Pancreatic lesion resection type auxiliary decision making system, method and device

Abstract

The invention relates to a pancreatic lesion resection type auxiliary decision making system, method and device, computer equipment and a storage medium. The system comprises a processor which executes the following steps: acquiring a three-dimensional medical image of the pancreas, wherein the three-dimensional medical image of the pancreas comprises a focus; the number of lesions and lesion properties are recognized, the number of the lesions is one or more, and the lesion properties comprise at least one of a first lesion type and a second lesion type; and constructing a decision tree model according to the number of the lesions, the lesion properties and the surgical function to generate a resection auxiliary decision corresponding to the lesions. By adopting the system, the specificity of different pancreatic lesions can be fully considered, a lesion resection type decision-making tree model is constructed according to the number of the lesions, lesion properties and a surgical function, corresponding resection type auxiliary decisions are generated by utilizing judgment branches of the decision-making tree model according to the specific conditions of different lesions, and the lesion resection type auxiliary decisions are obtained. And a doctor is accurately, efficiently and intelligently assisted in selecting a pancreatic focus resection mode.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a pancreatic lesion resection procedure decision-making support system, method, apparatus, computer equipment, and storage medium. Background Art

[0002] Pancreatic tumors are highly malignant, and surgical resection is an effective treatment. CT (computed tomography) and MRI (magnetic resonance imaging) images are crucial for pancreatic tumor assessment and preoperative planning. Currently, surgeons typically assess the pancreas, pancreatic duct, tumor, blood vessels, and other organs and tissues layer by layer on two-dimensional images. They then use subjective assessment or two-dimensional distance measurement tools to determine the appropriate resection method. However, pancreatic tumors often progress rapidly, making this method less intuitive, requiring a high level of surgeon experience, and inefficient, with low accuracy. Summary of the Invention

[0003] Based on this, it is necessary to provide a pancreatic lesion resection procedure decision-making support system, method, device, computer equipment and storage medium to address the above technical issues.

[0004] One of the embodiments of the present specification provides a pancreatic lesion resection procedure decision-making support system, the system including a processor, the processor being configured to perform the following steps: acquiring a three-dimensional medical image of the pancreas, the three-dimensional medical image of the pancreas including lesions; identifying the number of lesions and the nature of the lesions, the number of lesions being one or more, the lesion nature including at least one of a first lesion type and a second lesion type; constructing a decision tree model based on the number of lesions, the lesion nature, and the procedure function to generate a resection procedure decision-making support system corresponding to the lesion.

[0005] In one embodiment, when the processor executes the step of acquiring the three-dimensional medical image of the pancreas, the processor further includes executing the following steps: acquiring medical images of multiple modalities, the multiple modalities including a first modality and a second modality; acquiring medical images of multiple phases under the first modality, and registering the medical images of multiple phases acquired under the first modality to obtain a first-modality pancreatic medical image; acquiring medical images of multiple time sequences under the second modality, and registering the medical images of multiple time sequences acquired under the second modality to obtain a second-modality pancreatic medical image; registering the first-modality pancreatic medical image and the second-modality pancreatic medical image to obtain a registered pancreatic medical image; and performing three-dimensional reconstruction on the registered pancreatic medical image to acquire the three-dimensional medical image of the pancreas.

[0006] In one embodiment, the processor executes the construction of a decision tree model based on the number of lesions, the nature of the lesions and the procedure function to generate an auxiliary decision for the resection procedure corresponding to the lesion, and further includes executing the following steps: constructing the procedure function based on lesion parameters, the lesion parameters including at least one of the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; the procedure function includes a first procedure function, a second procedure function and a third procedure function; constructing the root node of the decision tree model based on the number of lesions, when the number of lesions is one, constructing the first and second level nodes of the decision tree model based on the nature of the lesion, and constructing the decision tree model based on the first procedure function. The first third-level node of the type, or the second third-level node of the decision tree model is constructed according to the second procedure function, and the auxiliary decision of the resection procedure corresponding to the lesion is generated according to the first procedure matching engine; the first procedure matching engine is used to characterize the mapping relationship between the output value of the first procedure function or the output value of the second procedure function and the resection procedure; the root node of the decision tree model is constructed according to the number of lesions, and when the number of lesions is multiple, the second second-level node of the decision tree model is constructed according to the third procedure function, and the auxiliary decision of the resection procedure corresponding to the lesion is generated according to the second procedure matching engine; the second procedure matching engine is used to characterize the mapping relationship between the output value of the third procedure function and the resection procedure.

[0007] In one embodiment, the processor is further used to perform the following steps: when the number of lesions is multiple, executing the second secondary node to calculate the output value of the third surgical function, and the output value of the third surgical function is related to the lesion location; when the lesion location of multiple lesions is the lesion located in the head of the pancreas and / or the lesion located in the neck of the pancreas, generating an auxiliary decision for combined pancreatic head and body resection according to the second surgical matching engine; when the lesion location of multiple lesions is the lesion located in the body of the pancreas and / or the lesion located in the tail of the pancreas, generating an auxiliary decision for pancreatic body and tail resection according to the second surgical matching engine; when the lesion location is at least one of the lesion located in the head of the pancreas and the lesion located in the neck of the pancreas, and the lesion location is also at least one of the lesion located in the body of the pancreas and the lesion located in the tail of the pancreas, generating an auxiliary decision for total pancreatectomy according to the second surgical matching engine.

[0008] In one embodiment, the processor is further configured to perform the following steps: when the number of lesions is one, executing the first secondary node to determine the nature of the lesion; when the nature of the lesion is the first lesion type, executing the first tertiary node to calculate the output value of the first procedure function; constructing the first procedure function based on the lesion parameters, the first procedure matching engine includes a first sub-engine, and generating a resection procedure auxiliary decision corresponding to the lesion based on the first sub-engine; the lesion parameters include at least one of the lesion location and the distance between the lesion and the blood vessel; the lesion location includes the lesion located in the head of the pancreas, the lesion located in the neck of the pancreas, the lesion located in the body of the pancreas, or the lesion located in the tail of the pancreas; the distance between the lesion and the blood vessel includes at least one of the distance between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein; the first procedure matching sub-engine is configured to characterize the mapping relationship between the output value of the first procedure function and the resection procedure.

[0009] In one embodiment, the processor is further used to perform the following steps: when the lesion location is that the lesion is located in the head of the pancreas or the lesion is located in the neck of the pancreas, the lesion parameter is the lesion location, and the output value of the first surgical procedure function is related to the lesion location; when the lesion location is that the lesion is located in the head of the pancreas, a pancreaticoduodenectomy auxiliary decision is generated according to the first sub-engine; when the lesion location is that the lesion is located in the neck of the pancreas, a combined pancreatic head and body resection is generated according to the first sub-engine.

[0010] In one embodiment, the processor is further configured to perform the following steps: when the lesion is located in the pancreatic body or the tail of the pancreas, the lesion parameters include the lesion position and the distance between the lesion and the blood vessel, and when each of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is greater than a first threshold, an auxiliary decision for pancreatic body and tail resection is generated according to the first sub-engine; when the lesion is located in the pancreatic body or the tail of the pancreas, the lesion parameters include the lesion position and the distance between the lesion and the blood vessel, and when any one of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is less than or equal to the first threshold, an auxiliary decision for extended pancreatic body and tail resection is generated according to the first sub-engine.

[0011] In one embodiment, the processor is further configured to perform the following steps: when the number of lesions is one, executing the first secondary node to determine the nature of the lesion; when the lesion nature is the second lesion type, executing the second tertiary node to calculate the output value of the second procedure function; constructing the second procedure function based on the lesion parameters, the first procedure matching engine includes a second sub-engine, and generating a resection procedure auxiliary decision corresponding to the lesion based on the second sub-engine; the lesion parameters include at least one of the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; the lesion location includes the lesion located in the head of the pancreas, the lesion located in the neck of the pancreas, the lesion located in the body of the pancreas, or the lesion located in the tail of the pancreas; the distance between the lesion and the blood vessel includes at least one of the distance between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein; the second sub-engine is configured to characterize the mapping relationship between the output value of the second procedure function and the resection procedure.

[0012] In one embodiment, the processor is further configured to perform the following steps: when the distance between the lesion and the pancreatic duct and the distance between the lesion and the bile duct are both greater than a second threshold, the lesion parameters are the distance between the lesion and the pancreatic duct and the distance between the lesion and the bile duct, generating a local resection auxiliary decision according to the second sub-engine;

[0013] When the lesion location is that the lesion is located in the pancreatic head, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, and the distance between the lesion and the bile duct; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, generating an auxiliary decision for pancreatic head resection with duodenum preservation according to the second sub-engine;

[0014] When the lesion location is that the lesion is located in the pancreatic neck, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, and when each of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is greater than the first threshold, generating an auxiliary decision for mid-segment pancreatectomy with duodenum preservation according to the second sub-engine;

[0015] When the lesion location is that the lesion is located in the pancreatic neck, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, and when any of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, or the distance between the lesion and the portal vein is less than or equal to a first threshold, an auxiliary decision for combined pancreatic head and body resection is generated according to the second sub-engine;

[0016] When the lesion location is the lesion located in the pancreatic body or the lesion located in the pancreatic tail, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, and the distance between the lesion and the bile duct; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, an auxiliary decision for spleen-preserving pancreatectomy is generated according to the second sub-engine.

[0017] In one embodiment, the lesion location is determined by a processor executing the following steps: based on the three-dimensional medical image of the pancreas, skeletonizing and extracting the pancreas in the three-dimensional medical image of the pancreas to obtain skeleton center points of the pancreas, and sorting the skeleton center points according to a first preset rule to form a skeleton center point set; dividing the skeleton center point set into a first subset, a second subset, a third subset, and a fourth subset according to a second preset rule;

[0018] Obtaining the center of gravity of the lesion, calculating the distance between the center of gravity of the lesion and each skeleton center point in the skeleton center point set one by one, and determining the skeleton center point closest to the center of gravity of the lesion as the center point of the lesion position;

[0019] When the center point of the lesion location is located in the first subset, the lesion location is that the lesion is located in the head of the pancreas; when the center point of the lesion location is located in the second subset, the lesion location is that the lesion is located in the neck of the pancreas; when the center point of the lesion location is located in the third subset, the lesion location is that the lesion is located in the body of the pancreas; when the center point of the lesion location is located in the fourth subset, the lesion location is that the lesion is located in the body of the pancreas.

[0020] One of the embodiments of the present specification provides a method for assisting decision-making in a pancreatic lesion resection procedure, the method comprising: acquiring a three-dimensional medical image of the pancreas, the three-dimensional medical image of the pancreas including lesions; identifying the number of lesions and the nature of the lesions, the number of lesions being one or more, and the nature of the lesions including at least one of a first lesion type and a second lesion type; constructing a decision tree model based on the number of lesions, the nature of the lesions, and a procedure function to generate an assisting decision-making for a resection procedure corresponding to the lesion.

[0021] One of the embodiments of the present specification provides a device for assisting decision-making in a pancreatic lesion resection procedure, the device comprising: a medical image acquisition module for acquiring a three-dimensional medical image of the pancreas, the three-dimensional medical image of the pancreas including lesions; a lesion identification module for identifying the number and nature of lesions, the number of lesions being one or more, and the nature of lesions including at least one of a first lesion type and a second lesion type; and an auxiliary decision-making module for constructing a decision tree model based on the number of lesions, the nature of the lesions and a procedure function to generate an auxiliary decision for the resection procedure corresponding to the lesion.

[0022] One of the embodiments of the present specification provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: acquiring a three-dimensional medical image of the pancreas, wherein the three-dimensional medical image of the pancreas includes lesions; identifying the number of lesions and the nature of the lesions, wherein the number of lesions is one or more, and the nature of the lesions includes at least one of a first lesion type and a second lesion type; constructing a decision tree model based on the number of lesions, the nature of the lesions, and the procedure function to generate an auxiliary decision for the resection procedure corresponding to the lesion.

[0023] One of the embodiments of the present specification provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps: acquiring a three-dimensional medical image of the pancreas, wherein the three-dimensional medical image of the pancreas includes lesions; identifying the number of lesions and the nature of the lesions, wherein the number of lesions is one or more, and the nature of the lesions includes at least one of a first lesion type and a second lesion type; constructing a decision tree model based on the number of lesions, the nature of the lesions, and the procedure function to generate an auxiliary decision for the resection procedure corresponding to the lesion.

[0024] Compared with the prior art, the present invention provides a pancreatic lesion resection procedure decision-making support system, method, apparatus, computer equipment, and storage medium, which have the following beneficial effects:

[0025] Taking full account of the specificity of different pancreatic lesions, a decision tree model for lesion resection procedures is constructed based on the number of lesions, the nature of the lesions, and the procedure function. According to the specific conditions of different lesions, the judgment branches of the decision tree model are used to generate corresponding resection procedure auxiliary decision-making, accurately, efficiently, and intelligently assisting doctors in selecting the resection procedure for pancreatic lesions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 Schematic diagram of a pancreatic lesion resection procedure decision support system 100 according to one embodiment;

[0027] Figure 2 A schematic diagram of the execution flow of a pancreatic lesion resection procedure auxiliary decision-making system in one embodiment;

[0028] Figure 3 Schematic diagram of a pancreatic lesion resection procedure auxiliary decision tree model in one embodiment;

[0029] Figure 4 1. It is a structural block diagram of a pancreatic lesion resection surgical procedure decision-making support device according to one embodiment;

[0030] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0032] Figure 1 Figure 1 is a schematic diagram of a pancreatic lesion resection procedure decision support system 100 according to one embodiment of the present application. The pancreatic lesion resection procedure decision support system 100 may include a data acquisition device 110, a processing device 120, a storage device 140, and an interaction device 150. The data acquisition device 110, the processing device 120, the storage device 140, and the interaction device 150 may communicate with each other via a network 130. The processing device 120 includes a processor.

[0033] The data acquisition device 110 can be a device that collects data. The collected data can include image data, object feature data, medical images of the pancreas in different modalities, medical images of the pancreas in different phases, or medical images of the pancreas in different time sequences. For example, the collected image data is a three-dimensional medical image of the pancreas. In one embodiment, the data acquisition device 110 can include one or more imaging devices. The imaging device can collect image data. The imaging device can be a magnetic resonance imaging (MRI), a computed tomography (CT), a positron emission computed tomography (PET), a B-scan ultrasonography, a diasonography, a thermal texture map (TTM), a medical electronic endoscope (MEE), or a combination thereof. The image data can be a three-dimensional medical image of the pancreas. The image data can include images or data of blood vessels, tissues, or organs of the subject. The image data may include multi-phase phase-enhanced CT images, which may include arterial phase, portal venous phase, and delayed phase. The image data may include time-series MRI images, which may include T1-weighted images, T2-weighted images, diffusion-weighted images, dynamic contrast-enhanced magnetic resonance imaging, and magnetic resonance cholangiopancreatography. In one embodiment, the object feature acquisition device may be integrated into the imaging device, thereby simultaneously acquiring image data and object feature data. In one embodiment, the data acquisition device 110 may transmit the acquired data to the processing device 120, the storage device 140, and / or the interactive device 150, etc., via the network 130.

[0034] The processing device 120 can process data. The data can be data collected by the data acquisition device 110, data read from the storage device 140, feedback data obtained from the interactive device 150, such as user input data, or data obtained from the cloud or external device via the network 130. In one embodiment, the data can include image data, object feature data, user input data, decision tree model data, etc. Data processing can include selecting a region of interest in the image data. The region of interest can be selected by the processing device 120 itself or based on user input data. In one embodiment, the selected region of interest can be a lesion, blood vessel, tissue, or organ. For example, the region of interest can be a pancreatic organ, a lesion, a pancreatic duct, a bile duct, a splenic artery, a superior mesenteric artery, a splenic vein, a superior mesenteric vein, or a portal vein. The processing device 120 can further segment the region of interest in the image. Image segmentation methods can include edge-based image segmentation methods, such as the Perwitt operator method, the Sobel operator method, the gradient operator method, the Kirch operator method, etc., region-based image segmentation methods, such as the region growing method, the threshold method, the clustering method, etc., and other segmentation methods, such as methods based on fuzzy sets and neural networks.

[0035] In one embodiment, the processing device 120 can register medical images in multiple phases. For example, the processing device 120 can receive CT arterial phase medical images, CT portal phase medical images, and CT delayed phase medical images acquired by the data acquisition device 110, and register the CT medical images in multiple phases according to image features to obtain a first modality pancreatic medical image. The processing device 120 can also receive magnetic resonance T1-weighted images, T2-weighted images, diffusion-weighted images, dynamic contrast-enhanced magnetic resonance images, and magnetic resonance pancreaticobiliary images acquired by the data acquisition device 110, and register the MRI medical images in multiple phases according to image features to obtain a second modality pancreatic medical image. The first modality pancreatic medical image and the second modality pancreatic medical image are registered to obtain a registered pancreatic medical image. In one embodiment, the registration method includes rigid registration, elastic registration, etc.

[0036] In one embodiment, processing device 120 can automatically distinguish benign and malignant pancreatic tumors through data annotation, model training, and other steps based on a deep learning classification algorithm, such as the classic VGG16, and output the number of lesions and lesion nature labels. In one embodiment, the lesion nature includes at least one of a first lesion type and a second lesion type. The first lesion type includes malignant tumors, and the second lesion type includes benign tumors and / or low-grade tumors.

[0037] In one embodiment, the processing device 120 can construct a decision tree model based on the number of lesions, the nature of the lesions, and the procedure function to generate an auxiliary decision for the resection procedure corresponding to the lesions. In one embodiment, the processing device 120 can determine lesion parameters, which include at least one of the following: lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessels. The processing device 120 can construct a procedure function based on the lesion parameters and generate an auxiliary decision for the resection procedure corresponding to the lesion based on the output value of the procedure function.

[0038] In one embodiment, the processing device 120 can perform noise reduction or smoothing on the data or processing results it obtains. In one embodiment, the processing device 120 can send the data or processing results it obtains to the storage device 140 for storage, or to the interactive device 150 for display. The processing results can be intermediate results generated during the processing, such as identifying the number and nature of lesions, or they can be the final results of the processing, such as generating an auxiliary decision-making for the resection procedure corresponding to the lesion. In one embodiment, the processing device 120 can be one or more processing elements or devices, such as a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a system on a chip (SoC), a microcontroller unit (MCU), etc. In one embodiment, the processing device 120 can also be a specially designed processing element or device with special functions. The processing device 120 can be local or remote relative to the data acquisition device 110.

[0039] The storage device 140 can store data or information. The data or information may include data acquired by the data acquisition device 110, processing results or control instructions generated by the processing device 120, and user input data received by the interactive device 150. The storage device 140 can be one or more readable or writable storage media, including static random access memory (SRAM), random-access memory (RAM), read-only memory (ROM), hard disk, flash memory, etc. In one embodiment, the storage device 140 can also be a remote storage device, such as a cloud disk.

[0040] The interactive device 150 can receive, send, and / or display data or information. The received data or information may include data acquired by the data acquisition device 110, processing results generated by the processing device 120, data stored by the storage device 140, and the like. For example, the data or information displayed by the interactive device 150 may include three-dimensional medical images of the pancreas acquired by the data acquisition device 110, the number and nature of lesions identified by segmentation by the processing device 120, surgical procedure functions calculated by the processing device 120, decision tree models constructed by the processing device 120, and auxiliary decision-making for the resection procedure corresponding to the lesion calculated by the processing device 120. Display formats may include one or more combinations of two-dimensional color medical images, three-dimensional color medical images, color geometric models and their grid analysis, vector maps (such as velocity vector lines), contour maps, filled contour maps (cloud maps), XY scatter plots, particle trajectory plots, simulated flow effects, and the like. For another example, the data or information sent by the interactive device 150 may include user input. The interactive device 150 may receive one or more operating parameters input by the user and send them to the processing device 120. In one embodiment, the interactive device 150 may include a user interface, and the user may input user input data to the interactive device 150 through a specific interactive device, such as a mouse, keyboard, touchpad, microphone, etc.

[0041] In one embodiment, the interactive device 150 may be a device with display functionality, such as a display screen. In one embodiment, the interactive device 150 may have some or all of the functions of the processing device 120. For example, the interactive device 150 may perform operations such as smoothing, noise reduction, and color change on the results generated by the processing device 120. For example, the color change operation may convert a grayscale image into a color image, or vice versa. In one embodiment, the interactive device 150 and the processing device 120 may be an integrated device. The integrated device may simultaneously perform the functions of the processing device 120 and the interactive device 150. In one embodiment, the interactive device 150 may include a desktop computer 150-2, a server, a mobile device, etc. The mobile device may include a mobile phone 150-1, a laptop computer, a tablet computer 150-3, a built-in device in a vehicle (e.g., a motor vehicle, a ship, an airplane, etc.), a wearable device, etc. In one embodiment, the interactive device 150 may include or be connected to a display device, a printer, a fax machine, etc.

[0042] The network 130 can be used for internal communication within the pancreatic lesion resection decision support system 100, receiving information from outside the system, sending information to outside the system, etc. In one embodiment, the data acquisition device 110, the processing device 120, and the interactive device 150 can access the network 130 through a wired connection, a wireless connection, or a combination thereof. The network 130 can be a single network or a combination of multiple networks. In one embodiment, the network 130 can include but is not limited to a local area network, a wide area network, a public network, a private network, a wireless local area network, a virtual network, a metropolitan area network, a public switched telephone network, etc., or a combination of several of them. In one embodiment, the network 130 can include multiple network access points, such as wired or wireless access points, base stations, or network exchange points, through which the data source can connect to the network 130 and send information through the network.

[0043] In one embodiment, Figure 2 The process 200 shown provides an execution process of a pancreatic lesion resection procedure decision support system. The system includes a processor configured to execute the following steps:

[0044] Step 210: Acquire a three-dimensional medical image of the pancreas, where the three-dimensional medical image of the pancreas includes the lesion.

[0045] In one embodiment, the three-dimensional pancreatic medical image may include an X-ray (X-ray) image, a CT image, an MRI image, an ultrasound image, or any combination thereof. The three-dimensional pancreatic medical image includes a lesion. The lesion may be a malignant tumor, a benign tumor, or a low-grade tumor.

[0046] Step 220 , identifying the number of lesions and the nature of the lesions, where the number of lesions is one or more, and the nature of the lesions includes at least one of a first lesion type and a second lesion type.

[0047] In one embodiment, the processor uses deep learning classification algorithms such as VGG16 (Visual Geometry Group 16-layer Convolutional Neural Network), nnUNet (Normalized U-Net, a normalized U-net that does not require manual parameter adjustment), and SWIN-Unet (Swin Transformer-based U-Net, a U-net based on a sliding window attention mechanism) to automatically identify benign and malignant pancreatic tumors through data annotation, model training, and other steps, outputting the number of lesions and lesion nature labels, thereby improving diagnostic accuracy. In one embodiment, the lesion nature includes at least one of a first lesion type and a second lesion type. The first lesion type includes malignant tumors, and the second lesion type includes benign tumors and / or low-grade tumors.

[0048] Step 230: construct a decision tree model based on the number of lesions, the nature of the lesions, and the surgical procedure function to generate an auxiliary decision for the resection surgical procedure corresponding to the lesion.

[0049] In one embodiment, the number of lesions is one or more, each belonging to a different decision tree branch. The first lesion type or the second lesion type belongs to a different decision tree branch. Different output values of the procedure function are used to represent different resection procedure decisions. The resection procedure decision is used to provide decision recommendations to the physician. The specific diagnosis and treatment plan is subject to the physician's judgment.

[0050] The above method fully considers the specificity of different pancreatic lesions. A decision tree model for lesion resection procedures is constructed based on the number of lesions, the nature of the lesions, and the procedure function. According to the specific conditions of different lesions, the judgment branches of the decision tree model are used to generate corresponding resection procedure auxiliary decision-making, accurately, efficiently, and intelligently assisting doctors in selecting the resection procedure for pancreatic lesions, assisting doctors in making more precise pancreatic tumor treatment plans, and improving the accuracy of surgery and treatment effects.

[0051] Step 210 of the processor further includes executing the following steps when acquiring a three-dimensional medical image of the pancreas:

[0052] Step 211 : Acquire medical images of multiple modalities, where the multiple modalities include a first modality and a second modality.

[0053] In one embodiment, the first modality is CT imaging and the second modality is MRI imaging.

[0054] Step 212 : Acquire medical images in a plurality of phases in the first modality, and register the medical images in the plurality of phases acquired in the first modality to obtain a pancreatic medical image in the first modality.

[0055] In one embodiment, medical images acquired under multiple phases in the first modality include CT arterial phase medical images, CT portal phase medical images, and CT delayed phase medical images. CT arterial phase medical images display the blood supply of pancreatic lesions, CT portal phase medical images observe the portal vein system and liver metastases, and CT delayed phase medical images evaluate fibrosis or cystic components. With the portal phase as a reference, the arterial phase and delayed phase data are registered to achieve registration between multiple phases to obtain a first modality pancreatic medical image, that is, a CT modality pancreatic medical image after multi-phase registration. In one embodiment, respiratory gating or breath-hold scanning is used to reduce respiratory artifacts when acquiring medical images under multiple phases in the first modality.

[0056] Step 213 : Acquire multiple time-sequence medical images in the second modality, and register the multiple time-sequence medical images acquired in the second modality to obtain a second-modality pancreatic medical image.

[0057] In one embodiment, medical images acquired in multiple time series under the second modality include T1-weighted images, T2-weighted images, diffusion-weighted images, dynamic contrast-enhanced magnetic resonance images, and magnetic resonance pancreaticobiliary images. T1-weighted images or T2-weighted images are used to contrast the pancreatic parenchyma with the surrounding fat, diffusion-weighted images are used to assess tumor cell density, dynamic contrast-enhanced magnetic resonance images are used to enhance the display of pancreatic tissue, and magnetic resonance pancreaticobiliary images are used to display pancreatic duct or bile duct dilatation. The deformation of each phase is captured according to the optical flow method, etc., and the registration between multiple time series is achieved to obtain the second modality pancreatic medical image, that is, the MRI modality pancreatic medical image after multi-time series registration. In one embodiment, navigation echo triggering is used to reduce respiratory artifacts when acquiring medical images in multiple time series under the second modality.

[0058] Step 214 : Register the pancreatic medical image of the first modality and the pancreatic medical image of the second modality to obtain a registered pancreatic medical image.

[0059] In one embodiment, the pancreas is used as the region of interest, and rigid registration is performed on the first modality pancreatic medical image and the second modality pancreatic medical image. A symmetric normalization algorithm is then used to optimize local alignment, and elastic registration is performed on the rigid registration of the first modality pancreatic medical image and the second modality pancreatic medical image. In one embodiment, vascular-guided registration is performed, and the celiac trunk and portal vein are extracted as registration references to enhance vascular alignment accuracy. In one embodiment, the registered pancreatic medical image is in CT image space. In one embodiment, the registered pancreatic medical image is in MRI image space.

[0060] Step 215 : Perform three-dimensional reconstruction on the registered pancreatic medical image to obtain a three-dimensional pancreatic medical image.

[0061] In one embodiment, 3D reconstruction of registered pancreatic medical images includes tissue and organ structure segmentation. This includes segmentation of the pancreas, lesions, pancreatic ducts, bile ducts, blood vessels, and surrounding organs. Blood vessels include the splenic artery, superior mesenteric artery, splenic vein, superior mesenteric vein, and portal vein. Peripheral organs include the stomach, duodenum, or spleen. Pancreas segmentation can be achieved by pre-training a pancreas segmentation model using the nnUNet algorithm. Lesion segmentation can be achieved using the SWIN-Unet algorithm. U-Net (U-shaped network) combined with a vessel tracking algorithm can be used to extract tubular structures and achieve pancreatic and bile duct segmentation. Vessel segmentation can be achieved using a vessel enhancement filter combined with region growing. Deep learning methods such as V-Net (V-shaped network) can also be used for vessel segmentation. Automatic whole-body medical image segmentation tools can be used to achieve segmentation of surrounding organs.

[0062] In one embodiment, 3D reconstruction of the registered pancreatic medical image includes tissue and organ structure fusion. This fusion includes vascular fusion, pancreatic duct fusion, bile duct fusion, and multi-phase and multi-time series lesion fusion. Vascular fusion primarily utilizes CTA (CT Angiography) and / or CTV (CT Venography), supplemented by MRI vascular wall information. Pancreatic duct fusion and bile duct fusion fuse the segmentation results of the pancreatic and bile ducts into the registered pancreatic medical image. Multi-phase and multi-time series lesion fusion utilizes an enhanced regional weighted fusion approach, for example, prioritizing the arterial phase image by increasing its weight and decreasing the weight of images from other phases or time series.

[0063] In one embodiment, a 3D reconstruction of the registered pancreatic medical image is performed, including surface reconstruction, volume rendering fusion, and spatiotemporal dynamic modeling. Surface reconstruction uses the marching cubes method to generate smooth surfaces of the pancreas, lesions, and surrounding organs. A tubular mesh is generated by extracting vascular centerlines. Volume rendering fusion includes multimodal transparency adjustment and color coding. The spatiotemporal dynamic modeling includes 4D blood flow simulation to simulate the perfusion dynamics of the contrast agent within the lesion.

[0064] The above system integrates the advantages of multi-modality and multi-time series imaging, such as CT display of calcification and blood vessels, and MRI definition of tumor boundaries. By accurately calculating the positional relationship between the tumor and the pancreatic duct, bile duct and surrounding blood vessels, it improves the assessment accuracy, provides an accurate medical imaging basis for auxiliary decision-making on subsequent pancreatic lesion resection procedures, and provides users with intuitive display support, reducing dependence on physician experience.

[0065] refer to Figure 3 The processor executes step 230 to construct a decision tree model for pancreatic lesion resection surgery, based on the number of lesions, the nature of the lesions, and the surgery function, to generate an auxiliary decision tree for the resection surgery corresponding to the lesion, and further includes executing the following steps:

[0066] Step 310, constructing a procedure function based on the lesion parameters, the lesion parameters including at least one of the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; the procedure function includes a first procedure function, a second procedure function, and a third procedure function.

[0067] In one embodiment, a procedure function is used to characterize the relationship between lesion parameters and lesion resection procedures. Different lesions have different lesion parameters, and different lesion parameters result in different resection procedures being applicable to the lesions. The procedure function is constructed from lesion parameters, which include at least one of lesion location, distance between the lesion and the pancreatic duct, distance between the lesion and the bile duct, and distance between the lesion and a blood vessel. The procedure functions include a first procedure function y1, a second procedure function y2, and a third procedure function y3.

[0068] Step 320, construct the root node of the decision tree model according to the number of lesions. When the number of lesions is one, construct the first and second level nodes of the decision tree model according to the nature of the lesion, construct the first and third level nodes of the decision tree model according to the first procedure function, or construct the second and third level nodes of the decision tree model according to the second procedure function, and generate the resection procedure auxiliary decision corresponding to the lesion according to the first procedure matching engine; the first procedure matching engine is used to characterize the mapping relationship between the output value of the first procedure function or the output value of the second procedure function and the resection procedure.

[0069] In one embodiment, the lesion resection procedure is also related to the number and nature of the lesions. The number of lesions serves as the root node of the decision tree model, and the lesion nature serves as the first and second level nodes of the decision tree model. When the lesion is a single lesion, the lesion nature needs to be further considered. Based on the lesion nature, the first and third level nodes constructed by the first procedure function y1 or the second and third level nodes constructed by the second procedure function y2 are selected. The resection procedure corresponding to the lesion is generated based on the first procedure matching engine. The first procedure matching engine represents the mapping relationship between the output value of y1 or the output value of y2 and the resection procedure.

[0070] Step 330, construct the root node of the decision tree model according to the number of lesions. When the number of lesions is multiple, construct the second secondary node of the decision tree model according to the third procedure function, and generate the auxiliary decision of the resection procedure corresponding to the lesion according to the second procedure matching engine; the second procedure matching engine is used to characterize the mapping relationship between the output value of the third procedure function and the resection procedure.

[0071] In one embodiment, the lesion resection procedure is also related to the number of lesions. The number of lesions serves as the root node of the decision tree model. When there are multiple lesions, i.e., multiple lesions, the decision tree model is constructed using the third procedure function y3, which is used to generate the corresponding resection procedure for the lesion. The second procedure matching engine generates a mapping between the output value of y3 and the resection procedure.

[0072] Through the above system, according to the construction of the lesion function of the lesion reference system, based on the decision tree model, the number of lesions, the nature of the lesions, and the lesion function are strictly designed, forming an intelligent and efficient pancreatic lesion resection procedure auxiliary decision-making system. It is suitable for various tumor scenarios such as single, multiple, malignant and benign tumors, with a wider range of applications, helping users to accurately and quickly determine the resection procedure for specific lesions.

[0073] The lesion location in step 310 is determined by the processor performing the following steps:

[0074] Step 311: Based on the three-dimensional medical image of the pancreas, skeletonization and extraction of the pancreas in the three-dimensional medical image of the pancreas are performed to obtain skeleton center points of the pancreas. The skeleton center points are sorted according to a first preset rule to form a skeleton center point set; and the skeleton center point set is divided into a first subset, a second subset, a third subset, and a fourth subset according to a second preset rule.

[0075] In one embodiment, a U-Net variant combined with skeleton regression, topology thinning, distance transform, or end-to-end centerline prediction can be used to skeletonize and extract the pancreas from a three-dimensional medical image to obtain the pancreatic skeleton center points. In one embodiment, the left side of the three-dimensional medical image represents the pancreatic head and the right side represents the pancreatic tail. A first preset rule is to sort the skeleton center points from left to right to form a skeleton center point set. A second preset rule is to divide the skeleton center point set from left to right, with the first 30% (inclusive) of the skeleton center point set as the first subset, 30% (excluding) to 40% (inclusive) of the skeleton center point set as the second subset, 40% (excluding) to 75% (inclusive) of the skeleton center point set as the third subset, and 75% (excluding) to 100% (inclusive) of the skeleton center point set as the fourth subset. Of course, if the patient is a mirror image, the first preset rule can also be to sort the skeleton center points from right to left to form the skeleton center point set. The second preset rule is to divide the skeleton center point set from right to left, and the subsets are divided from right to left with reference to the subset division ratio from left to right, which will not be repeated here.

[0076] Step 312: Obtain the center of gravity of the lesion, calculate the distance between the center of gravity of the lesion and each skeleton center point in the skeleton center point set, and determine the skeleton center point closest to the center of gravity of the lesion as the center point of the lesion position.

[0077] In one embodiment, a distance calculation method is used to calculate the distance between the center of gravity of the lesion and each skeleton center point in the skeleton center point set one by one until the skeleton center point closest to the center of gravity of the lesion is found as the lesion position center point. The lesion position center point is used to indicate the location of the lesion. In one embodiment, the center of gravity of the lesion can be determined by spatial moment calculation, key point regression, heat map regression, principal component analysis, or centroid calculation. In one embodiment, the distance calculation method can be Euclidean distance, etc.

[0078] Step 313: When the center point of the lesion location is located in the first subset, the lesion location is located in the head of the pancreas; when the center point of the lesion location is located in the second subset, the lesion location is located in the neck of the pancreas; when the center point of the lesion location is located in the third subset, the lesion location is located in the body of the pancreas; when the center point of the lesion location is located in the fourth subset, the lesion location is located in the body of the pancreas.

[0079] In one embodiment, lesion location center points belonging to different subsets represent different lesion locations.

[0080] Through the above system, the location of the lesion can be accurately determined, providing accurate lesion parameter support for auxiliary decision-making on subsequent pancreatic lesion resection procedures.

[0081] Step 330 also includes the processor performing the following steps:

[0082] Step 331: When there are multiple lesions, the second secondary node is executed to calculate the output value of the third formula function, and the output value of the third formula function is related to the position of the lesion.

[0083] Step 332: When the lesion is located in the pancreatic head or the pancreatic neck, an auxiliary decision for combined pancreatic head and body resection is generated according to the second surgical procedure matching engine.

[0084] Step 333 : When the lesion location is the pancreatic body or the pancreatic tail, an auxiliary decision for pancreatic body and tail resection is generated according to the second surgical procedure matching engine.

[0085] Step 334: When the lesion location is at least one of the pancreatic head and the pancreatic neck, and the lesion location is also at least one of the pancreatic body and the pancreatic tail, a total pancreatectomy auxiliary decision is generated according to the second surgical procedure matching engine.

[0086] In one embodiment, the third formula function is , the output value of the third surgical function is related to the location of the lesion, y3 is expressed by the following formula (1).

[0087] (1)

[0088] When the number of lesions is multiple, the processor executes to calculate the third surgical procedure function, where a i is used to represent the lesion location of the i-th lesion, i = (1, 2, 3, ……, N), δ(a i , 1) and δ(a i , 3) are respectively used to represent the Kronecker function, and N is used to represent the number of lesions. When a i = 1, δ(a i , 1) = 1; when a i ≠ 1, δ(a i , 1) = 0; when a i = 3, δ(a i , 3) = 1; when a i ≠ 3, δ(a i , 3) = 0. a i is assigned different values according to different lesion locations, the output value of y3 is different, and the corresponding surgical procedure assisted decision is different. The mapping relationship between the output value of the third surgical procedure function represented by the second surgical procedure matching engine and the surgical procedure is specifically referred to Table 1.

[0089] Referring to Table 1, when the lesion location is that the lesion is located in the pancreatic head, a i = 1, when the lesion is located in the pancreatic neck, a i = 2, when the N lesion locations are all in the pancreatic head, the function value of y3 is 2; when the N lesion locations are all in the pancreatic neck, the function value of y3 is 2; when some of the N lesions are located in the pancreatic head and some are located in the pancreatic neck, the function value of y3 is 2. According to the second surgical procedure matching engine, y3 = 2, and a pancreatic head-body combined resection assisted decision is generated for the current multiple lesions.

[0090] Referring to Table 1, when the lesion location is that the lesion is located in the pancreatic body, a i = 3, when the lesion is located in the pancreatic tail, a i = 4, when the N lesion locations are all in the pancreatic body, the function value of y3 is 4; when the N lesion locations are all in the pancreatic tail, the function value of y3 is 4; when some of the N lesions are located in the pancreatic body and some are located in the pancreatic tail, the function value of y3 is 4. According to the second surgical procedure matching engine, y3 = 4, and a pancreatic body-tail resection assisted decision is generated for the current multiple lesions.

[0091] Referring to Table 1, at least one of the N lesions has a lesion location of the lesion located in the pancreatic head or the lesion located in the pancreatic neck, and at least one of the N lesions also has a lesion location of the lesion located in the pancreatic body or the lesion located in the pancreatic tail. According to the calculation of formula (1), it can be known that 2 < y3 < 4. According to the second surgical procedure matching engine, 2 < y3 < 4, and a total pancreatectomy assisted decision is generated for the current multiple lesions.

[0092] Through the above system, when there are multiple lesions, it is only necessary to construct a surgical procedure function based on the location of the lesions, and to construct a decision tree model based on the number of lesions and the third surgical procedure function. Based on the output value of the third surgical procedure function, the surgical procedure for resection of pancreatic lesions can be determined quickly, accurately and efficiently to assist in decision-making.

[0093] Table 1 Second formula matching engine

[0094]

[0095] Step 320 also includes the processor performing the following steps:

[0096] Step 3210: When the number of lesions is one, the first and second level nodes are executed to determine the nature of the lesion; when the nature of the lesion is the first lesion type, the first and third level nodes are executed to calculate the output value of the first formula function.

[0097] Step 3211, construct a first procedure function based on lesion parameters, the first procedure matching engine includes a first sub-engine, and generates a resection procedure auxiliary decision corresponding to the lesion based on the first sub-engine; the lesion parameters include at least one of the lesion location and the distance between the lesion and the blood vessel; the lesion location includes the lesion located in the head of the pancreas, the lesion located in the neck of the pancreas, the lesion located in the body of the pancreas, or the lesion located in the tail of the pancreas; the distance between the lesion and the blood vessel includes at least one of the distance between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein; the first sub-engine is used to characterize the mapping relationship between the output value of the first procedure function and the resection procedure.

[0098] In one embodiment, the first technique function is y1, and the first technique function is related to at least one of the lesion location and the distance between the lesion and the blood vessel. The first technique function y1 is expressed by the following formula (2).

[0099] (2)

[0100] When the number of lesions is one, the processor further determines the nature of the lesion. If the lesion is of the first lesion type, i.e., a malignant tumor, the processor calculates the first surgical procedure function, where a represents the lesion location. When the lesion is located in the pancreatic head, a is assigned a value of 1; when the lesion is located in the pancreatic neck, a is assigned a value of 2; when the lesion is located in the pancreatic body, a is assigned a value of 3; and when the lesion is located in the pancreatic tail, a is assigned a value of 4. δ(a,4) represents the Kronecker function. When the lesion is located in the pancreatic tail, δ(a,4) = 1; when the lesion is located elsewhere, δ(a,4) = 0. To round down, if the lesion is located in the pancreatic tail, a=4, =1; if the lesion is located in the pancreatic head a=1, = 0. c1 represents the distance between the lesion and the splenic artery, c2 represents the distance between the lesion and the superior mesenteric artery, c3 represents the distance between the lesion and the splenic vein, c4 represents the distance between the lesion and the superior mesenteric vein, and c5 represents the distance between the lesion and the portal vein.

[0101] Using the above system, when there is only one lesion, a decision tree model is constructed based on the number of lesions, the nature of the lesion, and the first procedure function. The first sub-engine refers to Table 2 to characterize the mapping relationship between the output value of the first procedure function and the resection procedure. Based on the output value of the first procedure function, a decision-making aid for the resection procedure of the pancreatic lesion can be quickly, accurately, and efficiently determined.

[0102] Step 3211 also includes the processor performing the following steps:

[0103] Step 32110: When the lesion location is the pancreatic head or the pancreatic neck, the lesion parameter is the lesion location, and the output value of the first procedure function is related to the lesion location.

[0104] Step 32111: When the lesion is located in the head of the pancreas, a pancreaticoduodenectomy auxiliary decision is generated according to the first sub-engine.

[0105] In step 32112, when the lesion is located in the pancreatic neck, a combined pancreatic head and body resection is generated according to the first sub-engine.

[0106] In one embodiment, referring to Table 2, when the lesion is located at the pancreatic head or the pancreatic neck, the first procedure function y1 is only related to the lesion location, and formula (2) can be simplified to the following formula (3).

[0107] y1=a-δ(a,4) (3)

[0108] When the lesion is located in the pancreatic head, a=1, δ(a,4)=0, y1=1, refer to the first sub-engine in Table 2 to generate a pancreaticoduodenectomy auxiliary decision. When the lesion is located in the pancreatic neck, a=2, δ(a,4)=0, y1=2, refer to the first sub-engine in Table 2 to generate a combined pancreatic head and body resection. Through the above system, when there is only one lesion, a decision tree model is constructed based on the number of lesions, the nature of the lesion, and the first procedure function. The first sub-engine refers to Table 2 to characterize the mapping relationship between the output value of the first procedure function and the resection procedure. Based on the output value of the first procedure function, the auxiliary decision of the resection procedure of the pancreatic lesion can be determined quickly, accurately, and efficiently. Furthermore, the first procedure function can be simplified according to the location of the lesion, making the calculation efficiency of the auxiliary decision of the resection procedure of the pancreatic lesion higher.

[0109] Step 3211 also includes the processor performing the following steps:

[0110] In step 32120, when the lesion is located in the pancreatic body or the pancreatic tail, the lesion parameters include the lesion location and the distance between the lesion and the blood vessels. When each of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is greater than a first threshold, an auxiliary decision for pancreatic body and tail resection is generated according to the first sub-engine.

[0111] Step 32121: When the lesion is located in the pancreatic body or the pancreatic tail, the lesion parameters include the lesion location and the distance between the lesion and the blood vessels. When any one of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is less than or equal to a first threshold, an auxiliary decision for extended pancreatic body and tail resection is generated according to the first sub-engine.

[0112] In one embodiment, referring to Table 2, when the lesion location is the lesion located in the pancreatic body or the lesion located in the pancreatic tail, the first procedure function is related to the lesion location and the distance between the lesion and the blood vessel. The first procedure function is y1 and is expressed by formula (2). When the distance between the lesion and the splenic artery is greater than the first threshold, c1=1, and when it is less than or equal to the first threshold, c1=0; when the distance between the lesion and the superior mesenteric artery is greater than the first threshold, c2=1, and when it is less than or equal to the first threshold, c2=0; when the distance between the lesion and the splenic vein is greater than the first threshold, c3=1, and when it is less than or equal to the first threshold, c3=0; when the distance between the lesion and the superior mesenteric vein is greater than the first threshold, c4=1, and when it is less than or equal to the first threshold, c4=0; when the distance between the lesion and the portal vein is greater than the first threshold, c5=1, and when it is less than or equal to the first threshold, c5=0.

[0113] When each of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is greater than the first threshold, the output value y1 of the first surgical procedure function is 3, and the first sub-engine generates an auxiliary decision for distal pancreatectomy according to Table 2.

[0114] When any one of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is less than or equal to the first threshold, the output value y1 of the first surgical procedure function is 4, and the first sub-engine generates an auxiliary decision for extended pancreatic tail resection according to Table 2.

[0115] In one embodiment, the first threshold is 1 mm. The distance relationship between the lesion and the splenic artery, the distance relationship between the lesion and the superior mesenteric artery, the distance relationship between the lesion and the splenic vein, the distance relationship between the lesion and the superior mesenteric vein, and the distance relationship between the lesion and the portal vein can have the same first threshold or different first thresholds. The first threshold can be adjusted according to user needs.

[0116] Table 2 The first sub-engine

[0117]

[0118] The “ / ” in Table 2 indicates that the parameter can take any value within the value range, a∈{1,2,3,4}, c1∈{0,1}, c2∈{0,1}, c3∈{0,1}, c4∈{0,1}, c5∈{0,1}.

[0119] Step 320 also includes the processor performing the following steps:

[0120] Step 3220: When the number of lesions is one, the first and second level nodes are executed to determine the nature of the lesion; when the nature of the lesion is the second lesion type, the second and third level nodes are executed to calculate the output value of the second formula function;

[0121] Step 3221, construct a second procedure function based on the lesion parameters, the first procedure matching engine includes a second sub-engine, and an auxiliary decision of the resection procedure corresponding to the lesion is generated according to the second sub-engine; the lesion parameters include at least one of the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; the lesion location includes the lesion located in the head of the pancreas, the lesion located in the neck of the pancreas, the lesion located in the body of the pancreas, or the lesion located in the tail of the pancreas; the distance between the lesion and the blood vessel includes at least one of the distance between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein; the second sub-engine is used to characterize the mapping relationship between the output value of the second procedure function and the resection procedure.

[0122] In one embodiment, the second procedure function is y2, and the second procedure function is related to at least one of the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel. The second procedure function y2 is expressed by the following formula (4).

[0123] (4)

[0124] When the number of lesions is 1, the processor further determines the nature of the lesion. When the lesion nature is the second lesion type, i.e., benign tumor and / or low-grade malignant tumor, the second surgical function is executed, where a represents the location of the lesion. When the lesion is located in the pancreatic head, a is assigned a value of 1; when the lesion is located in the pancreatic neck, a is assigned a value of 2; when the lesion is located in the pancreatic body, a is assigned a value of 3; when the lesion is located in the pancreatic tail, a is assigned a value of 4. δ(a,2) δ(a,3) represents the Kronecker function. When the lesion is located in the pancreatic neck, δ(a,2) = 1; when the lesion is located elsewhere, δ(a,2) = 0. Similarly, when the lesion is located in the pancreatic body, δ(a,3) = 1; when the lesion is located elsewhere, δ(a,3) = 0. b1 represents the distance between the lesion and the pancreatic duct, b2 represents the distance between the lesion and the bile duct, c1 represents the distance between the lesion and the splenic artery, c2 represents the distance between the lesion and the superior mesenteric artery, c3 represents the distance between the lesion and the splenic vein, c4 represents the distance between the lesion and the superior mesenteric vein, and c5 represents the distance between the lesion and the portal vein. Using the above system, when there is only one lesion, a decision tree model is constructed based on the number of lesions, lesion properties, and the second procedure function. The second sub-engine, referring to Table 3, represents the mapping relationship between the output value of the second procedure function and the resection procedure. Based on the output value of the second procedure function, a decision-making aid for pancreatic lesion resection can be quickly, accurately, and efficiently determined.

[0125] Step 3221 also includes the processor performing the following steps:

[0126] Step 32211, when the distance between the lesion and the pancreatic duct and the distance between the lesion and the bile duct are both greater than the second threshold, the lesion parameters are the distance between the lesion and the pancreatic duct and the distance between the lesion and the bile duct, and a local resection auxiliary decision is generated according to the second sub-engine.

[0127] In one embodiment, referring to Table 3, when the distance between the lesion and the pancreatic duct is greater than the second threshold, b1=1; when it is less than or equal to the second threshold, b1=0; when the distance between the lesion and the bile duct is greater than the second threshold, b2=1; when it is less than or equal to the second threshold, b2=0. When both the distance between the lesion and the pancreatic duct and the distance between the lesion and the bile duct are greater than the second threshold, the second surgical function is only related to the distance relationship between the lesion and the bile duct and the distance relationship between the lesion and the bile duct, and formula (4) can be simplified to formula (5)

[0128] (5)

[0129] The output value y2 of the second surgical procedure function is 5, and the second sub-engine generates a local resection auxiliary decision according to Table 3.

[0130] Step 32212, when the lesion location is that the lesion is located in the pancreatic head, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, and the distance between the lesion and the bile duct; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold, an auxiliary decision for pancreatic head resection with duodenum preservation is generated according to the second sub-engine.

[0131] In one embodiment, referring to Table 3, when the lesion is located in the pancreatic head, a=1, δ(a,3)=0, the second surgical function is related to the lesion location, the distance relationship between the lesion and the bile duct, and the distance relationship between the lesion and the bile duct. Formula (4) can be simplified to Formula (6)

[0132] (6)

[0133] When the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold, b1=0 and / or b2=0, the output value of the second surgical procedure function y2=6, and the second sub-engine generates an auxiliary decision for duodenum-preserving pancreatic head resection according to Table 3.

[0134] Step 32213, when the lesion location is that the lesion is located in the pancreatic neck, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold, and when each of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is greater than the first threshold, an auxiliary decision for mid-pancreatectomy with duodenum preservation is generated according to the second sub-engine.

[0135] In one embodiment, referring to Table 3, when the lesion is located at the pancreatic neck a=2, the second surgical procedure function refers to formula (4), and the second surgical procedure function is related to the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel. When the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold b1=0 and / or b2=0, and the distance between the lesion and the splenic artery is greater than the first threshold c1=1, the distance between the lesion and the superior mesenteric artery is greater than the first threshold c2=1, the distance between the lesion and the splenic vein is greater than the first threshold c3=1, the distance between the lesion and the superior mesenteric vein is greater than the first threshold c4=1, and the distance between the lesion and the portal vein is greater than the first threshold c5=1, then the output value y2=7 of the second surgical procedure function is generated according to Table 3, and the second sub-engine generates an auxiliary decision for mid-pancreatectomy with duodenum preservation.

[0136] In step 32214, when the lesion location is that the lesion is located in the pancreatic neck, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessels; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold, and when the distance between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, or the distance between the lesion and the portal vein is less than or equal to the first threshold, an auxiliary decision for combined pancreatic head and body resection is generated according to the second sub-engine.

[0137] In one embodiment, referring to Table 3, when the lesion is located at the pancreatic neck with a=2, the second surgical procedure function refers to formula (4), and the second surgical procedure function is related to the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel. When the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold b1=0 and / or b2=0, and when any of the following conditions exists: c1=0 when the distance between the lesion and the splenic artery is less than or equal to the first threshold, c2=0 when the distance between the lesion and the superior mesenteric artery is less than or equal to the first threshold, c3=0 when the distance between the lesion and the splenic vein is less than or equal to the first threshold, c4=0 when the distance between the lesion and the superior mesenteric vein is less than or equal to the first threshold, or c5=0 when the distance between the lesion and the portal vein is less than or equal to the first threshold, the output value y2=8 of the second surgical procedure function is generated according to Table 3 by the second sub-engine for pancreatic head and body resection auxiliary decision making.

[0138] Step 32215, when the lesion location is the lesion located in the pancreatic body or the lesion is located in the pancreatic tail, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, and the distance between the lesion and the bile duct; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold, an auxiliary decision for spleen-preserving pancreatectomy is generated according to the second sub-engine.

[0139] In one embodiment, referring to Table 3, when the lesion location is a=3 for the lesion in the pancreatic body or a=4 for the lesion in the pancreatic tail, δ(a,3)=0, the second procedure function is related to the lesion location, the distance relationship between the lesion and the bile duct, and the distance relationship between the lesion and the bile duct. Formula (4) can be simplified to Formula (6) above. When the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to the second threshold, b1=0 and / or b2=0, the output value of the second procedure function y2=9, and the second sub-engine generates an auxiliary decision for spleen-preserving pancreatectomy with the body and tail of the pancreas according to Table 3.

[0140] In one embodiment, the first threshold is 1 mm. The distance relationship between the lesion and the splenic artery, the distance relationship between the lesion and the superior mesenteric artery, the distance relationship between the lesion and the splenic vein, the distance relationship between the lesion and the superior mesenteric vein, and the distance relationship between the lesion and the portal vein can have the same first threshold or different first thresholds. The first threshold can be adjusted according to user needs. In one embodiment, the second threshold is 3 mm. The second threshold used to represent the distance relationship between the lesion and the pancreatic duct can be the same as or different from the second threshold used for the distance relationship between the lesion and the bile duct.

[0141] Through the above system, when there is only one lesion, a decision tree model is constructed based on the number of lesions, the nature of the lesion, and the second procedure function. The second sub-engine refers to Table 3 to characterize the mapping relationship between the output value of the second procedure function and the resection procedure. Based on the output value of the second procedure function, the resection procedure for pancreatic lesions can be quickly, accurately, and efficiently determined. Furthermore, the second procedure function can be simplified based on the location of the lesion, making the computational efficiency of the resection procedure for pancreatic lesions more efficient.

[0142] Table 3 Second sub-engine

[0143]

[0144] The “ / ” in Table 3 indicates that the parameter can take any value within the value range, a∈{1,2,3,4}, b1∈{0,1}, b2∈{0,1}, c1∈{0,1}, c2∈{0,1}, c3∈{0,1}, c4∈{0,1}, c5∈{0,1}.

[0145] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0146] In one embodiment, a method for assisting decision-making in pancreatic lesion resection surgery is provided, the method comprising the following steps:

[0147] Obtaining three-dimensional medical images of the pancreas, including lesions;

[0148] identifying the number of lesions and the nature of the lesions, where the number of lesions is one or more, and the nature of the lesions includes at least one of a first lesion type and a second lesion type;

[0149] A decision tree model was constructed based on the number of lesions, the nature of the lesions, and the surgical procedure function to generate auxiliary decisions on the resection procedure corresponding to the lesions.

[0150] In one embodiment, Figure 4 As shown, a pancreatic lesion resection procedure decision support device 400 is provided, which includes a medical image acquisition module 410, a lesion identification module 420 and a decision support module 430, wherein:

[0151] A medical image acquisition module 410 is configured to acquire a three-dimensional medical image of the pancreas, wherein the three-dimensional medical image of the pancreas includes a lesion;

[0152] a lesion identification module 420, configured to identify the number of lesions and the nature of the lesions, wherein the number of lesions is one or more, and the nature of the lesions includes at least one of a first lesion type and a second lesion type;

[0153] The auxiliary decision module 430 is used to construct a decision tree model according to the number of lesions, the nature of the lesions and the surgical procedure function to generate an auxiliary decision for the resection surgical procedure corresponding to the lesion.

[0154] For the specific definition of the pancreatic lesion resection procedure decision-making support device, please refer to the definition of the pancreatic lesion resection procedure decision-making support system above, which will not be repeated here. The various modules in the above-mentioned pancreatic lesion resection procedure decision-making support device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0155] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication. The wireless communication can be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a method for assisting decision-making regarding pancreatic lesion resection procedures. The display screen of the computer device can be a liquid crystal display or an electronic ink display. The input device of the computer device can be a touch screen covering the display screen, keys, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse.

[0156] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0157] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0158] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0159] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0160] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A pancreatic lesion resection procedure decision support system, characterized in that: The system includes a processor configured to perform the following steps: Acquiring a three-dimensional medical image of the pancreas, wherein the three-dimensional medical image of the pancreas includes a lesion; identifying the number of lesions and the nature of the lesions, where the number of lesions is one or more, and the nature of the lesions includes at least one of a first lesion type and a second lesion type; A decision tree model is constructed according to the number of lesions, the nature of the lesions and the surgical procedure function to generate an auxiliary decision for the resection surgical procedure corresponding to the lesions.

2. The system according to claim 1, wherein: When the processor executes the method of acquiring a three-dimensional medical image of the pancreas, the processor further comprises executing the following steps: Acquiring medical images of multiple modalities, the multiple modalities including a first modality and a second modality; Acquire medical images in a plurality of phases in the first modality, and register the medical images in the plurality of phases acquired in the first modality to obtain a pancreatic medical image in the first modality; Acquire multiple time-series medical images in the second modality, and register the multiple time-series medical images acquired in the second modality to obtain a second-modality pancreatic medical image; Registering the first modality pancreatic medical image and the second modality pancreatic medical image to obtain a registered pancreatic medical image; Perform three-dimensional reconstruction on the registered pancreatic medical image to obtain the three-dimensional pancreatic medical image.

3. The system according to claim 1, wherein: When the processor executes the step of constructing a decision tree model according to the number of lesions, the nature of the lesions, and the surgical procedure function to generate an auxiliary decision on the resection surgical procedure corresponding to the lesion, the processor further includes executing the following steps: constructing the procedure function according to lesion parameters, wherein the lesion parameters include at least one of the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; the procedure function includes a first procedure function, a second procedure function, and a third procedure function; Constructing a root node of the decision tree model according to the number of lesions; when the number of lesions is one, constructing first and second-level nodes of the decision tree model according to the properties of the lesion; constructing first and third-level nodes of the decision tree model according to the first procedure function, or constructing second and third-level nodes of the decision tree model according to the second procedure function; generating an auxiliary decision of a resection procedure corresponding to the lesion according to a first procedure matching engine; the first procedure matching engine is used to characterize a mapping relationship between an output value of the first procedure function or an output value of the second procedure function and the resection procedure; The root node of the decision tree model is constructed according to the number of lesions. When the number of lesions is multiple, the second secondary node of the decision tree model is constructed according to the third procedure function, and the auxiliary decision of the resection procedure corresponding to the lesion is generated according to the second procedure matching engine; the second procedure matching engine is used to characterize the mapping relationship between the output value of the third procedure function and the resection procedure.

4. The system according to claim 3, characterized in that The processor is further configured to perform the following steps: When the number of the lesions is multiple, executing the second secondary node to calculate the output value of the third formula function, the output value of the third formula function is related to the position of the lesions; When the lesion locations of the multiple lesions are lesions located in the pancreatic head and / or lesions located in the pancreatic neck, generating an auxiliary decision for combined pancreatic head and body resection according to the second surgical procedure matching engine; When the lesion locations of the multiple lesions are lesions located in the pancreatic body and / or lesions located in the pancreatic tail, generating an auxiliary decision for pancreatic body and tail resection according to the second surgical procedure matching engine; When the lesion location is at least one of the lesion located in the head of the pancreas and the lesion located in the neck of the pancreas, and the lesion location is also at least one of the lesion located in the body of the pancreas and the lesion located in the tail of the pancreas, a total pancreatectomy auxiliary decision is generated according to the second surgical procedure matching engine.

5. The system according to claim 3, wherein: The processor is further configured to perform the following steps: When the number of lesions is one, executing the first secondary node to determine the lesion property; when the lesion property is the first lesion type, executing the first tertiary node to calculate the output value of the first formula function; The first surgical procedure function is constructed based on the lesion parameters, and the first surgical procedure matching engine includes a first sub-engine, and an auxiliary decision of the resection surgical procedure corresponding to the lesion is generated based on the first sub-engine; the lesion parameters include at least one of the lesion location and the distance between the lesion and the blood vessel; the lesion location includes the lesion located in the head of the pancreas, the lesion located in the neck of the pancreas, the lesion located in the body of the pancreas or the lesion located in the tail of the pancreas; the distance between the lesion and the blood vessel includes at least one of the distance between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein and the distance between the lesion and the portal vein; the first surgical procedure matching sub-engine is used to characterize the mapping relationship between the output value of the first surgical procedure function and the resection surgical procedure.

6. The system according to claim 5, characterized in that The processor is further configured to perform the following steps: When the lesion location is the lesion located at the pancreatic head or the lesion located at the pancreatic neck, the lesion parameter is the lesion location, and the output value of the first surgical function is related to the lesion location; When the lesion is located in the head of the pancreas, generating a pancreaticoduodenectomy auxiliary decision according to the first sub-engine; When the lesion is located in the pancreatic neck, a combined pancreatic head and body resection is generated according to the first sub-engine.

7. The system according to claim 5, characterized in that The processor is further configured to perform the following steps: When the lesion is located in the pancreatic body or tail, the lesion parameters include the lesion location and the distance between the lesion and a blood vessel; when each of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is greater than a first threshold, generating an auxiliary decision for pancreatic body and tail resection according to the first sub-engine; When the lesion location is that the lesion is located in the pancreatic body or the lesion is located in the pancreatic tail, the lesion parameters include the lesion location and the distance between the lesion and the blood vessel. When any one of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is less than or equal to a first threshold, an auxiliary decision for extended pancreatic body and tail resection is generated according to the first sub-engine.

8. The system according to claim 3, wherein: The processor is further configured to perform the following steps: When the number of lesions is one, executing the first second-level node to determine the lesion property; when the lesion property is the second lesion type, executing the second third-level node to calculate the output value of the second formula function; The second surgical procedure function is constructed based on the lesion parameters, and the first surgical procedure matching engine includes a second sub-engine, and an auxiliary decision of the resection surgical procedure corresponding to the lesion is generated based on the second sub-engine; the lesion parameters include at least one of the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; the lesion location includes the lesion located in the head of the pancreas, the lesion located in the neck of the pancreas, the lesion located in the body of the pancreas, or the lesion located in the tail of the pancreas; the distance between the lesion and the blood vessel includes at least one of the distance between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein; the second sub-engine is used to characterize the mapping relationship between the output value of the second surgical procedure function and the resection surgical procedure.

9. The system according to claim 8, characterized in that The processor is further configured to perform the following steps: When the distance between the lesion and the pancreatic duct and the distance between the lesion and the bile duct are both greater than a second threshold, the lesion parameters are the distance between the lesion and the pancreatic duct and the distance between the lesion and the bile duct, and a local resection auxiliary decision is generated according to the second sub-engine; When the lesion location is that the lesion is located in the pancreatic head, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, and the distance between the lesion and the bile duct; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, generating an auxiliary decision for pancreatic head resection with duodenum preservation according to the second sub-engine; When the lesion location is that the lesion is located in the pancreatic neck, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, and when each of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, and the distance between the lesion and the portal vein is greater than the first threshold, generating an auxiliary decision for mid-segment pancreatectomy with duodenum preservation according to the second sub-engine; When the lesion location is that the lesion is located in the pancreatic neck, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, the distance between the lesion and the bile duct, and the distance between the lesion and the blood vessel; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, and when any of the distances between the lesion and the splenic artery, the distance between the lesion and the superior mesenteric artery, the distance between the lesion and the splenic vein, the distance between the lesion and the superior mesenteric vein, or the distance between the lesion and the portal vein is less than or equal to a first threshold, an auxiliary decision for combined pancreatic head and body resection is generated according to the second sub-engine; When the lesion location is the lesion located in the pancreatic body or the lesion located in the pancreatic tail, the lesion parameters are the lesion location, the distance between the lesion and the pancreatic duct, and the distance between the lesion and the bile duct; when the distance between the lesion and the pancreatic duct or the distance between the lesion and the bile duct is less than or equal to a second threshold, an auxiliary decision for spleen-preserving pancreatectomy is generated according to the second sub-engine.

10. The system according to claim 3, wherein: The lesion location is determined by the processor executing the following steps: Based on the three-dimensional medical image of the pancreas, skeletonization and extraction are performed on the pancreas in the three-dimensional medical image of the pancreas to obtain skeleton center points of the pancreas, the skeleton center points are sorted according to a first preset rule to form a skeleton center point set; and the skeleton center point set is divided into a first subset, a second subset, a third subset, and a fourth subset according to a second preset rule; Obtaining the center of gravity of the lesion, calculating the distance between the center of gravity of the lesion and each skeleton center point in the skeleton center point set one by one, and determining the skeleton center point closest to the center of gravity of the lesion as the center point of the lesion position; When the center point of the lesion location is located in the first subset, the lesion location is that the lesion is located in the head of the pancreas; when the center point of the lesion location is located in the second subset, the lesion location is that the lesion is located in the neck of the pancreas; when the center point of the lesion location is located in the third subset, the lesion location is that the lesion is located in the body of the pancreas; when the center point of the lesion location is located in the fourth subset, the lesion location is that the lesion is located in the body of the pancreas.

11. A method for assisting decision-making in pancreatic lesion resection surgery, characterized in that: Acquiring a three-dimensional medical image of the pancreas, wherein the three-dimensional medical image of the pancreas includes a lesion; identifying the number of lesions and the nature of the lesions, where the number of lesions is one or more, and the nature of the lesions includes at least one of a first lesion type and a second lesion type; A decision tree model is constructed according to the number of lesions, the nature of the lesions and the surgical procedure function to generate an auxiliary decision for the resection surgical procedure corresponding to the lesions.

12. A device for assisting decision-making in pancreatic lesion resection, characterized in that: The device comprises: A medical image acquisition module, configured to acquire a three-dimensional medical image of the pancreas, wherein the three-dimensional medical image of the pancreas includes a lesion; a lesion identification module, configured to identify the number and nature of lesions, wherein the number of lesions is one or more, and the nature of lesions includes at least one of a first lesion type and a second lesion type; The auxiliary decision module is used to construct a decision tree model based on the number of lesions, the nature of the lesions and the surgical procedure function to generate an auxiliary decision for the resection procedure corresponding to the lesion.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to claim 11 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 11 are implemented.

Images