Method and apparatus for training diagnosis model

Abstract

The present application discloses a method and apparatus for training a diagnosis model. The diagnosis model is used for diagnosing extrapancreatic perineural invasion (EPNI). The method comprises: segmenting multiple layers of CT images of multiple pancreatic cancer patients, to obtain three-dimensional initial images comprising tumors and multiple blood vessels; expanding each of the multiple blood vessels in the three-dimensional initial images by 1 to n pixels, to obtain n expanded three-dimensional images; forming n+1 candidate models by using the three-dimensional initial images and the n expanded three-dimensional images; inputting a pre-acquired training data set into each of the n+1 candidate models for training, to obtain multiple diagnosis parameters of each trained candidate model; and on the basis of the multiple diagnosis parameters of each candidate model, selecting a candidate model from the n+1 candidate models to be the diagnosis model. The present invention can accurately diagnose EPNI.

Description

Method and device for training diagnostic model

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on March 8, 2024, with application number 202410265980.1 and application name “Method and Apparatus for Training Diagnostic Models”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of artificial intelligence, and in particular to a method for training a diagnostic model, a method, apparatus, medium, electronic device, and computer program product for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer. Background Art

[0003] Pancreatic ductal adencarcinoma (PDAC) is a highly lethal malignancy that will become the second leading cause of cancer-related deaths worldwide by 2030. Surgical resection is the mainstay of curative treatment for PDAC. Although surgical procedures for PDAC have been highly developed, the prognosis for PDAC remains poor. Postoperative recurrence remains a major obstacle to improving survival, with a 5-year recurrence rate as high as 70% even in patients with small PDAC (≤2 cm). One of the main reasons for this is peripancreatic nerve invasion (EPNI), which is observed in 52.2%-75.8% of surgical specimens and is a key factor for early recurrence and poor prognosis.

[0004] The peripancreatic nerve plexus is often intertwined with major blood vessels around the pancreas, such as the celiac artery (CA) and its branches, the portal vein (PV), the superior mesenteric artery (SMA), and the splenic artery (SA), and is a common pathway for tumor spread. This complexity poses a challenge to the complete resection of the involved nerve plexus. If the involved nerves are not removed, the surgical margin is positive, and the patient is prone to recurrence and metastasis after surgery, with a very poor prognosis. If the nerve plexus is blindly removed in its entirety, it will lead to serious complications such as diarrhea and malnutrition, and the patient's quality of life will be low after surgery. Therefore, accurate preoperative diagnosis of EPNI is crucial for formulating surgical strategies, reducing postoperative recurrence, and improving long-term survival rates.

[0005] Currently, thin-slice high-resolution CT is the most commonly used assessment method for pancreatic cancer and has been used to evaluate EPIN. Studies have shown that low-density tumor contact with peripancreatic vessels or the presence of soft tissue density around the pancreatic vessels are reliable imaging features of EPIN. However, the diagnosis of EPIN is limited to subjective observations of anatomy and morphology, lacking objective criteria. Furthermore, perivascular fibrosis and inflammation are very similar to EPIN and difficult to distinguish, resulting in a diagnostic specificity of only 64.7%. These shortcomings limit the clinical application of CT in the assessment of EPIN. An accurate, objective, and fully automated EPIN diagnostic model is currently urgently needed. Summary of the Invention

[0006] The embodiments of the present application provide a method for training a diagnostic model, a method, an apparatus, a medium, an electronic device, and a computer program product for diagnosing EPNI (peripancreatic nerve invasion) of pancreatic cancer.

[0007] In a first aspect, embodiments of the present application provide a method for training a diagnostic model for an electronic device, wherein the diagnostic model is used to diagnose peripancreatic nerve invasion (EPNI) of pancreatic cancer, the method comprising:

[0008] From multiple CT images of multiple pancreatic cancer patients, a 3D initial image containing the tumor and multiple blood vessels is obtained by segmentation;

[0009] amplifying 1 to n pixels of each of the plurality of blood vessels in the three-dimensional initial image to obtain n amplified three-dimensional images;

[0010] Using the three-dimensional initial image and the n augmented three-dimensional images, forming n+1 candidate models;

[0011] Inputting the pre-acquired training data set into n+1 candidate models for training respectively, and obtaining multiple diagnostic parameters of each candidate model after training;

[0012] Based on multiple diagnostic parameters of each candidate model, a candidate model is selected from the n+1 candidate models as the diagnostic model.

[0013] In a possible implementation of the first aspect, segmenting multiple CT images of multiple pancreatic cancer patients to obtain a three-dimensional initial image containing a tumor and multiple blood vessels includes:

[0014] Acquire a region of interest from the plurality of CT images, wherein the region of interest includes a tumor and a plurality of blood vessels around the pancreas;

[0015] The region of interest is segmented from the multiple CT images using a segmentation model to obtain a three-dimensional initial image containing the tumor and the multiple blood vessels.

[0016] In a possible implementation of the first aspect, the training dataset includes historical CT images and historical contact labels of multiple pancreatic cancer patients, wherein the historical contact labels are used to indicate whether the EPNI exists in the corresponding historical CT images, wherein the presence of the EPNI is determined based on whether the tumor is in contact with the blood vessel.

[0017] The pre-acquired training data set is input into n+1 candidate models respectively to obtain multiple diagnostic parameters of each candidate model after training, including, for each candidate model:

[0018] Input multiple historical CT images and multiple historical contact labels for training to obtain a trained candidate model;

[0019] Input a plurality of historical CT images into the trained candidate model respectively, and output a current contact label indicating whether the EPNI exists in each historical CT image.

[0020] Based on the comparison between the multiple current contact labels and the multiple historical contact labels, multiple diagnostic parameters of the trained candidate model are obtained.

[0021] In a possible implementation of the first aspect, n+1 candidate models are sorted based on multiple diagnostic parameters, so as to select the diagnostic model from the n+1 candidate models.

[0022] In a possible implementation of the first aspect, in each of the augmented three-dimensional images, the augmented pixels are used to represent nerve plexuses on the blood vessel wall.

[0023] In a second aspect, a method for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer is provided for use in an electronic device, the method comprising:

[0024] Acquire a CT image of the patient to be tested;

[0025] The CT image is input into the diagnostic model obtained according to the method of the first aspect to output a contact label, wherein the contact label indicates whether the EPNI exists in the CT image.

[0026] In a third aspect, an embodiment of the present application provides a device for training a diagnostic model, wherein the diagnostic model is used to diagnose pancreatic peripancreatic nerve invasion (EPNI) of pancreatic cancer, and the device comprises:

[0027] A segmentation unit, which segments multiple multi-slice CT images of pancreatic cancer patients to obtain a three-dimensional initial image containing the tumor and multiple blood vessels;

[0028] an amplification unit, for amplifying 1 to n pixels of each of the plurality of blood vessels in the three-dimensional initial image, to obtain n amplified three-dimensional images;

[0029] a forming unit, forming n+1 candidate models using the three-dimensional initial image and the n augmented three-dimensional images;

[0030] A training unit, which inputs the pre-acquired training data set into n+1 candidate models for training, and obtains multiple diagnostic parameters of each candidate model after training;

[0031] The selection unit selects one candidate model from the n+1 candidate models as the diagnosis model based on multiple diagnosis parameters of each candidate model.

[0032] In a fourth aspect, an embodiment of the present invention provides a device for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer, the device comprising:

[0033] An acquisition unit, for acquiring a CT image of a patient to be detected;

[0034] a diagnosis unit that inputs the CT image into a diagnosis model to output a contact tag, wherein the contact tag indicates whether the EPNI exists in the CT image,

[0035] Wherein, the diagnostic model is obtained by training according to the device described in the third aspect.

[0036] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, causes the computer to execute the method for training a diagnostic model in the first aspect or the method for diagnosing EPNI (peripancreatic nerve invasion) of pancreatic cancer in the second aspect.

[0037] In a sixth aspect, an embodiment of the present application provides an electronic device comprising: one or more processors; one or more memories; the one or more memories storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device executes the method for training a diagnostic model in the first aspect or the method for diagnosing EPNI of pancreatic cancer in the second aspect.

[0038] In a seventh aspect, an embodiment of the present application provides a computer program product comprising computer executable instructions, which are executed by a processor to implement the method for training a diagnostic model in the first aspect or the method for diagnosing pancreatic peripancreatic nerve invasion (EPNI) of pancreatic cancer in the second aspect.

[0039] In this invention, the pancreatic perivascular space, due to its proximity to the neural plexus, can serve as a neural plexus. To capture this perivascular space, a deep learning approach is employed to segment the vessels and expand the vascular boundaries outward by 1 to 5 pixels to accurately delineate the perivascular space, thereby enabling quantification of tumor contact within this region. By selecting the optimal candidate model from multiple candidate models depicting the perivascular space as the diagnostic model, EPNI can be accurately diagnosed, providing an effective assessment for early clinical decision-making. The diagnostic model of this invention is simple, accurate, objective, repeatable, and easy to implement. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] FIG1 is a flowchart showing a method for training a diagnostic model according to an embodiment of the present application;

[0041] FIG2 is a flowchart showing a method for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer according to an embodiment of the present application;

[0042] FIG3 shows a structural diagram of an apparatus for training a diagnostic model according to an embodiment of the present application;

[0043] FIG4 shows a structural diagram of a device for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer according to an embodiment of the present application;

[0044] FIG5 shows a diagram of a three-dimensional initial image and an augmented three-dimensional image according to an embodiment of the present application;

[0045] FIG6 shows a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] The illustrative embodiments of the present application include, but are not limited to, methods for training diagnostic models, methods, devices, media, electronic devices, and computer program products for diagnosing pancreatic cancer peripancreatic nerve invasion (EPNI).

[0047] As research progresses, it is clear that EPNI is driven by the interaction between cancer cells and the neural microenvironment, and the spatial gap between the neural plexus and the tumor represents a key area for nerve growth, tumor proliferation, and perineural invasion. Given the close anatomical relationship between the neural plexus and blood vessels, the perivascular space is an important area surrounding the neural plexus and perineural invasion sites. With the widespread application of deep learning (DL) segmentation tools, automatic segmentation of tumors and blood vessels has become a feasible method. The present invention uses a DL algorithm to automatically segment the tumor and surrounding blood vessels, and then amplifies the vascular contours to depict the perivascular space. The interaction between the tumor and the perivascular space is then evaluated to simulate tumor infiltration into the neural plexus. This objective measurement, as the output of the final model, breaks the imaging limitations of traditional EPNI diagnosis and makes it possible to use EPNI to diagnose pancreatic cancer.

[0048] The embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

[0049] FIG1 shows a method for training a diagnostic model according to an embodiment of the present application, which is used in an electronic device. The diagnostic model is used to diagnose peripancreatic nerve invasion (EPNI) of pancreatic cancer.

[0050] In step S11, a 3D initial image containing a tumor and multiple blood vessels is obtained by segmenting multiple multi-slice CT images of pancreatic cancer patients. For example, a 3D initial image containing a tumor and multiple blood vessels is obtained by segmenting multiple multi-slice CT images of the pancreas during the enhanced portal venous phase of pancreatic cancer patients.

[0051] First, a region of interest (ROI) is acquired from multiple CT images. The ROI includes the tumor and multiple blood vessels surrounding the pancreas.

[0052] Specifically, 50 CT images of 50 pancreatic cancer patients were randomly selected. It is understood that a CT image is a three-dimensional image formed by multi-slice two-dimensional CT images. A professional (e.g., a radiologist) delineates a region of interest (ROI) from each slice of the two-dimensional CT image during the portal venous phase. The ROI includes the pancreatic tumor and the multiple blood vessels surrounding the pancreas. In other words, the tumor and the multiple blood vessels surrounding the pancreas are delineated from each slice of the two-dimensional CT image.

[0053] The pancreas is surrounded by 10 blood vessels, namely the proper hepatic artery (PHA), gastroduodenal artery (GDA), superior mesenteric vein to the first jejunal branch (SMV-JT), abdominal aorta (AA), common hepatic artery (CHA), celiac trunk (CA), portal vein (PV), splenic artery (SA), superior mesenteric artery (SMA) and inferior pancreaticoduodenal artery (IPDA).

[0054] Secondly, the segmentation model is used to segment the region of interest from multiple CT images to obtain a three-dimensional initial image containing the tumor and multiple blood vessels.

[0055] The segmentation model is, for example, 3D-UNET, which is a deep learning model for medical image processing and is particularly suitable for segmentation tasks in medical image processing.

[0056] 3D-UNET segments the tumor and the 10 blood vessels surrounding the pancreas outlined in the CT image, generating multiple segmentation masks. Each mask corresponds to a single layer of the 2D CT image. The segmentation process is to separate the tumor and blood vessels from each layer of the 2D CT image. The multiple 2D segmentation masks are then combined to form the initial 3D image (E0) that includes the blood vessels and tumor.

[0057] In step S12, the plurality of blood vessels in the three-dimensional initial image (E0) are respectively enlarged by 1 to n pixels to obtain n enlarged three-dimensional images, where n is an integer greater than or equal to 1, and preferably, n is less than or equal to 5.

[0058] In this embodiment, n is 5, for example. Using Python 3.7, for example, the blood vessels in the initial 3D image are expanded outward by 1 pixel, 2 pixels, 3 pixels, 4 pixels, and 5 pixels, respectively, thereby obtaining five expanded 3D images, namely, an expanded 3D image of 1 pixel (E1), an expanded 3D image of 2 pixels (E2), an expanded 3D image of 3 pixels (E3), an expanded 3D image of 4 pixels (E4), and an expanded 3D image of 5 pixels (E5), as shown in FIG5 .

[0059] It can be understood that in these augmented three-dimensional images, the augmented pixels can represent nerve plexuses on the blood vessel wall, that is, the augmented pixels can represent the spatial positions of nerves.

[0060] In step S13 , n+1 candidate models are formed using the 3D initial image and the n augmented 3D images.

[0061] In this embodiment, a three-dimensional initial image (also referred to as a non-augmented three-dimensional image) and five augmented three-dimensional images are included, and a corresponding candidate model is formed using each image. For example, the three-dimensional initial image is used as the parameter of the non-augmented candidate model (M0), E1 is used as the parameter of the augmented 1-pixel candidate model (M1), E2 is used as the parameter of the augmented 2-pixel candidate model (M2), E3 is used as the parameter of the augmented 3-pixel candidate model (M3), E4 is used as the parameter of the augmented 4-pixel candidate model (M4), and E5 is used as the parameter of the augmented 5-pixel candidate model (M5). In this way, six candidate models can be formed. The specific process of forming candidate models using three-dimensional images is well known and will not be described in detail here.

[0062] It is understood that the candidate model is an artificial intelligence (AI) model.

[0063] In step S14, the pre-acquired training data set is input into n+1 candidate models for training respectively, and a plurality of diagnostic parameters of each candidate model after training are obtained.

[0064] The training dataset includes historical CT images and historical contact labels of multiple pancreatic cancer patients, where the historical contact labels are used to indicate whether EPNI exists in the corresponding historical CT images. The presence of EPNI is determined based on whether the tumor is in contact with a blood vessel.

[0065] Specifically, for each of the six candidate models, multiple historical CT images and multiple historical contact labels are input for training to obtain a trained candidate model. The specific process of training the candidate models is similar to that in the prior art and will not be described in detail here. It will be appreciated that the trained candidate models can be validated using a pre-acquired validation dataset.

[0066] After obtaining the six candidate models after training, it is necessary to select the best candidate model from them. The specific selection process is as follows.

[0067] First, multiple historical CT images are input into the trained six candidate models respectively, and the current contact label indicating whether EPNI exists in each historical CT image is output.

[0068] It can be understood that for each trained candidate model, the input is the historical CT image and the output is the corresponding current contact label.

[0069] It can be understood that the contact label indicates whether the tumor and the blood vessel are in contact. When they are in contact, the contact label indicates EPNI positive, indicating the presence of EPNI; when they are not in contact, the contact label indicates EPNI negative, indicating the absence of EPNI.

[0070] Secondly, based on the comparison of multiple current contact labels and multiple historical contact labels, multiple diagnostic parameters of the trained candidate model are obtained.

[0071] Specifically, for each trained candidate model, after inputting multiple historical CT images, multiple corresponding current contact labels are output. Based on the comparison between these current contact labels and these historical contact labels, multiple diagnostic parameters of the candidate model can be obtained.

[0072] To evaluate each candidate model, a receiver operating characteristic (ROC) curve was drawn based on these current exposure labels and these historical exposure labels. Multiple diagnostic parameters can be calculated from the ROC curve, including area under the curve (AUC), sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV).

[0073] It can be understood that for each trained candidate model, there are 6 diagnostic parameters mentioned above.

[0074] In step S15 , based on the multiple diagnostic parameters of each candidate model, one candidate model is selected from the six candidate models as a diagnostic model.

[0075] Based on multiple diagnostic parameters, the six candidate models are ranked so as to select a diagnostic model from the six candidate models.

[0076] For example, based on AUC, the six candidate models are ranked, and the first one is, for example, the trained amplified 1-pixel candidate model (M1). Thus, the trained M1 is selected as the final diagnosis model.

[0077] It is understandable that the six candidate models may also be ranked based on other diagnostic parameters without limitation. The purpose of the selection is to select the best one from the six candidate models as the diagnostic model.

[0078] It can be understood that the diagnostic model accurately locates the spatial position of the extravascular nerves, so it can accurately determine whether the tumor is in contact with the extravascular nerves, thereby accurately diagnosing EPNI.

[0079] Figure 2 shows a method for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer according to an embodiment of the present invention, which is used in an electronic device. As shown in Figure 2 , in step S21 , a CT image of a patient to be tested is acquired.

[0080] In step S22, the CT image is fed into the diagnostic model developed using the method described in FIG1 to output a contact label. For example, the CT image is fed into the trained M1 to output a contact label. The output contact label indicates whether EPNI is present in the CT image.

[0081] Based on the contact signature, EPNI can be accurately diagnosed, which helps to adjust the scope of surgical resection, reduce postoperative recurrence, and improve long-term survival.

[0082] In this invention, the pancreatic perivascular space, due to its proximity to the neural plexus, can serve as a neural plexus. To capture this perivascular space, a deep learning approach is employed to segment the vessels and expand the vascular boundaries outward by 1 to 5 pixels to accurately delineate the perivascular space, thereby enabling quantification of tumor contact within this region. By selecting the optimal candidate model from multiple candidate models depicting the perivascular space as the diagnostic model, EPNI can be accurately diagnosed, providing an effective assessment for early clinical decision-making. The diagnostic model of this invention is simple, accurate, objective, repeatable, and easy to implement.

[0083] The present invention provides an apparatus for training a diagnostic model for diagnosing pancreatic peripancreatic nerve invasion (EPNI) caused by pancreatic cancer. As shown in FIG3 , apparatus 30 includes: a segmentation unit 301 for obtaining a three-dimensional initial image containing a tumor and multiple blood vessels from multiple CT images of multiple pancreatic cancer patients; an amplification unit 302 for amplifying the multiple blood vessels in the three-dimensional initial image by 1 to n pixels, respectively, to obtain n amplified three-dimensional images; a formation unit 303 for forming n+1 candidate models using the three-dimensional initial image and the n amplified three-dimensional images; a training unit 304 for inputting a pre-acquired training dataset into each of the n+1 candidate models for training, thereby obtaining multiple diagnostic parameters for each trained candidate model; and a selection unit 305 for selecting a candidate model from the n+1 candidate models as the diagnostic model based on the multiple diagnostic parameters of each candidate model.

[0084] It can be understood that the segmentation unit 301, the amplification unit 302, the formation unit 303, the training unit 304, and the selection unit 305 can be implemented by the processor 102 having the functions of these modules or units in the electronic device 100 in Figure 6.

[0085] The present invention also provides a device for diagnosing peripancreatic nerve invasion (EPNI). As shown in Figure 4 , device 40 includes an acquisition unit 401 for acquiring a CT image of the patient to be examined; and a diagnosis unit 402 for inputting the CT image into a diagnostic model to output a contact label indicating whether the EPNI is present in the CT image. The diagnostic model is trained using device 30 shown in Figure 3 .

[0086] It is understandable that the acquisition unit 401 and the diagnosis unit 402 can be implemented by the processor 102 having the functions of these modules or units in the electronic device 100 in FIG. 6 .

[0087] The present invention also provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed on a computer, the computer is enabled to execute the method shown in FIG. 1 or FIG. 2 .

[0088] The present invention further provides a computer program product, comprising computer executable instructions, where the instructions are executed by the processor 102 to implement the method shown in FIG. 1 or FIG. 2 .

[0089] Reference is now made to Figure 6, which schematically illustrates an example electronic device 1400 according to an embodiment of the present invention. In one embodiment, the system 1400 may include one or more processors 1404, system control logic 1408 coupled to at least one of the processors 1404, system memory 1412 coupled to the system control logic 1408, non-volatile memory (NVM) 1416 coupled to the system control logic 1408, and a network interface 1420 coupled to the system control logic 1408.

[0090] In some embodiments, processor 1404 may include one or more single-core or multi-core processors. In some embodiments, processor 1404 may include any combination of general-purpose processors and specialized processors (e.g., graphics processors, application processors, baseband processors, etc.). In embodiments where system 1400 employs an eNB (Evolved Node B) 101 or a RAN (Radio Access Network) controller 102, processor 1404 may be configured to execute various embodiments, such as the embodiment shown in FIG2 .

[0091] In some embodiments, system control logic 1408 may include any suitable interface controller to provide any suitable interface to at least one of processors 1404 and / or any suitable device or component in communication with system control logic 1408 .

[0092] In some embodiments, the system control logic 1408 may include one or more memory controllers to provide an interface to the system memory 1412. The system memory 1412 may be used to load and store data and / or instructions. In some embodiments, the memory 1412 of the system 1400 may include any suitable volatile memory, such as a suitable dynamic random access memory (DRAM).

[0093] NVM / memory 1416 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, NVM / memory 1416 may include any suitable non-volatile memory such as flash memory and / or any suitable non-volatile storage device, such as at least one of an HDD (Hard Disk Drive), a CD (Compact Disc) drive, and a DVD (Digital Versatile Disc) drive.

[0094] NVM / storage 1416 may comprise a portion of the storage resources on the device on which system 1400 is installed, or it may be accessible to the device but not necessarily be part of the device. For example, NVM / storage 1416 may be accessed over a network via network interface 1420 .

[0095] In particular, system memory 1412 and NVM / storage 1416 may include, respectively, a temporary copy and a permanent copy of instructions 1424. Instructions 1424 may include instructions that, when executed by at least one of processors 1404, cause electronic device 1400 to implement the method illustrated in FIG1 . In some embodiments, instructions 1424, hardware, firmware, and / or software components thereof may additionally or alternatively reside in system control logic 1408, network interface 1420, and / or processor 1404.

[0096] The network interface 1420 may include a transceiver for providing a radio interface for the system 1400, thereby communicating with any other suitable devices (such as a front-end module, an antenna, etc.) via one or more networks. In some embodiments, the network interface 1420 may be integrated with other components of the system 1400. For example, the network interface 1420 may be integrated with at least one of the processor 1404, the system memory 1412, the NVM / storage 1416, and a firmware device (not shown) having instructions. When at least one of the processors 1404 executes the instructions, the electronic device 1400 implements the method shown in FIG1 .

[0097] The network interface 1420 may further include any suitable hardware and / or firmware to provide a multiple-input multiple-output radio interface. For example, the network interface 1420 may be a network adapter, a wireless network adapter, a telephone modem, and / or a wireless modem.

[0098] In one embodiment, at least one of the processors 1404 may be packaged together with logic for one or more controllers of the system control logic 1408 to form a system-in-package (SiP). In one embodiment, at least one of the processors 1404 may be integrated on the same die with logic for one or more controllers of the system control logic 1408 to form a system-on-chip (SoC).

[0099] Electronic device 1400 may further include an input / output (I / O) device 1432. I / O device 1432 may include a user interface that enables a user to interact with electronic device 1400; peripheral component interfaces may also be designed to enable peripheral components to interact with electronic device 1400. In some embodiments, electronic device 1400 may further include a sensor for determining at least one of environmental conditions and location information related to electronic device 1400.

[0100] In some embodiments, the user interface may include, but is not limited to, a display (e.g., an LCD display, a touch screen display, etc.), a speaker, a microphone, one or more cameras (e.g., a still image camera and / or a video camera), a flashlight (e.g., an LED flash), and a keyboard.

[0101] The various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or a combination of these implementation methods. The embodiments of the present application can be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0102] Program code can be applied to input instructions to perform the functions described herein and generate output information. The output information can be applied to one or more output devices in a known manner. For purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0103] Program code can be implemented with a high-level programming language or an object-oriented programming language to communicate with the processing system. Where necessary, program code can also be implemented in assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0104] In some cases, the disclosed embodiments can be implemented in hardware, firmware, software or any combination thereof. The disclosed embodiments can also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which can be read and executed by one or more processors. For example, instructions can be distributed over a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer), including but not limited to, floppy disks, optical disks, optical discs, read-only memories (CD-ROMs), magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memories, or tangible machine-readable memories for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in electrical, optical, acoustic or other forms of propagation signals. Therefore, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a form readable by a machine (e.g., a computer).

[0105] In the accompanying drawings, some structural or method features may be shown in a particular arrangement and / or order. However, it should be understood that such a particular arrangement and / or order may not be required. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of a structural or method feature in a particular figure does not imply that such feature is required in all embodiments, and in some embodiments, such features may not be included or may be combined with other features.

[0106] It should be noted that the units / modules mentioned in the various device embodiments of the present application are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems raised by this application. In addition, in order to highlight the innovative part of this application, the above-mentioned device embodiments of this application do not introduce units / modules that are not closely related to solving the technical problems raised by this application. This does not mean that other units / modules do not exist in the above-mentioned device embodiments.

[0107] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "including a" does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0108] Although the present application has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the application.

Claims

1. A method for training a diagnostic model for an electronic device, characterized in that: The diagnostic model is used to diagnose pancreatic peripancreatic nerve invasion (EPNI) of pancreatic cancer, and the method comprises: From multiple CT images of multiple pancreatic cancer patients, a 3D initial image containing the tumor and multiple blood vessels is obtained by segmentation; amplifying 1 to n pixels of each of the plurality of blood vessels in the three-dimensional initial image to obtain n amplified three-dimensional images; Using the three-dimensional initial image and the n augmented three-dimensional images, forming n+1 candidate models; Inputting the pre-acquired training data set into n+1 candidate models for training respectively, and obtaining multiple diagnostic parameters of each candidate model after training; Based on multiple diagnostic parameters of each candidate model, a candidate model is selected from the n+1 candidate models as the diagnostic model.

2. The method according to claim 1, characterized in that The 3D initial images containing tumors and multiple blood vessels are segmented from multiple CT images of multiple pancreatic cancer patients, including: Acquire a region of interest from the plurality of CT images, wherein the region of interest includes a tumor and a plurality of blood vessels around the pancreas; The region of interest is segmented from the multiple CT images using a segmentation model to obtain a three-dimensional initial image containing the tumor and the multiple blood vessels.

3. The method according to claim 1, characterized in that The training dataset includes historical CT images and historical contact labels of multiple pancreatic cancer patients, wherein the historical contact labels are used to indicate whether the EPNI exists in the corresponding historical CT images, wherein the presence of the EPNI is determined based on whether the tumor is in contact with the blood vessel. The pre-acquired training data set is input into n+1 candidate models respectively to obtain multiple diagnostic parameters of each candidate model after training, including, for each candidate model: Input multiple historical CT images and multiple historical contact labels for training to obtain a trained candidate model; Input a plurality of historical CT images into the trained candidate model respectively, and output a current contact label indicating whether the EPNI exists in each historical CT image. Based on the comparison between the multiple current contact labels and the multiple historical contact labels, multiple diagnostic parameters of the trained candidate model are obtained.

4. The method according to claim 3, characterized in that Based on a plurality of diagnosis parameters, the n+1 candidate models are sorted so as to select the diagnosis model from the n+1 candidate models.

5. The method according to any one of claims 1 to 4, characterized in that In each of the augmented three-dimensional images, augmented pixels are used to represent nerve plexuses on the blood vessel wall.

6. A method for diagnosing pancreatic peripancreatic nerve invasion (EPNI) of pancreatic cancer, for use in electronic equipment, characterized in that: The method comprises: Acquire a CT image of the patient to be tested; The CT image is input into the diagnostic model obtained by the method according to any one of claims 1 to 5 to output a contact label, wherein the contact label indicates whether the EPNI exists in the CT image.

7. A device for training a diagnostic model, characterized in that: The diagnostic model is used to diagnose pancreatic cancer peripancreatic nerve invasion (EPNI), and the device comprises: A segmentation unit, which segments multiple CT images of multiple pancreatic cancer patients to obtain a three-dimensional initial image containing a tumor and multiple blood vessels; an amplification unit, for amplifying 1 to n pixels of each of the plurality of blood vessels in the three-dimensional initial image, to obtain n amplified three-dimensional images; a forming unit, forming n+1 candidate models using the three-dimensional initial image and the n augmented three-dimensional images; A training unit, which inputs the pre-acquired training data set into n+1 candidate models for training, and obtains multiple diagnostic parameters of each candidate model after training; The selection unit selects one candidate model from the n+1 candidate models as the diagnosis model based on multiple diagnosis parameters of each candidate model.

8. A device for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer, characterized by: The device comprises: An acquisition unit, for acquiring a CT image of a patient to be detected; a diagnosis unit that inputs the CT image into a diagnosis model to output a contact tag, wherein the contact tag indicates whether the EPNI exists in the CT image, Wherein, the diagnostic model is trained according to the device according to claim 7.

9. A computer-readable storage medium, characterized in that The storage medium stores instructions, which, when executed on a computer, enable the computer to execute the method for training a diagnostic model according to any one of claims 1 to 5 or the method for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer according to claim 6.

10. An electronic device, characterized in that: include: one or more processors; One or more memories; the one or more memories store one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device executes the method for training a diagnostic model according to any one of claims 1 to 5 or the method for diagnosing pancreatic cancer peripancreatic nerve invasion (EPNI) according to claim 6.

11. A computer program product comprising computer executable instructions, characterized in that: The instructions are executed by a processor to implement the method for training a diagnostic model according to any one of claims 1 to 5 or the method for diagnosing peripancreatic nerve invasion (EPNI) of pancreatic cancer according to claim 6.

Images