35 results about "Digital pathology" patented technology

This invention relates to an intelligent decision support system for rectal cancer prognosis integrating digital pathological images, belonging to the field of medical image processing technology. The system includes a data acquisition module for collecting multiple sets of sample data; a feature selection module for identifying multiple key medical imaging features of rectal cancer based on the multiple sets of sample data; a model building module for acquiring a pre-trained deep learning model and constructing a rectal cancer prognosis prediction model based on transfer learning, the pre-trained deep learning model, the multiple sets of sample data, and the multiple key medical imaging features of rectal cancer; an image acquisition module for acquiring pre- and post-operative medical images of the rectal cancer patient to be evaluated; and a recurrence prediction module for predicting the recurrence probability of the rectal cancer patient to be evaluated based on the pre- and post-operative medical images of the patient using the rectal cancer prognosis prediction model. This system has the advantage of improving the accuracy of non-invasive prediction of postoperative recurrence of rectal cancer.

The application discloses a kind of kidney cell cancer patient prognosis risk prediction methods based on multi-modal deep learning.The present application processes whole field digital pathology section (WSI) image and pathological diagnosis report by deep learning algorithm, extracts text features using natural language processing model, extracts image features using computer vision model and ABMIL network, and carries out multi-modal feature fusion through Cross-attention Transformer network, and finally outputs the survival risk curve of patient changes with time in combination with Weibull survival function, for assisting doctor to carry out more accurate prognosis evaluation and survival analysis.

The present application relates to the technical field of digital pathology image analysis, and discloses an animal tissue pathological section cell atypia image automatic grading method and system, the method comprises the following steps: scanning the whole section image to obtain a high-power field image by traversing the tumor area with a sliding window; inputting a star-convex polygon regression kernel instance segmentation network trained by multi-species animal tumor annotation data to obtain each nuclear boundary; extracting morphological parameters such as nuclear area, long-short axis ratio, nuclear-plasma ratio, nuclear membrane regularity and chromatin texture; detecting and counting nuclear mitotic figures; introducing a species adaptive baseline correction to normalize the morphological parameters and then inputting the normalized morphological parameters into a classifier to output a three-level atypia grading.

This application discloses a method, device, and storage medium for correcting digital pathological fluorescence images, relating to the field of digital pathology technology. The method includes: downsampling the original fluorescence image to obtain a sampled fluorescence image; solving for initial path parameters and initial quenching field parameters of the sampled fluorescence image according to a joint optimization objective function; upsampling the initial path parameters and mapping them to the image coordinates of the original fluorescence image to obtain original path parameters; solving for the target quenching field of the original fluorescence image based on the original path parameters, the initial quenching field parameters, and the joint optimization objective function; and correcting the original fluorescence image according to the target quenching field to obtain the target fluorescence image. This application solves the problem of distortion in the results of quantitative pathological analysis by using a multi-resolution joint optimization scheme, first solving the initial path and quenching field parameters at a coarse scale, and then mapping them to a high-resolution solution for the target quenching field, thereby improving the iteration convergence speed while balancing correction accuracy and pathological signal fidelity.

The application discloses an AI-assisted pathological sample diagnosis method and a diagnosis system, relates to the technical field of medical image assistance, and comprises the following steps: acquiring a pathological sample from a digital pathology image library through a data access layer, and acquiring user information corresponding to the pathological sample from a clinical information library; performing multi-scale attention feature extraction and representation learning on the pathological sample through a multi-scale feature extraction network; quantifying the dynamic uncertainty of the pathological sample through a Bayesian neural network; performing multi-modal knowledge fusion; performing diagnosis decision process visualization output through a visualization module; evaluating and verifying the diagnosis system based on the visualization output result; the recognition ability of microstructure in the pathological sample and the confidence evaluation accuracy of the diagnosis result are significantly improved, the explainability and clinical practicability of the system are enhanced, incremental learning and long-term verification are supported, and the robustness, generalization ability and cost-effectiveness of the diagnosis system are effectively improved.

The application discloses an emergency unit for slice emergency scanning and a scanning device, and relates to the technical field of digital pathology. The emergency unit for slice emergency scanning comprises a base, a fixing assembly and a detection assembly. The fixing assembly is movably installed on the base and can switch between a first feeding and discharging position and a second feeding and discharging position. The fixing assembly is used for fixing the slice for emergency scanning. The detection assembly is installed on the base and is used for detecting whether the fixing assembly is in the second feeding and discharging position. The detection assembly is also installed on the base and is used for detecting whether the fixing assembly has the slice. The designed emergency unit can efficiently process the emergency slice priority scanning requirement.

The scheme provides a digital pathological section automatic focusing method and device based on five-point heterogeneous constraints, a low-power objective lens with a lower target magnification is used to obtain a low-power preview image of a target section, and an organization region in the low-power preview image is segmented; coarse focusing is performed on the low-power preview image to obtain a coarse focal surface model; a high-risk region in the coarse focal surface model is divided; fine focusing is performed on each high-risk region to obtain a plurality of fine focal surface models; a focal surface of a non-high-risk region is taken as a first focal surface set, and the fine focal surface models of the high-risk regions are taken as a second focal surface set, and an automatic focusing path of the target section is obtained based on the first focal surface set and the second focal surface set. In the coarse focusing and the fine focusing, five focusing points are selected, which take into account the overall focal surface reference, the scanning direction trend, the lateral boundary prediction accuracy and the local focal surface mutation compensation, so as to make up for the insufficient adaptation of the low-order curved surface fitting to the local abnormal region, and to realize accurate acquisition of the automatic focusing path.

The application relates to the field of artificial intelligence medical technology and discloses an early esophageal cancer screening method and system based on artificial intelligence, which comprises the following steps: preparing an obtained esophageal epithelial cell sample of a subject into a single-layer cytological smear, generating an original digital pathology image through optical scanning; extracting independent cells therefrom, calculating local spatial moment parameters of the independent cells; determining the geometric principal axis direction and stretching degree of the independent cells based on the local spatial moment parameters; judging whether the stretching degree exceeds the length-width ratio benchmark constant of normal esophageal squamous epithelial cells, if yes, applying a local two-dimensional affine transformation to the independent cells along the geometric principal axis direction to offset the mechanical stretching deformation caused by sampling, and generating calibrated cell image data; inputting the calibrated cell image data into an artificial intelligence classification module, extracting cell pathological features based on a deep convolutional neural network, and outputting a screening diagnosis result. The application offsets cell deformation interference and improves screening accuracy.

The application discloses a kind of digital pathological image standardization systems based on task constraint enhancement adversarial generation network, including data set construction module, data preprocessing module, generator module, discriminator module, task constraint module and loss calculation module.The application constructs huge source data set according to the training set of the deep learning model based on the computer-aided pathological diagnosis system of specific task, compared with the limited number of digital pathological image template, more adapt to complex and changeable clinical practice, while converting digital pathological image into gray image as the input of generator, the structural information of original digital pathological image is retained.The application adopts multilayer nested U-Net network architecture in generator module, can generate higher resolution digital pathological image, while introducing task constraint to enhance adversarial generation network, ensure that generator learns required image features for specific task, have strong universality.

Systems and methods are described for grouping cells in a slide image that share a similar target, comprising receiving a digital pathology image corresponding to a tissue sample, applying a trained machine learning system to the digital pathology image, said system trained to predict at least one target difference throughout the tissue sample, and determining, using the trained machine learning system, one or more predicted groups, each of the predicted groups corresponding to a subportion of the tissue sample associated with a target.

The application discloses an auxiliary lymphoma immunohistochemical positive cell positioning analysis device and method, and relates to the technical field of positive cell positioning.The application comprises an image acquisition and preprocessing module, a positive area preliminary screening module, a cell morphology analysis module, a three-dimensional coordinate positioning module and a report generation and visualization interaction module, is used for accessing a digital slice scanner or a digital pathology image management system, reading an immunohistochemical slice image in a WSI format, and being internally provided with a convolutional neural network model based on deep learning; the model is trained and optimized through a large number of annotated lymphoma immunohistochemical slice images, and can automatically identify suspicious areas with positive cell characteristics in the image.The double-layer analysis mechanism combining the deep learning model and the multi-dimensional screening of morphological parameters can significantly reduce the interference of non-specific staining and background impurities, and effectively reduce the missed detection rate and the false detection rate, compared with the traditional manual film reading or single threshold judgment method.

This invention discloses an incremental rendering system for dirty rectangles based on digital pathological images, comprising: a preprocessing module for preprocessing digital pathological images, including noise extraction during the initial rendering process; a collision tracking module for completing the initial rendering of digital pathological images, determining the rendering direction through collision detection and ray tracing; a local rendering module for incremental rendering of the initially rendered digital pathological images, performing local rendering of the digital pathological images by determining the changing positions of dirty rectangles; and a rendering detection module for detecting the results of incremental rendering, calculating the structural similarity and signal-to-noise ratio between the initial digital pathological images and the incrementally rendered digital pathological images, and judging the rendering quality.

The application discloses a kind of multi-modal oral pathology large model system and method for auxiliary diagnosis and teaching, the system includes data acquisition module, oral pathology knowledge graph module, multiscale visual coding module, multi-modal semantic alignment module, reasoning decision module and user interaction module.Oral pathology whole digital section image is extracted to multi-resolution feature, cross-modal semantic alignment and fusion of clinical history text and medical image data are combined, and oral pathology knowledge graph is introduced to constraint reasoning, realize oral pathology auxiliary diagnosis, structured report generation and intelligent teaching interaction.Compared with traditional single task artificial intelligence model, the system can complete pathological section preliminary analysis and lesion area positioning in seconds, significantly improve the efficiency of diagnosis.The application has intelligent interaction and explainable analysis capability, compared with traditional static digital pathology system, can shorten the case teaching preparation time, improve teaching interactivity and learning efficiency.

A computer system may enable an end-to-end platform for evaluating digital pathology information. An example process that uses the platform may include receiving first image data corresponding to a tissue sample. The process may also include generating second image data from the first image data by applying at least one virtual stain to the first image data, where at least one virtual stain is selected based on a target clinical diagnosis. The process may also include generating, by a predictive modeling suite, third image data from the second image data by identifying a plurality of histologic features present in the second image data in accordance with the target clinical diagnosis. The process may also include generating, by the predictive modeling suite and using the third image data, a clinical prediction relating to the target clinical diagnosis. The process may also include providing information associated with the clinical prediction for presentation.

This application discloses a method, device, and storage medium for collaborative self-calibration of the optical path and light source, relating to the field of digital pathology scanning calibration technology. The method includes: acquiring bright-field images at multiple preset positions on a standard target, and calculating the similarity value between each bright-field image and a reference image using the SSIM evaluation function; determining the optical path perpendicularity deviation and the light source uniformity deviation based on the similarity values ​​and the corresponding image features of the bright-field images; and adjusting the optical path adjustment mechanism and the light source adjustment mechanism according to the optical path perpendicularity deviation and the light source uniformity deviation until the optical axis is perpendicular to the plane of the standard target and the brightness distribution is uniform. This application achieves collaborative self-calibration of the optical path and light source, improving calibration efficiency and accuracy, and meeting the real-time calibration requirements of digital pathology scanning systems.

The application provides a super large image hash index and topology retrieval method and system, aiming at the contradiction between high-dimensional floating point calculation power demand and long time consumption in mass pathological image retrieval, and adopts multi-scale feature extraction and cascade retrieval architecture.In offline database construction, the image block features are decoupled by a deep network and quantified into segmented structured hash codes;in online retrieval, a dynamic mask is generated according to the retrieval intention, coarse screening is carried out through the bottom mask XOR logic, then high-dimensional floating point feature accurate rearrangement is called, and the spatial microenvironment topology subgraph is constructed combining with the absolute physical coordinates of the block to carry out topology verification rearrangement.The application is mainly used for similar block retrieval of mass pathological sections in digital pathology, effectively reduces the memory and calculation power consumption, and improves the retrieval speed and accuracy of super large images.

The application provides an image tile rendering and video memory scheduling method and system and a readable storage medium thereof, and belongs to the technical field of computer graphics. In order to solve the problems of rendering delay and video memory overflow during super high resolution image browsing, the application collects the speed and acceleration of the viewport coordinate at a high frequency, dynamically calculates a prediction time window and outputs a predicted viewport bounding box; the intersection tile priority score is calculated and a preloading queue is generated; a background asynchronous thread decodes the image according to the queue and silently uploads the image to the video memory of the graphics processor, meanwhile, the reverse predictive de-weighting elimination is performed on the resident tile based on the motion direction; finally, the main rendering thread directly hits the ready texture in the video memory to complete the drawing. The application can be used for smooth browsing of super resolution images such as digital pathology.

The application discloses a pathological image color restoration method and a scanner based on deep learning, and the method comprises the following steps: reducing the resolution of input data and target data based on a bilateral grid downsampling technology; training a neural network model for the first time by using the input data and the target data after the resolution is reduced; improving the resolution of the input data and the target data after the resolution is reduced based on a bilateral grid upsampling technology; and training the neural network model for the second time by using the input data and the target data after the resolution is improved, so that the training speed of the neural network model is improved, and the staining effect of the pathological image collected by a digital pathology scanner is improved.

The application relates to the technical field of digital pathology and artificial intelligence, in particular to an immunohistochemical efficacy prediction system based on dynamic analysis. The system comprises an image processing module, which is used for acquiring and preprocessing paired immunohistochemical digital pathology sections before and after treatment of the same patient; a dynamic registration and analysis module, which is used for high-precision image registration of the paired sections and extraction of dynamic quantitative parameters of biomarker expression changes with treatment; a spatial heterogeneity quantification module, which is used for dividing tumor functional subareas and quantifying spatial distribution heterogeneity parameters of biomarkers in different functional subareas; and a fusion prediction module, which is used for feature fusion of the dynamic quantitative parameters and the spatial distribution heterogeneity parameters and output of a clinical efficacy prediction result through a survival analysis model. The system realizes accurate prediction of tumor immunotherapy efficacy by performing dynamic and quantitative analysis on paired immunohistochemical sections before and after treatment and integrating multi-modal data.

The application relates to the technical field of digital pathology, and particularly provides a method, system and device for quickly obtaining a virtual IHC staining image during breast surgery and a storage medium, the method comprising the following steps: obtaining a breast lesion tissue sample of a patient, preparing an HE staining section, inputting a pre-trained virtual immunohistochemical staining generation model after scanning, and obtaining a virtual IHC image. According to the method, only the HE staining digital whole section image needs to be input to the pre-trained virtual immunohistochemical staining generation model, and the virtual IHC image equivalent to the traditional intraoperative IHC staining can be output within several minutes, so that the time limit requirement of 30 minutes for providing a diagnosis report in intraoperative rapid pathology can be met; the method does not need to perform the experimental operation of traditional intraoperative IHC staining, does not need to consume IHC staining related reagents, simultaneously reduces the artificial operation cost, and effectively reduces the diagnosis and treatment economic burden of the patient.

The application provides a tumor medical pattern recognition method and system based on image detection, relates to medical image processing and artificial intelligence assisted diagnosis, generates a local quality evaluation map to recognize a quality impaired area by blocking a digital pathology section image, evaluating color distribution, light and dark contrast and microscopic structure geometric features of each block, generates a local diagnosis judgment map based on a tumor recognition model analysis, and directly reflects the model's diagnosis confidence for each area; the low confidence area and the quality impaired area in the two maps are analyzed in association, and if the overlapping degree meets the standard, a quality association explanation is generated, and it is clear that the uncertainty is caused by the image quality; finally, an explainability report containing an original map, two evaluation maps and an explanation is generated, which provides clear basis for doctors, avoids traditional compensation defects, improves recognition reliability and transparency, assists accurate clinical decision making, and has practical value.

The application provides a digital pathology image enhancement method and system based on HSV-RGB combined disturbance and rough random occlusion, solves problems such as digital pathology image analysis, and comprises the following steps: S1, color disturbance; S2, tissue defect simulation; and S3, sample output. The application has the advantages of good compatibility, high flexibility and the like.

The application discloses a kind of based on digital pathology section local high-precision magnifying glass system, comprising: main view module, for loading and display digital pathology whole section image;Magnifying glass module, including nested sub-viewport, for specified local area in the current field of view of the main view module is carried out high-power display;Wherein, the magnifying glass module is shared with the main view module by cloning mechanism Image resources;Display area layer, which is overlaid on the display interface of the main view module, is used to visually mark the corresponding position of the local area in the main view module;Control handle layer, integrated in the display area layer, is used to receive user input to interactively adjust the local area, realize local magnification based on original high-resolution data;Non-repeated loading of image resources significantly reduces server and network pressure;Main view and local view are highly consistent, to avoid misdiagnosis.

Digital pathology images acquired using bright-field imaging depicting slides with stained sample slices are accessed. Stain intensity corresponding to at least a portion of the digital pathology images is detected. A biomarker intensity prediction function is accessed, linearly relating predicted biomarker intensity levels to the detected stain intensity. A nonlinear confidence function is accessed, relating the confidence of the predicted biomarker intensity to the detected intensity of the stain. Predicted biomarker intensity is generated for at least a portion of the slide using the detected stain intensity corresponding to at least a portion of the slide and the linear biomarker intensity prediction function. A confidence metric for the predicted biomarker intensity is generated based on the confidence function using the detected stain intensity corresponding to at least a portion of the slide. Results based on the predicted biomarker intensity and confidence metric are output.