medical image processing, please refer to [link to relevant documentation]. Figures 1 to 8 The medical image processing methods described in any of the illustrated embodiments will not be repeated here. The above description of the medical image processing system 400 is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art will recognize that various forms and details of improvements and changes can be made to the application of the above methods and systems without departing from the principles of this specification. However, such changes and modifications will not depart from the scope of this specification.

[0113] Some embodiments of this specification also provide a medical image processing apparatus, including a processor, which is used to execute the medical image processing method described in any embodiment. See details... Figures 1 to 8 The relevant descriptions will not be repeated here. In some embodiments, the medical image processing apparatus further includes a display device that displays the results of the medical image processing method executed by the processor.

[0114] Some embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions, the computer executes the medical image processing method as described in any of the above embodiments. See details below. Figures 1 to 8 The relevant descriptions will not be repeated here.

[0115] The medical image processing methods, systems, devices, and computer-readable storage media provided in the embodiments of this specification have at least the following beneficial effects:

[0116] (1) By expanding the target organ mask and shrinking the de-lipid mask, the connection between the false positive area and the mask body (e.g., the de-lipid mask body and the target organ mask body) can be broken, and the over-segmentation of the de-lipid mask can be normalized. (2) By performing connected component processing on the shrunken de-lipid mask, the main area of ​​the de-lipid mask and the effective connected area around the target organ mask can be preserved, and the noise area can be removed. (3) By expanding (i.e. restoring) the de-lipid mask after connected component processing, the processed de-lipid mask can be obtained, which can ensure that the processed de-lipid mask does not deform and improve the accuracy of the rapid segmentation results. (4) Combining rapid segmentation with precise segmentation can improve the segmentation efficiency and the accuracy of the segmentation results on the one hand, and allow for the selection of appropriate target organs for segmentation according to clinical needs on the other hand, making the medical image processing workflow more flexible.

[0117] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0118] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0119] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0120] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0121] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0122] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A medical image processing method, comprising: Acquiring medical images; The target structure set in the medical image is segmented to obtain a delipidation mask; Determine a first intersection between the target organ mask and the degreasing mask within a preset range, and adjust the regions of the target organ mask and the degreasing mask based on the first intersection. The adjustment includes expanding the region of the target organ mask and shrinking the region of the degreasing mask. The adjusted degreasing mask is then subjected to connected component processing; Based on the degreasing mask after connected component processing, the processed degreasing mask is obtained, including: The adjusted target organ mask was then inspected. Based on the detection results, the adjacent boundaries between the delipidated mask and the target organ mask after connected component processing are determined. The degreasing mask, after being processed by connected components, is expanded based on the adjacent boundaries to obtain the processed degreasing mask.

2. The method according to claim 1, characterized in that, The step of determining a first intersection between the target organ mask and the degreasing mask within a preset range, and adjusting the regions of the target organ mask and the degreasing mask based on the first intersection, includes: The target organ mask was inspected; Based on the detection results, a first intersection between the target organ mask and the delipidation mask is determined within a first preset range, wherein the first preset range is determined according to a first preset parameter; Based on the first intersection, the regions of the target organ mask and the degreasing mask are adjusted for the first time. The first adjustment includes expanding the region of the target organ mask and shrinking the region of the degreasing mask.

3. The method according to claim 2, characterized in that, Also includes: The second intersection of the target organ mask after the first adjustment and the delipidation mask after the first adjustment is determined within a second preset range, wherein the second preset range is determined according to a second preset parameter; Based on the second intersection, a second adjustment is made to the regions of the target organ mask and the de-lipid mask after the first adjustment. The second adjustment includes a second expansion of the region of the target organ mask after the first adjustment and a second contraction of the region of the de-lipid mask after the first adjustment.

4. The method according to claim 3, characterized in that, The second preset parameter is less than or equal to the first preset parameter, and the first preset parameter and / or the second preset parameter are obtained based on big data and artificial intelligence methods.

5. The method according to claim 1, characterized in that, The connected component processing of the adjusted degreasing mask includes: Determine whether the positioning information of the target organ mask overlaps with the positioning information of the pseudo-de-lipidation connected region, wherein the pseudo-de-lipidation connected region is a connected region within a preset range around the target organ mask; When the judgment result is non-overlapping, the pseudo-de-grease connected region is identified as belonging to the de-grease mask; When the judgment result is overlap, it is determined whether the pseudo-degreased connected region should belong to the degreased mask based on the relationship between the area of ​​the pseudo-degreased connected region and the preset area threshold.

6. The method according to claim 5, characterized in that, The step of determining whether the pseudo-de-liquid connected region should belong to the de-liquidation mask based on the relationship between the area of ​​the pseudo-de-liquid connected region and a preset area threshold includes: When the area of ​​the pseudo-degreasing connected region is greater than the preset area threshold, the pseudo-degreasing connected region is identified as belonging to the degreasing mask; When the area of ​​the pseudo-degreasing connected region is less than or equal to the preset area threshold, the pseudo-degreasing connected region is identified as not belonging to the degreasing mask.

7. The method according to claim 5, characterized in that, Also includes: Retain identifiers and / or discard identifiers, where a retained identifier indicates a pseudo-de-de-smoothed connected region belonging to the de-de-smoothed mask, and a discard identifier indicates a pseudo-de-smoothed connected region not belonging to the de-de-smoothed mask.

8. The method according to claim 1, characterized in that, Also includes: Obtain operation instructions; According to the operation instructions, at least one target organ in the medical image is segmented to obtain at least one target organ mask; A third intersection of at least one target organ mask and a fast segmentation result mask is determined within a first preset range. Based on the third intersection, the regions of at least one target organ mask and the fast segmentation result mask are adjusted. The fast segmentation result mask includes the processed degreasing mask, the target organ mask, and a blood vessel mask within the target organ. The adjusted fast segmentation result mask is then subjected to connected component processing; Based on the fast segmentation result mask after connected component processing, the processed fast segmentation result mask is obtained.

9. A medical image processing system, comprising: The acquisition module is used to acquire medical images; The segmentation module is used to segment the target structure set in the medical image to obtain a delipidated mask; The first modification module is used to determine the first intersection of the target organ mask and the degreasing mask within a preset range, and to adjust the regions of the target organ mask and the degreasing mask based on the first intersection. The adjustment includes expanding the region of the target organ mask and shrinking the region of the degreasing mask. A connected component processing module is used to perform connected component processing on the adjusted degreasing mask; The second modification module is used to obtain the processed degreasing mask based on the degreasing mask after connected component processing, including: The adjusted target organ mask was then inspected. Based on the detection results, the adjacent boundaries between the delipidated mask and the target organ mask after connected component processing are determined. The degreasing mask, after being processed by connected components, is expanded based on the adjacent boundaries to obtain the processed degreasing mask.

10. A medical image processing apparatus, comprising a processor, the processor being configured to perform the medical image processing method according to any one of claims 1 to 8.

11. The processing apparatus of claim 10, further comprising a display device displaying the results of performing the medical image processing method based on the processor.

12. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the medical image processing method as described in any one of claims 1 to 8.

Images