WO2021151307A1 - 基于病理切片扫描和分析一体化方法、装置、设备及介质 - Google Patents

基于病理切片扫描和分析一体化方法、装置、设备及介质 Download PDF

Info

Publication number
WO2021151307A1
WO2021151307A1 PCT/CN2020/119104 CN2020119104W WO2021151307A1 WO 2021151307 A1 WO2021151307 A1 WO 2021151307A1 CN 2020119104 W CN2020119104 W CN 2020119104W WO 2021151307 A1 WO2021151307 A1 WO 2021151307A1
Authority
WO
WIPO (PCT)
Prior art keywords
pathological
digital
slice image
scanning
pathology
Prior art date
Application number
PCT/CN2020/119104
Other languages
English (en)
French (fr)
Inventor
郭冰雪
吕传峰
初晓
王季勇
楼文杰
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2021151307A1 publication Critical patent/WO2021151307A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00ICT specially adapted for the handling or processing of medical images
    • G16H30/20ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10072Tomographic images
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20084Artificial neural networks [ANN]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing

Definitions

  • This application relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device, and computer-readable storage medium based on pathological slice-based scanning and analysis integration.
  • Pathological biopsy is the gold standard for clinical diagnosis. It is used in a large number of clinical work and scientific research. Based on the results of pathological biopsy, it can help doctors make better pathological diagnosis.
  • the inspection of pathological slices mainly involves converting the pathological slice to be inspected into a digital pathological image through a pathological scanning system, and then using an intelligent analysis algorithm to analyze the pathological information of the digital pathological image.
  • the inventor realizes that the above-mentioned method has the following drawbacks: it is impossible to perform intelligent analysis of digital pathological images in real time based on the results of digitization of pathological slices, that is, it is necessary to export the digital pathological images before performing intelligent analysis of digital pathological images, so that large batches cannot be processed.
  • the pathological biopsy will affect the efficiency of pathological biopsy.
  • the present application provides a method, device, electronic equipment, and computer-readable storage medium based on integrated scanning and analysis of pathological slices.
  • This application provides an integrated method for scanning and analysis based on pathological slices, including:
  • pathological analysis is performed on each digital pathological slice image in the digital pathological slice image set to obtain a pathological analysis result of the digital pathological slice image;
  • Reading software is used to read and output the pathological scan analysis result of the digital pathological slice image.
  • the application also provides an integrated scanning and analysis device based on pathological slices, the device including:
  • the integration module is used to integrate a pre-built pathological scanning system and a pre-built pathological analysis system to obtain a pathological scanning analysis system;
  • the scanning module is configured to use the scanner in the pathological scanning analysis system to perform image scanning on the digital pathological slice set to generate a digital pathological slice image set;
  • the analysis module is configured to perform pathological analysis on each digital pathological slice image in the digital pathological slice image set based on the pathological analysis system of the pathological scanning analysis system to obtain the pathological analysis result of the digital pathological slice image;
  • the reading and output module is used for reading and outputting the pathological scan analysis result of the digital pathological slice image by using the reading software.
  • This application also provides an electronic device, which includes:
  • Memory storing at least one instruction
  • the processor executes the instructions stored in the memory to implement the following steps:
  • pathological analysis is performed on each digital pathological slice image in the digital pathological slice image set to obtain a pathological analysis result of the digital pathological slice image;
  • Reading software is used to read and output the pathological scan analysis result of the digital pathological slice image.
  • the present application also provides a computer-readable storage medium in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the following steps:
  • pathological analysis is performed on each digital pathological slice image in the digital pathological slice image set to obtain a pathological analysis result of the digital pathological slice image;
  • Reading software is used to read and output the pathological scan analysis result of the digital pathological slice image.
  • FIG. 1 is a schematic flow chart of the integrated scanning and analysis method based on pathological slices according to the first embodiment of this application;
  • step S3 is a schematic flowchart of step S3 of the integrated method for scanning and analysis based on pathological slices provided in FIG. 1 in the first embodiment of the application;
  • FIG. 4 is a schematic diagram of modules of an integrated device for scanning and analysis based on pathological slices according to the first embodiment of the application;
  • FIG. 5 is a schematic diagram of the internal structure of an electronic device that implements an integrated method for scanning and analyzing pathological slices according to the first embodiment of the application;
  • the execution subject of the integrated pathological slice-based scanning and analysis method provided in the embodiments of the present application includes, but is not limited to, at least one of the electronic devices that can be configured to execute the method provided in the embodiments of the present application, such as a server and a terminal.
  • the integrated method of scanning and analysis based on pathological slices can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform.
  • the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.
  • This application provides an integrated method of scanning and analysis based on pathological slices.
  • FIG. 1 it is a schematic flowchart of an integrated method for scanning and analyzing pathological slices according to an embodiment of this application.
  • the integrated method of scanning and analysis based on pathological slices includes:
  • the pathology scanning system is obtained by a combination of software/hardware facilities, where the software facilities include, but are not limited to: image scanning software, image browsing software, image and data management software, etc.
  • the hardware facilities include, but are not limited to: scanners, slides, output devices, etc.
  • the pathological scanning system is used to convert pathological information existing in pathological slices into storable digital images, which can help doctors perform pathological diagnosis.
  • the creation of the pathology scanning system can use current relatively mature technology, which will not be further elaborated here.
  • this application integrates a preset pathological analysis system into the In the pathological scanning system, pathological analysis of the scanned digital images can be realized, so that the scanning and analysis of pathological slices can be integrated, which can help users perform pathological diagnosis more efficiently and quickly.
  • the preset pathological analysis system described in the embodiment of the present application includes: a residual network (resnet) and a region proposal network (region proposal network, RPN), wherein the resnet is used to analyze the pathological images subsequently scanned Perform feature extraction, and the RPN is used to generate a prediction frame of the pathological image after feature extraction and the corresponding pathological abnormality type.
  • a residual network resnet
  • region proposal network region proposal network
  • said integrating the constructed pathology analysis system into the pathology scanning system to obtain a pathology scanning analysis system includes:
  • the interface parameters of the pathology analysis system are configured to import the pathology analysis system into the pathology scanning system using a preset driver program according to the configured interface parameters of the pathology analysis system.
  • the preset driver is compiled and generated by the java programming language.
  • the digital pathological slice set is obtained by combining different digital pathological slices, and the digital pathological slice can characterize the pathological information contained in the pathological slice, for example, the digital pathological slice It can be: digital pathological slice of cervical cancer, digital pathological slice of tracheitis, digital pathological slice of pneumonia, etc.
  • the pathological section is made by selecting tissue cells of a certain size and using a histopathological method.
  • the digital pathological slice is generated by inputting the prepared pathological slice into the pathological scanning system constructed above.
  • the embodiment of the present application saves the digital pathological slice set to the slide of the pathological scanning analysis system, so as to realize subsequent mass digital pathology Efficient processing of segmentation.
  • using the scanner in the pathological scanning analysis system to perform image scanning on the digital pathological slice in the slide glass to generate the digital pathological slice image includes:
  • the digital pathological slices placed in the slides of the pathological scanning analysis system are transferred to the scanner, and the slides are observed through the objective lens in the scanner
  • Existing regional image focus on the regional image, generate the focal point of the regional image, determine the image generation function of the digital pathological slice in the slide according to the focal point, and generate the function according to the image
  • To generate a digital pathological slice image of the digital pathological slice in the slide glass and obtain the digital pathological slice image set according to the digital pathological slice image.
  • the above-mentioned digital pathological slice image set may also be stored in a node of a blockchain.
  • the first-in-first-out order means that the digital pathological slices stored on the slide glass are preferentially scanned for images, which can ensure the order of scanning of the digital pathological slices.
  • a currently known image focusing tool is used to focus the region image, for example, the Helicon Focus image focusing tool.
  • the pathological analysis system based on the pathological scan analysis system performs pathological analysis on each digital pathological slice image in the digital pathological slice image set to obtain a pathological analysis result of the digital pathological slice image.
  • the present application since the pathological analysis system has been integrated into the pathological scanning system in the above S1, the present application can implement pathological analysis on the generated digital pathological slice images at the same time.
  • the pathological analysis system based on the pathological scan analysis system performs pathological analysis on each digital pathological slice image in the digital pathological slice image set, and obtains the value of the digital pathological slice image.
  • Pathological analysis results including:
  • gamma correction is performed on the digital pathological slice image according to a preset gamma correction threshold.
  • the gamma correction threshold is 0.7.
  • the gamma correction is used to adjust the gray value in the image, that is, to adjust the too bright part of the image to a moderate gray level, and to adjust the dark part of the image to a suitable gray level, through the gamma correction
  • the gray value of the digital pathological slice image can be enhanced, so that the accuracy of pathological analysis of the subsequent digital pathological slice image can be improved.
  • the target digital pathological slice image is input to the feature extractor of the residual network to perform a convolution operation to generate the characteristic digital pathological slice image.
  • the calculation of the coordinate information and types of abnormal tissue cells in the characteristic digital pathological slice image by using the region generation network in the pathological analysis system includes:
  • S322. Use the region generation network in the pathology analysis system to calculate a second predicted coordinate frame of abnormal tissue cells in the first predicted digital pathological slice image area, and calculate the difference between the second predicted coordinate frame and the real coordinate frame. Second intersection ratio threshold, and filter out the second predicted coordinate frame whose second intersection ratio threshold is greater than the preset second threshold to obtain the initial second predicted coordinate frame, and generate the second predicted coordinate frame according to the initial second predicted coordinate frame 2. Predict the image area of digital pathology slices;
  • S324 According to the third predicted digital pathological slice image area, identify the coordinate information and category of the abnormal tissue cells of the characteristic digital pathological slice image.
  • the true coordinate frame of the abnormal tissue cells in the digital pathological slice image is obtained through a large number of clinical experiments.
  • the preset first threshold value is 0.5
  • the preset second threshold value is 0.6
  • the preset third threshold value is 0.7.
  • the category of the abnormal tissue cell is identified according to the corresponding coordinate information, and the category may be a mildly abnormal tissue cell, a moderately abnormal tissue cell, a severely abnormal tissue cell, and the like.
  • the reading software is pathological image reading software.
  • the embodiment of this application integrates a pre-built pathological scanning system and a pre-built pathological analysis system to obtain a pathological scanning analysis system.
  • This application integrates the pathological analysis system into the pathological scanning system, and realizes the integration of the scanning and analysis of subsequent pathological slices.
  • the embodiment of the application obtains a digital pathological slice set, saves the digital pathological slice set to the slide of the pathology scanning analysis system, and uses the scanner in the pathology scanning analysis system to compare the slide
  • the digital pathological slices in the image scan are performed to generate digital pathological slice images, which can process a large number of pathological slices at high throughput without additional transmission and transfer processing of the scanning results; further, the embodiments of the present application are based on the pathological scanning analysis
  • the pathological analysis system of the system performs pathological analysis on each digital pathological slice image generated, and obtains the pathological analysis result of the digital pathological slice image, which realizes the intelligent analysis of pathological digital images while scanning the pathological slice;
  • the software reads and outputs the pathological scan analysis result of the digital pathological slice image. Therefore, the integrated scanning and analysis device based on pathological slices proposed in this application can realize the integration of scanning and analysis of pathological slices.
  • FIG. 4 it is a schematic diagram of modules of an integrated device for scanning and analyzing pathological slices according to an embodiment of the present application.
  • the integrated scanning and analysis device 100 based on pathological slices described in this application can be installed in an electronic device.
  • the integrated scanning and analysis device based on pathological slices may include an integration module 101, a scanning module 102, an analysis module 103, and a reading and analysis module 104.
  • the module described in this application can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.
  • each module/unit is as follows:
  • the integration module 101 is used to integrate a pre-built pathology scan system and a pre-built pathology analysis system to obtain a pathology scan analysis system.
  • the pathology scanning system is obtained by a combination of software/hardware facilities, where the software facilities include, but are not limited to: image scanning software, image browsing software, image and data management software, etc.
  • the hardware facilities include, but are not limited to: scanners, slides, output devices, etc.
  • the pathological scanning system is used to convert pathological information existing in pathological slices into storable digital images, which can help doctors perform pathological diagnosis.
  • the creation of the pathology scanning system can use current relatively mature technology, which will not be further elaborated here.
  • this application integrates a preset pathological analysis system into the In the pathological scanning system, pathological analysis of the scanned digital images can be realized, so that the scanning and analysis of pathological slices can be integrated, which can help users perform pathological diagnosis more efficiently and quickly.
  • the preset pathological analysis system described in the embodiment of the present application includes: a residual network (resnet) and a region proposal network (region proposal network, RPN), wherein the resnet is used to analyze the pathological images subsequently scanned Perform feature extraction, and the RPN is used to generate a prediction frame of the pathological image after feature extraction and the corresponding pathological abnormality type.
  • a residual network resnet
  • region proposal network region proposal network
  • said integrating the constructed pathology analysis system into the pathology scanning system to obtain a pathology scanning analysis system includes:
  • the preset driver is compiled and generated by the java programming language.
  • the scanning module 102 is configured to use a scanner in the pathology scanning analysis system to perform image scanning on a digital pathology slice set to generate a digital pathology slice image set.
  • the digital pathological slice set is obtained by combining different digital pathological slices, and the digital pathological slice can characterize the pathological information contained in the pathological slice, for example, the digital pathological slice It can be: digital pathological slice of cervical cancer, digital pathological slice of tracheitis, digital pathological slice of pneumonia, etc.
  • the pathological section is made by selecting tissue cells of a certain size and using a histopathological method.
  • the digital pathological slice is generated by inputting the prepared pathological slice into the pathological scanning system constructed above.
  • the embodiment of the present application saves the digital pathological slice set to the slide of the pathological scanning analysis system, so as to realize subsequent mass digital pathology Efficient processing of segmentation.
  • using the scanner in the pathological scanning analysis system to perform image scanning on the digital pathological slice in the slide glass to generate the digital pathological slice image includes:
  • the digital pathological slices placed on the slides of the pathology scanning analysis system are transferred to the scanner, and the presence of the slides in the slides is observed through the objective lens in the scanner Area image
  • the digital pathological slice image set is obtained according to the digital pathological slice image.
  • the above-mentioned digital pathological slice image set may also be stored in a node of a blockchain.
  • the first-in-first-out order means that the digital pathological slices stored on the slide glass are preferentially scanned for images, which can ensure the order of scanning of the digital pathological slices.
  • a currently known image focusing tool is used to focus the region image, for example, the Helicon Focus image focusing tool.
  • the analysis module 103 is configured to perform pathological analysis on each digital pathological slice image in the digital pathological slice image set based on the pathological analysis system of the pathological scanning analysis system to obtain the pathological analysis result of the digital pathological slice image .
  • the present application can implement pathological analysis on the generated digital pathological slice images at the same time.
  • the pathological analysis system based on the pathological scan analysis system performs pathological analysis on each digital pathological slice image in the digital pathological slice image set, and obtains the image of the digital pathological slice image.
  • Pathological analysis results including:
  • gamma correction is performed on the digital pathological slice image according to a preset gamma correction threshold.
  • the gamma correction threshold is 0.7.
  • the gamma correction is used to adjust the gray value in the image, that is, adjust the too bright part of the image to a moderate gray level, and adjust the dark part of the image to a suitable gray level, and the gamma correction
  • the gray value of the digital pathological slice image can be enhanced, so that the accuracy of pathological analysis of the subsequent digital pathological slice image can be improved.
  • the target digital pathological slice image is input to the feature extractor of the residual network to perform a convolution operation to generate the characteristic digital pathological slice image.
  • the calculation of the coordinate information and types of abnormal tissue cells in the characteristic digital pathological slice image by using the region generation network in the pathological analysis system includes:
  • S324 According to the third predicted digital pathological slice image area, identify the coordinate information and category of the abnormal tissue cells of the characteristic digital pathological slice image.
  • the true coordinate frame of the abnormal tissue cells in the digital pathological slice image is obtained through a large number of clinical experiments.
  • the preset first threshold value is 0.5
  • the preset second threshold value is 0.6
  • the preset third threshold value is 0.7.
  • the type of the abnormal tissue cell is identified according to the corresponding coordinate information, and the type may be a mildly abnormal tissue cell, a moderately abnormal tissue cell, a severely abnormal tissue cell, and the like.
  • the reading and outputting module 104 is used for reading and outputting the pathological scan analysis result of the digital pathological slice image using image reading software.
  • the reading software is pathological image reading software.
  • the embodiment of this application integrates a pre-built pathological scanning system and a pre-built pathological analysis system to obtain a pathological scanning analysis system, and obtains a pathological scanning analysis system.
  • This application integrates the pathological analysis system into the pathological scanning system to realize subsequent pathological slices.
  • the embodiment of the application obtains a digital pathological slice set, saves the digital pathological slice set to the slide of the pathological scan analysis system, and uses the pathology scan analysis system
  • the scanner performs image scanning on the digital pathological slices in the slides to generate digital pathological slice images, which can process a large number of pathological slices at high throughput without the need for additional transmission and transfer processing of the scanning results; further, the embodiment of the present application
  • pathology analysis is performed on each digital pathology slice image generated, and the pathology analysis result of the digital pathology slice image is obtained, which realizes the intelligent analysis of pathology while scanning the pathology slice.
  • Digital image read and output the pathological scan analysis result of the digital pathological slice image by using the reading software. Therefore, the integrated scanning and analysis device based on pathological slices proposed in this application can realize the integration of scanning and analysis of pathological slices.
  • FIG. 5 it is a schematic structural diagram of an electronic device for realizing the integrated method of scanning and analyzing pathological slices according to an embodiment of the present application.
  • the electronic device 1 may include a processor 10, a memory 11, and a bus, and may also include a computer program stored in the memory 11 and running on the processor 10, such as integrated scanning and analysis based on pathological slices. program.
  • the memory 11 includes at least one type of readable storage medium.
  • the computer-readable storage medium may be non-volatile or volatile.
  • the readable storage medium includes flash memory, mobile hard disk, and multimedia.
  • Card card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc.
  • the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, for example, a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), and a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash card (Flash Card), etc.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 can be used not only to store application software and various types of data installed in the electronic device 1, such as the code of an integrated program for scanning and analyzing pathological slices, etc., but also to temporarily store the output that has been output or will be output. data.
  • the processor 10 may be composed of integrated circuits in some embodiments, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions, including one or more Combinations of central processing unit (CPU), microprocessor, digital processing chip, graphics processor, and various control chips, etc.
  • the processor 10 is the control unit of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and runs or executes programs or modules stored in the memory 11 (for example, based on An integrated program for scanning and analyzing pathological slices, etc.), and calling data stored in the memory 11 to execute various functions of the electronic device 1 and processing data.
  • the bus may be a peripheral component interconnect standard (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • PCI peripheral component interconnect standard
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the bus is configured to implement connection and communication between the memory 11 and at least one processor 10 and the like.
  • FIG. 5 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 5 does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure. Components, or a combination of certain components, or different component arrangements.
  • the electronic device 1 may also include a power source (such as a battery) for supplying power to various components.
  • the power source may be logically connected to the at least one processor 10 through a power management device, thereby controlling power
  • the device implements functions such as charge management, discharge management, and power consumption management.
  • the power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators.
  • the electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
  • the electronic device 1 may also include a network interface.
  • the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • the electronic device 1 may also include a user interface.
  • the user interface may be a display (Display) and an input unit (such as a keyboard (Keyboard)).
  • the user interface may also be a standard wired interface or a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc.
  • the display can also be appropriately called a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visualized user interface.
  • the pathological slice-based scanning and analysis integrated program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can realize:
  • pathological analysis is performed on each digital pathological slice image in the digital pathological slice image set to obtain a pathological analysis result of the digital pathological slice image;
  • Reading software is used to read and output the pathological scan analysis result of the digital pathological slice image.
  • the above-mentioned audit data can also be stored in a node of a blockchain.
  • the integrated module/unit of the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) .
  • modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional modules in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional modules.
  • the blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Epidemiology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Primary Health Care (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

一种基于病理切片的扫描和分析一体化方法,涉及人工智能技术领域,可以实现病理切片的扫描和分析一体化。所述方法包括:集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统(S1);利用所述病理扫描系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集(S2);基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果(S3);利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果( S4)。所述方法还涉及区块链技术,所述数字病理切片图像集可部署于区块链节点中。

Description

基于病理切片扫描和分析一体化方法、装置、设备及介质
本申请要求于2020年06月09日提交中国专利局、申请号为CN 202010520678.8,发明名称为“基于病理切片扫描和分析一体化方法、装置、设备及介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能技术领域,尤其涉及一种基于病理切片的扫描和分析一体化的方法、装置、电子设备及计算机可读存储介质。
背景技术
病理切片检查是临床上诊断的金标准,应用于大量的临床工作及科学研究中,根据病理切片的检查结果可以帮助医生更好的进行病理诊断。
目前关于病理切片的检查主要是通过病理扫描系统将待检查的病理切片转换为数字化病理图像,再利用智能分析算法分析出所述数字化病理图像的病理信息。但是发明人意识到基于上述的方法存在如下弊端:无法根据病理切片数字化的结果实时进行数字化病理图像的智能分析,即需要导出数字化病理图像之后,再进行数字化病理图像智能分析,从而无法处理大批量的病理切片检查,进而会影响病理切片检查的检查效率。
因此,亟待需要一种实现病理切片扫描和分析一体化的方案。
发明内容
本申请提供一种基于病理切片的扫描和分析一体化的方法、装置、电子设备及计算机可读存储介质。
本申请提供的一种基于病理切片的扫描和分析一体化方法,包括:
集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
本申请还提供一种基于病理切片的扫描和分析一体化装置,所述装置包括:
集成模块,用于集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
扫描模块,用于利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
分析模块,用于基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
读取及输出模块,用于利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
本申请还提供一种电子设备,所述电子设备包括:
存储器,存储至少一个指令;及
处理器,执行所述存储器中存储的指令以实现如下步骤:
集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理 切片图像集;
基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
本申请还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有至少一个指令,所述至少一个指令被电子设备中的处理器执行以实现如下步骤:
集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
附图说明
图1为本申请第一实施例提供的基于病理切片的扫描和分析一体化方法的流程示意图;
图2为本申请第一实施例中图1提供的基于病理切片的扫描和分析一体化方法步骤S3的流程示意图;
图3为本申请第一实施例中图2提供的基于病理切片的扫描和分析一体化方法步骤S32的流程示意图;
图4为本申请第一实施例提供的基于病理切片的扫描和分析一体化装置的模块示意图;
图5为本申请第一实施例提供的实现基于病理切片的扫描和分析一体化方法的电子设备的内部结构示意图;
本申请目的的实现、功能特点及优点将整合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例提供的基于病理切片的扫描和分析一体化方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述基于病理切片的扫描和分析一体化方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
本申请提供一种基于病理切片的扫描和分析一体化的方法。参照图1所示,为本申请一实施例提供的基于病理切片的扫描和分析一体化方法的流程示意图。在本实施例中,所述基于病理切片的扫描和分析一体化的方法包括:
S1、集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统。
在本申请的至少一个实施例中,所述病理扫描系统是由软/硬件设施组合得到,其中,所述软件设施包括、但不限于:图像扫描软件、图像浏览软件以及图像和数据管理软件等,所述硬件设施包括、但不限于:扫描仪、载玻片以及输出设备等。所述病理扫描系统用于将病理切片中所存在的病理信息转换为可存储的数字化图像,可以帮助医生进行病理诊断。
一个可选实施例中,所述病理扫描系统的创建可选用当前较为成熟的技术,在此不做进一步阐述。
进一步地,由于所述病理扫描系统仅仅只能扫描出病理切片的数字化图像信息,并不能直接对所述数字化图像信息进行病理分析,因此,本申请将一个预设的病理分析系统集成至所述病理扫描系统中,以实现对扫描出的数字化图像进行病理分析,从而可以实现病理切片的扫描与分析一体化,进而可以帮助用户更加高效快速的进行病理诊断。
较佳地,本申请实施例所述预设的病理分析系统包括:残差网络(resnet)和区域生成网络(region proposal network,RPN),其中,所述resnet用于对后续扫描出的病理图像进行特征提取,所述RPN用于生成特征提取后的病理图像的预测框和对应病理异常类型。
一个可选实施例中,所述将构建的病理分析系统集成至所述病理扫描系统中,得到病理扫描分析系统,包括:
获取所述病理扫描系统中扫描仪的API(Application Programming Interface)接口参数,根据所述API接口参数,查询所述扫描仪的外部系统连接配置文件,根据所述外部系统连接配置文件,配置所述病理分析系统的接口参数,根据配置后的所述病理分析系统的接口参数,利用预设驱动程序将所述病理分析系统导入至所述病理扫描系统中。
可选的,所述预设的驱动程序通过java编程语言进行编译生成。
S2、利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集。
在本申请的至少一个实施例中,所述数字病理切片集是由不同的数字病理切片进行组合得到,所述数字病理切片可以表征出病理切片所包含的病理信息,例如,所述数字病理切片可以为:宫颈癌数字病理切片、气管炎数字病理切片以及肺炎数字病理切片等。
可选的,所述病理切片通过选取一定大小的组织细胞,利用病理组织学方法制成。
可选的,所述数字病理切片通过将制成后的病理切片输入至上述构建的病理扫描系统中进行生成。
进一步地,为了后续更好的进行数字病理切片的扫描和分析,本申请实施例将所述数字病理切片集保存至所述病理扫描分析系统的载玻片中,以实现后续大批量的数字病理切分的高效处理。
进一步地,本申请实施例中利用所述病理扫描分析系统中的扫描仪对载玻片中的数字病理切片进行图像扫描,生成数字病理切片图像,包括:
基于先入先出的顺序,将放置于所述病理扫描分析系统的所述载玻片中的数字病理切片传输至所述扫描仪中,通过所述扫描仪中的物镜观察所述载玻片中所存在的区域图像,对所述区域图像进行聚焦,生成所述区域图像的聚焦点,根据所述聚焦点,确定所述载玻片中数字病理切片的图像生成函数,根据所述图像生成函数,生成所述载玻片中数字病理切片的数字病理切片图像,根据所述数字病理切片图像,得到所述数字病理切片图像集。其中,需要强调的是,为进一步保证上述数字病理切片图像集的私密和安全性,上述数字病理切片图像集还可以存储于一区块链的节点中。
其中,所述先入先出的顺序指的是优先保存至载玻片的数字病理切片优先进行图像扫描,可以保证数字病理切片扫描的秩序性。
可选的,利用当前已知的图像聚焦工具对所述区域图像进行聚焦,例如Helicon Focus图像聚焦工具。
需要声明的是,本申请所采用数字病理切片的图像扫描技术与现有技术所不同的是:本申请通过聚焦手段生成的数字病理图像更为清晰,便于获取病理信息的病理分析。
S3、基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果。
在本申请的至少一个实施例中,由于在上述S1中已经将病理分析系统集成至病理扫描系统中,因此,本申请可以实现对生成的数字病理切片图像同时进行病理分析。
详细地,参阅图2所示,所述基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果,包括:
S30、对所述数字病理切片图像进行伽马矫正,得到目标数字病理切片图像。
一个可选实施例中,根据预设的伽马矫正阈值对所述数字病理切片图像进行伽马矫正矫 正。可选的,所述伽马矫正阈值为0.7。
其中,所述伽马矫正用于将调节图像中的灰度值,即将图像中过于明亮的部分调节成适度灰度,将图像中过去暗黑的部分调节成合适灰度,通过所述伽马矫正可以增强数字病理切片图像的灰度值,从而可以提高后续数字病理切片图像的病理分析精确率。
S31、利用所述病理分析系统中的残差网络提取出所述目标数字病理切片图像的特征图像,得到特征数字病理切片图像。
在本申请的其中一个实施例中,将所述目标数字病理切片图像输入至所述残差网络的特征提取器中进行卷积运算,生成所述特征数字病理切片图像。
其中,利用残差网络进行特征图像提取属于当前较为成熟的技术,本申请在此不做进一步的阐述。
S32、利用所述病理分析系统中的区域生成网络计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,得到所述数字病理切片图像的病理分析结果。
详细地,参阅图3所示,所述利用所述病理分析系统中的区域生成网络计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,包括:
S320、获取所述特征数字病理切片图像中异常组织细胞的真实坐标框,即标签值;
S321、利用所述病理分析系统中的区域生成网络计算出所述特征数字病理切片图像的异常组织细胞第一预测坐标框,计算所述第一预测坐标框与所述真实坐标框的第一交并比阈值,并筛选出所述第一交并比阈值大于预设第一阈值的第一预测坐标框,得到初始第一预测坐标框,根据所述初始第一预测坐标框生成第一预测数字病理切片图像区域;
S322、利用所述病理分析系统中的区域生成网络计算出所述第一预测数字病理切片图像区域的异常组织细胞第二预测坐标框,计算所述第二预测坐标框与所述真实坐标框的第二交并比阈值,并筛选出所述第二交并比阈值大于预设第二阈值的第二预测坐标框,得到初始第二预测坐标框,根据所述初始第二预测坐标框生成第二预测数字病理切片图像区域;
S323、利用所述病理分析系统中的区域生成网络计算出所述第二预测数字病理切片图像区域的异常组织细胞第三预测坐标框,计算所述第三预测坐标框与所述真实坐标框的第三交并比阈值,并筛选出所述第三交并比阈值大于预设第三阈值的第三预测坐标框,得到初始第三预测坐标框,根据所述初始第三预测坐标框生成第三预测数字病理切片图像区域;
S324、根据所述第三预测数字病理切片图像区域,识别出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别。
可选的,所述数字病理切片图像中异常组织细胞的真实坐标框通过大量的临床实验得到。
可选的,所述预设第一阈值为0.5,所述预设第二阈值为0.6,所述预设第三阈值为0.7。
进一步地,所述异常组织细胞的类别根据对应的坐标信息识别出,其类别可以为轻度异常组织细胞、中度异常组织细胞以及重度异常组织细胞等。
进一步地,需要声明的是,利用区域生成网络计算图像的预测坐标框属于当前较为成熟的现有技术,在此不做详细的阐述。
S4、利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
可选的,所述阅片软件为病理影像阅片软件。
本申请实施例集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统,本申请将病理分析系统集成至病理扫描系统中,实现了后续病理切片的扫描与分析的一体化;其次,本申请实施例获取数字病理切片集,将所述数字病理切片集保存至所述病理扫描分析系统的载玻片中,利用所述病理扫描分析系统中的扫描仪对载玻片中的数字病理切片进行图像扫描,生成数字病理切片图像,可以高通量处理大量病理切片,不需要额外的将扫描结果进行传输和转移处理;进一步地,本申请实施例基于所述病理扫描分析系统的病理分析系统,对每生成一个所述数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果,实现了在病理切片扫描的同时进行智能分析病理数字化影像;利用阅 片软件读取并输出所述数字病理切片图像的病理扫描分析结果。因此,本申请提出的一种基于病理切片的扫描和分析一体化装置可以实现病理切片的扫描和分析一体化。
如图4所示,是本申请一实施例提供的基于病理切片的扫描和分析一体化装置的模块示意图。
本申请所述基于病理切片的扫描和分析一体化装置100可以安装于电子设备中。根据实现的功能,所述基于病理切片的扫描和分析一体化装置可以包括集成模块101、扫描模块102、分析模块103以及读取及分析模块104。本申请所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述集成模块101,用于集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统。
在本申请的至少一个实施例中,所述病理扫描系统是由软/硬件设施组合得到,其中,所述软件设施包括、但不限于:图像扫描软件、图像浏览软件以及图像和数据管理软件等,所述硬件设施包括、但不限于:扫描仪、载玻片以及输出设备等。所述病理扫描系统用于将病理切片中所存在的病理信息转换为可存储的数字化图像,可以帮助医生进行病理诊断。
一个可选实施例中,所述病理扫描系统的创建可选用当前较为成熟的技术,在此不做进一步阐述。
进一步地,由于所述病理扫描系统仅仅只能扫描出病理切片的数字化图像信息,并不能直接对所述数字化图像信息进行病理分析,因此,本申请将一个预设的病理分析系统集成至所述病理扫描系统中,以实现对扫描出的数字化图像进行病理分析,从而可以实现病理切片的扫描与分析一体化,进而可以帮助用户更加高效快速的进行病理诊断。
较佳地,本申请实施例所述预设的病理分析系统包括:残差网络(resnet)和区域生成网络(region proposal network,RPN),其中,所述resnet用于对后续扫描出的病理图像进行特征提取,所述RPN用于生成特征提取后的病理图像的预测框和对应病理异常类型。
一个可选实施例中,所述将构建的病理分析系统集成至所述病理扫描系统中,得到病理扫描分析系统,包括:
获取所述病理扫描系统中扫描仪的API接口参数,根据所述API接口参数,查询所述扫描仪的外部系统连接配置文件;
根据所述外部系统连接配置文件,配置所述病理分析系统的接口参数,根据配置后的所述病理分析系统的接口参数,利用预设驱动程序将所述病理分析系统导入至所述病理扫描系统中。
可选的,所述预设的驱动程序通过java编程语言进行编译生成。
所述扫描模块102,用于利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集。
在本申请的至少一个实施例中,所述数字病理切片集是由不同的数字病理切片进行组合得到,所述数字病理切片可以表征出病理切片所包含的病理信息,例如,所述数字病理切片可以为:宫颈癌数字病理切片、气管炎数字病理切片以及肺炎数字病理切片等。
可选的,所述病理切片通过选取一定大小的组织细胞,利用病理组织学方法制成。
可选的,所述数字病理切片通过将制成后的病理切片输入至上述构建的病理扫描系统中进行生成。
进一步地,为了后续更好的进行数字病理切片的扫描和分析,本申请实施例将所述数字病理切片集保存至所述病理扫描分析系统的载玻片中,以实现后续大批量的数字病理切分的高效处理。
进一步地,本申请实施例中利用所述病理扫描分析系统中的扫描仪对载玻片中的数字病理切片进行图像扫描,生成数字病理切片图像,包括:
基于先入先出的顺序,将放置于所述病理扫描分析系统的载玻片中的数字病理切片传输至所述扫描仪中,通过所述扫描仪中的物镜观察所述载玻片中所存在的区域图像
对所述区域图像进行聚焦,生成所述区域图像的聚焦点,根据所述聚焦点,确定所述载玻片中数字病理切片的图像生成函数,根据所述图像生成函数,生成所述载玻片中数字病理切片的数字病理切片图像,根据所述数字病理切片图像,得到所述数字病理切片图像集。
其中,需要强调的是,为进一步保证上述数字病理切片图像集的私密和安全性,上述数字病理切片图像集还可以存储于一区块链的节点中。
其中,所述先入先出的顺序指的是优先保存至载玻片的数字病理切片优先进行图像扫描,可以保证数字病理切片扫描的秩序性。
可选的,利用当前已知的图像聚焦工具对所述区域图像进行聚焦,例如Helicon Focus图像聚焦工具。
需要声明的是,本申请所采用数字病理切片的图像扫描技术与现有技术所不同的是:本申请通过聚焦手段生成的数字病理图像更为清晰,便于获取病理信息的病理分析。
所述分析模块103,用于基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果。
在本申请的至少一个实施例中,由于在上述已经将病理分析系统集成至病理扫描系统中,因此,本申请可以实现对生成的数字病理切片图像同时进行病理分析。
详细地,参阅图2所示,所述基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果,包括:
S30、对所述数字病理切片图像进行伽马矫正,得到目标数字病理切片图像。
一个可选实施例中,根据预设的伽马矫正阈值对所述数字病理切片图像进行伽马矫正矫正。可选的,所述伽马矫正阈值为0.7。
其中,所述伽马矫正用于将调节图像中的灰度值,即将图像中过于明亮的部分调节成适度灰度,将图像中过去暗黑的部分调节成合适灰度,通过所述伽马矫正可以增强数字病理切片图像的灰度值,从而可以提高后续数字病理切片图像的病理分析精确率。
S31、利用所述病理分析系统中的残差网络提取出所述目标数字病理切片图像的特征图像,得到特征数字病理切片图像。
在本申请的其中一个实施例中,将所述目标数字病理切片图像输入至所述残差网络的特征提取器中进行卷积运算,生成所述特征数字病理切片图像。
其中,利用残差网络进行特征图像提取属于当前较为成熟的技术,本申请在此不做进一步的阐述。
S32、利用所述病理分析系统中的区域生成网络计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,得到所述数字病理切片图像的病理分析结果。
详细地,参阅图3所示,所述利用所述病理分析系统中的区域生成网络计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,包括:
S320、获取所述特征数字病理切片图像中异常组织细胞的真实坐标框,即标签值;
S321、利用所述病理分析系统中的区域生成网络计算出所述特征数字病理切片图像的异常组织细胞第一预测坐标框,计算所述第一预测坐标框与所述真实坐标框的第一交并比阈值,并筛选出所述第一交并比阈值大于预设第一阈值的第一预测坐标框,得到初始第一预测坐标框,根据所述初始第一预测坐标框生成第一预测数字病理切片图像区域;
S322、利用所述病理分析系统中的区域生成网络计算出所述第一预测数字病理切片图像 区域的异常组织细胞第二预测坐标框,计算所述第二预测坐标框与所述真实坐标框的第二交并比阈值,并筛选出所述第二交并比阈值大于预设第二阈值的第二预测坐标框,得到初始第二预测坐标框,根据所述初始第二预测坐标框生成第二预测数字病理切片图像区域;
S323、利用所述病理分析系统中的区域生成网络计算出所述第二预测数字病理切片图像区域的异常组织细胞第三预测坐标框,计算所述第三预测坐标框与所述真实坐标框的第三交并比阈值,并筛选出所述第三交并比阈值大于预设第三阈值的第三预测坐标框,得到初始第三预测坐标框,根据所述初始第三预测坐标框生成第三预测数字病理切片图像区域;
S324、根据所述第三预测数字病理切片图像区域,识别出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别。
可选的,所述数字病理切片图像中异常组织细胞的真实坐标框通过大量的临床实验得到。
可选的,所述预设第一阈值为0.5,所述预设第二阈值为0.6,所述预设第三阈值为0.7。
进一步地,所述异常组织细胞的类别根据对应的坐标信息识别出,其类别可以为轻度异常组织细胞、中度异常组织细胞以及重度异常组织细胞等。
进一步地,需要声明的是,利用区域生成网络计算图像的预测坐标框属于当前较为成熟的现有技术,在此不做详细的阐述。
所述读取及输出模块104,用于利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
可选的,所述阅片软件为病理影像阅片软件。
本申请实施例集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统,得到病理扫描分析系统,本申请将病理分析系统集成至病理扫描系统中,实现了后续病理切片的扫描与分析的一体化;其次,本申请实施例获取数字病理切片集,将所述数字病理切片集保存至所述病理扫描分析系统的载玻片中,利用所述病理扫描分析系统中的扫描仪对载玻片中的数字病理切片进行图像扫描,生成数字病理切片图像,可以高通量处理大量病理切片,不需要额外的将扫描结果进行传输和转移处理;进一步地,本申请实施例基于所述病理扫描分析系统的病理分析系统,对每生成一个所述数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果,实现了在病理切片扫描的同时进行智能分析病理数字化影像;利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。因此,本申请提出的一种基于病理切片的扫描和分析一体化装置可以实现病理切片的扫描和分析一体化。
如图5所示,是本申请一实施例提供的实现基于病理切片的扫描和分析一体化的方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如基于病理切片的扫描和分析一体化程序。
其中,所述存储器11至少包括一种类型的可读存储介质,所述计算机可读存储介质可以是非易失性,也可以是易失性,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(Smart Media Card,SMC)、安全数字(Secure Digital,SD)卡、闪存卡(Flash Card)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如基于病理切片的扫描和分析一体化程序的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所 组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(Central Processing unit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(Control Unit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如基于病理切片的扫描和分析一体化程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图5仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图5示出的结构并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的基于病理切片的扫描和分析一体化程序12是多个指令的组合,在所述处理器10中运行时,可以实现:
集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
具体地,所述处理器10对上述指令的具体实现方法可参考图1对应实施例中相关步骤的描述,在此不赘述。需要强调的是,为进一步保证上述原始数据集的私密和安全性,上述稽核数据还可以存储于一区块链的节点中。
进一步地,所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过 其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图标记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。

Claims (20)

  1. 一种基于病理切片的扫描和分析一体化方法,其中,所述方法包括:
    集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
    利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
    基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
    利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
  2. 如权利要求1所述的基于病理切片的扫描和分析一体化方法,其中,所述集成预构建的病理分析系统及一个预构建的病理扫描系统,包括:
    获取所述病理扫描系统中扫描仪的API接口参数;
    根据所述API接口参数,查询所述扫描仪的外部系统连接配置文件;
    根据所述外部系统连接配置文件,配置所述病理分析系统的接口参数;
    根据配置后的所述病理分析系统的接口参数,利用预设驱动程序将所述病理分析系统导入至所述病理扫描系统中。
  3. 如权利要求1所述的基于病理切片的扫描和分析一体化方法,其中,所述利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集,包括:
    基于先入先出的顺序,将放置于所述病理扫描分析系统的载玻片中的数字病理切片传输至所述扫描仪中;
    通过所述扫描仪中的物镜观察所述载玻片中所存在的区域图像;
    对所述区域图像进行聚焦,生成所述区域图像的聚焦点;
    根据所述聚焦点,确定所述载玻片中数字病理切片的图像生成函数;
    根据所述图像生成函数,生成所述载玻片中数字病理切片的数字病理切片图像,根据所述数字病理切片图像,得到所述数字病理切片图像集。
  4. 如权利要求1所述的基于病理切片的扫描和分析一体化方法,其中,所述基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果,包括:
    对所述数字病理切片图像进行伽马矫正,得到目标数字病理切片图像;
    提取所述目标数字病理切片图像的特征图像,得到特征数字病理切片图像;
    计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,得到所述数字病理切片图像的病理分析结果。
  5. 如权利要求4所述的基于病理切片的扫描和分析一体化方法,其中,所述计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,包括:
    获取所述特征数字病理切片图像中异常组织细胞的真实坐标框;
    计算所述特征数字病理切片图像的异常组织细胞第一预测坐标框,计算所述第一预测坐标框与所述真实坐标框的第一交并比阈值,并筛选出所述第一交并比阈值大于预设第一阈值的第一预测坐标框,得到初始第一预测坐标框,根据所述初始第一预测坐标框生成第一预测数字病理切片图像区域;
    计算所述第一预测数字病理切片图像区域的异常组织细胞第二预测坐标框,计算所述第二预测坐标框与所述真实坐标框的第二交并比阈值,并筛选出所述第二交并比阈值大于预设第二阈值的第二预测坐标框,得到初始第二预测坐标框,根据所述初始第二预测坐标框生成第二预测数字病理切片图像区域;
    计算所述第二预测数字病理切片图像区域的异常组织细胞第三预测坐标框,计算所述第三预测坐标框与所述真实坐标框的第三交并比阈值,并筛选出所述第三交并比阈值大于预设 第三阈值的第三预测坐标框,得到初始第三预测坐标框,根据所述初始第三预测坐标框生成第三预测数字病理切片图像区域;
    根据所述第三预测数字病理切片图像区域,识别出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别。
  6. 如权利要求2所述的基于病理切片的扫描和分析一体化方法,其中,所述预设驱动程序通过java编程语言进行编译生成。
  7. 如权利要求1所述的基于病理切片的扫描和分析一体化方法,其中,所述病理扫描系统是由软/硬件设施组合得到,其中,所述软件设施包括:图像扫描软件、图像浏览软件以及图像和数据管理软件,所述硬件设施包括:扫描仪、载玻片以及输出设备。
  8. 一种基于病理切片的扫描和分析一体化装置,其中,所述装置包括:
    集成模块,用于集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
    扫描模块,用于利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
    分析模块,用于基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
    读取及输出模块,用于利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
  9. 一种电子设备,其中,所述电子设备包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述步骤:
    集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
    利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
    基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
    利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
  10. 如权利要求9所述的电子设备,其中,所述集成预构建的病理分析系统及一个预构建的病理扫描系统,包括:
    获取所述病理扫描系统中扫描仪的API接口参数;
    根据所述API接口参数,查询所述扫描仪的外部系统连接配置文件;
    根据所述外部系统连接配置文件,配置所述病理分析系统的接口参数;
    根据配置后的所述病理分析系统的接口参数,利用预设驱动程序将所述病理分析系统导入至所述病理扫描系统中。
  11. 如权利要求9所述的电子设备,其中,所述利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集,包括:
    基于先入先出的顺序,将放置于所述病理扫描分析系统的载玻片中的数字病理切片传输至所述扫描仪中;
    通过所述扫描仪中的物镜观察所述载玻片中所存在的区域图像;
    对所述区域图像进行聚焦,生成所述区域图像的聚焦点;
    根据所述聚焦点,确定所述载玻片中数字病理切片的图像生成函数;
    根据所述图像生成函数,生成所述载玻片中数字病理切片的数字病理切片图像,根据所述数字病理切片图像,得到所述数字病理切片图像集。
  12. 如权利要求9所述的电子设备,其中,所述基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果,包括:
    对所述数字病理切片图像进行伽马矫正,得到目标数字病理切片图像;
    提取所述目标数字病理切片图像的特征图像,得到特征数字病理切片图像;
    计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,得到所述数字病理切片图像的病理分析结果。
  13. 如权利要求12所述的电子设备,其中,所述计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,包括:
    获取所述特征数字病理切片图像中异常组织细胞的真实坐标框;
    计算所述特征数字病理切片图像的异常组织细胞第一预测坐标框,计算所述第一预测坐标框与所述真实坐标框的第一交并比阈值,并筛选出所述第一交并比阈值大于预设第一阈值的第一预测坐标框,得到初始第一预测坐标框,根据所述初始第一预测坐标框生成第一预测数字病理切片图像区域;
    计算所述第一预测数字病理切片图像区域的异常组织细胞第二预测坐标框,计算所述第二预测坐标框与所述真实坐标框的第二交并比阈值,并筛选出所述第二交并比阈值大于预设第二阈值的第二预测坐标框,得到初始第二预测坐标框,根据所述初始第二预测坐标框生成第二预测数字病理切片图像区域;
    计算所述第二预测数字病理切片图像区域的异常组织细胞第三预测坐标框,计算所述第三预测坐标框与所述真实坐标框的第三交并比阈值,并筛选出所述第三交并比阈值大于预设第三阈值的第三预测坐标框,得到初始第三预测坐标框,根据所述初始第三预测坐标框生成第三预测数字病理切片图像区域;
    根据所述第三预测数字病理切片图像区域,识别出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别。
  14. 如权利要求10所述的电子设备,其中,所述预设驱动程序通过java编程语言进行编译生成。
  15. 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下所述步骤:
    集成预构建的病理扫描系统及一个预构建的病理分析系统,得到病理扫描分析系统;
    利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集;
    基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果;
    利用阅片软件读取并输出所述数字病理切片图像的病理扫描分析结果。
  16. 如权利要求15所述的计算机可读存储介质,其中,所述集成预构建的病理分析系统及一个预构建的病理扫描系统,包括:
    获取所述病理扫描系统中扫描仪的API接口参数;
    根据所述API接口参数,查询所述扫描仪的外部系统连接配置文件;
    根据所述外部系统连接配置文件,配置所述病理分析系统的接口参数;
    根据配置后的所述病理分析系统的接口参数,利用预设驱动程序将所述病理分析系统导入至所述病理扫描系统中。
  17. 如权利要求15所述的计算机可读存储介质,其中,所述利用所述病理扫描分析系统中的扫描仪对数字病理切片集进行图像扫描,生成数字病理切片图像集,包括:
    基于先入先出的顺序,将放置于所述病理扫描分析系统的载玻片中的数字病理切片传输至所述扫描仪中;
    通过所述扫描仪中的物镜观察所述载玻片中所存在的区域图像;
    对所述区域图像进行聚焦,生成所述区域图像的聚焦点;
    根据所述聚焦点,确定所述载玻片中数字病理切片的图像生成函数;
    根据所述图像生成函数,生成所述载玻片中数字病理切片的数字病理切片图像,根据所述数字病理切片图像,得到所述数字病理切片图像集。
  18. 如权利要求15所述的计算机可读存储介质,其中,所述基于所述病理扫描分析系统的病理分析系统,对所述数字病理切片图像集中的每一个数字病理切片图像进行病理分析,得到所述数字病理切片图像的病理分析结果,包括:
    对所述数字病理切片图像进行伽马矫正,得到目标数字病理切片图像;
    提取所述目标数字病理切片图像的特征图像,得到特征数字病理切片图像;
    计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,得到所述数字病理切片图像的病理分析结果。
  19. 如权利要求18所述的计算机可读存储介质,其中,所述计算出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别,包括:
    获取所述特征数字病理切片图像中异常组织细胞的真实坐标框;
    计算所述特征数字病理切片图像的异常组织细胞第一预测坐标框,计算所述第一预测坐标框与所述真实坐标框的第一交并比阈值,并筛选出所述第一交并比阈值大于预设第一阈值的第一预测坐标框,得到初始第一预测坐标框,根据所述初始第一预测坐标框生成第一预测数字病理切片图像区域;
    计算所述第一预测数字病理切片图像区域的异常组织细胞第二预测坐标框,计算所述第二预测坐标框与所述真实坐标框的第二交并比阈值,并筛选出所述第二交并比阈值大于预设第二阈值的第二预测坐标框,得到初始第二预测坐标框,根据所述初始第二预测坐标框生成第二预测数字病理切片图像区域;
    计算所述第二预测数字病理切片图像区域的异常组织细胞第三预测坐标框,计算所述第三预测坐标框与所述真实坐标框的第三交并比阈值,并筛选出所述第三交并比阈值大于预设第三阈值的第三预测坐标框,得到初始第三预测坐标框,根据所述初始第三预测坐标框生成第三预测数字病理切片图像区域;
    根据所述第三预测数字病理切片图像区域,识别出所述特征数字病理切片图像的异常组织细胞的坐标信息和类别。
  20. 如权利要求16所述的计算机可读存储介质,其中,所述预设驱动程序通过java编程语言进行编译生成。
PCT/CN2020/119104 2020-06-09 2020-09-29 基于病理切片扫描和分析一体化方法、装置、设备及介质 WO2021151307A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010520678.8 2020-06-09
CN202010520678.8A CN111681738B (zh) 2020-06-09 2020-06-09 基于病理切片扫描和分析一体化方法、装置、设备及介质

Publications (1)

Publication Number Publication Date
WO2021151307A1 true WO2021151307A1 (zh) 2021-08-05

Family

ID=72454386

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/119104 WO2021151307A1 (zh) 2020-06-09 2020-09-29 基于病理切片扫描和分析一体化方法、装置、设备及介质

Country Status (2)

Country Link
CN (1) CN111681738B (zh)
WO (1) WO2021151307A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111681738B (zh) * 2020-06-09 2024-05-07 平安科技(深圳)有限公司 基于病理切片扫描和分析一体化方法、装置、设备及介质
CN112581438B (zh) * 2020-12-10 2022-11-08 腾讯医疗健康(深圳)有限公司 切片图像识别方法、装置和存储介质及电子设备
CN113763315B (zh) * 2021-05-18 2023-04-07 腾讯医疗健康(深圳)有限公司 玻片图像的信息获取方法、装置、设备及介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108733967A (zh) * 2017-04-24 2018-11-02 太豪生医股份有限公司 云端医疗图像分析系统与方法
US20190108905A1 (en) * 2016-12-26 2019-04-11 Shanghai United Imaging Healthcare Co., Ltd. System and method for processing medical image data
CN109979588A (zh) * 2019-01-22 2019-07-05 北京金智拓科技有限公司 图像扫描病理切片系统
CN110705583A (zh) * 2019-08-15 2020-01-17 平安科技(深圳)有限公司 细胞检测模型训练方法、装置、计算机设备及存储介质
CN110727097A (zh) * 2019-12-19 2020-01-24 上海兰脉信息科技有限公司 一种病理显微图像实时采集分析系统、方法、装置及介质
CN111681738A (zh) * 2020-06-09 2020-09-18 平安科技(深圳)有限公司 基于病理切片扫描和分析一体化方法、装置、设备及介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109979546A (zh) * 2019-04-04 2019-07-05 成都大学 基于人工智能数字病理的网络模型分析平台及构建方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190108905A1 (en) * 2016-12-26 2019-04-11 Shanghai United Imaging Healthcare Co., Ltd. System and method for processing medical image data
CN108733967A (zh) * 2017-04-24 2018-11-02 太豪生医股份有限公司 云端医疗图像分析系统与方法
CN109979588A (zh) * 2019-01-22 2019-07-05 北京金智拓科技有限公司 图像扫描病理切片系统
CN110705583A (zh) * 2019-08-15 2020-01-17 平安科技(深圳)有限公司 细胞检测模型训练方法、装置、计算机设备及存储介质
CN110727097A (zh) * 2019-12-19 2020-01-24 上海兰脉信息科技有限公司 一种病理显微图像实时采集分析系统、方法、装置及介质
CN111681738A (zh) * 2020-06-09 2020-09-18 平安科技(深圳)有限公司 基于病理切片扫描和分析一体化方法、装置、设备及介质

Also Published As

Publication number Publication date
CN111681738B (zh) 2024-05-07
CN111681738A (zh) 2020-09-18

Similar Documents

Publication Publication Date Title
WO2021151307A1 (zh) 基于病理切片扫描和分析一体化方法、装置、设备及介质
US10810735B2 (en) Method and apparatus for analyzing medical image
US11328365B2 (en) Systems and methods for insurance fraud detection
AU2018102232A4 (en) Bone marrow cell marking method and system
CN110705583B (zh) 细胞检测模型训练方法、装置、计算机设备及存储介质
WO2021217851A1 (zh) 异常细胞自动标注方法、装置、电子设备及存储介质
WO2021189901A1 (zh) 图像分割方法、装置、电子设备及计算机可读存储介质
WO2022110712A1 (zh) 图像增强方法、装置、电子设备及计算机可读存储介质
US20220351370A1 (en) Auxiliary pathological diagnosis method
CN111932482A (zh) 图像中目标物的检测方法、装置、电子设备及存储介质
WO2022105179A1 (zh) 生物特征图像识别方法、装置、电子设备及可读存储介质
WO2021151277A1 (zh) 目标物损伤程度判定方法、装置、电子设备及存储介质
WO2021189827A1 (zh) 识别模糊图像的方法、装置、设备及计算机可读存储介质
CN111476776B (zh) 胸部病灶位置确定方法、系统、可读存储介质和设备
WO2022048204A1 (zh) 图像生成方法、装置、电子设备及计算机可读存储介质
WO2021189856A1 (zh) 证件校验方法、装置、电子设备及介质
WO2022227192A1 (zh) 图像分类方法、装置、电子设备及介质
JP2019502994A (ja) 自動核セグメンテーション
CN112017763B (zh) 医疗影像数据传输方法、装置、设备及介质
WO2023134080A1 (zh) 相机作弊识别方法、装置、设备及存储介质
WO2022077914A1 (zh) 医学图片优化方法、装置、设备及计算机可读存储介质
CN113419951B (zh) 人工智能模型优化方法、装置、电子设备及存储介质
WO2022227191A1 (zh) 非主动活体检测方法、装置、电子设备及存储介质
CN115422123A (zh) 数据处理方法、装置、电子设备及存储介质
CN111859985B (zh) Ai客服模型测试方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20916438

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20916438

Country of ref document: EP

Kind code of ref document: A1