141 results about "Digital pathology" patented technology

The subject disclosure presents systems and computer-implemented methods for providing reliable risk stratification for early-stage cancer patients by predicting a recurrence risk of the patient and to categorize the patient into a high or low risk group. A series of slides depicting serial sections of cancerous tissue are automatically analyzed by a digital pathology system, a score for the sections is calculated, and a Cox proportional hazards regression model is used to stratify the patient into a low or high risk group. The Cox proportional hazards regression model may be used to determine a whole-slide scoring algorithm based on training data comprising survival data for a plurality of patients and their respective tissue sections. The coefficients may differ based on different types of image analysis operations applied to either whole-tumor regions or specified regions within a slide.

Systems and methods for improving quality assurance in pathology using automated quality assessment and digital image enhancements on digital slides prior to analysis by the pathologist are provided. A digital pathology system (slide scanning instrument and software) creates, assesses and improves the quality of a digital slide. The improved digital slide image has a higher image quality that results in increased efficiency and accuracy in the analysis and diagnosis of such digital slides when they are reviewed on a monitor by a pathologist. These improved digital slides yield a more objective diagnosis than reading the corresponding glass slide under a microscope.

For digital pathology imaging, intelligent processing, such as automatic recognition or content-based retrieval, is one significant benefit that drives the wide application of this technology. Before any intelligent processing on pathology images, every image is converted into a feature vector which quantitatively capture its visual characteristics. An algorithm characterizing pathology images with statistical analysis of local responses of neural networks is described herein. The algorithm framework enables extracting sophisticated textural features that are well adapted to the image data of interest.

A computer-based method and apparatus to facilitate the exchange of pathology studies for the purpose of providing a primary or secondary pathological diagnosis. A study consists of one or more lower-resolution images, the references to the corresponding higher-resolution images, associated image metadata, study metadata and patient metadata. The studies are exchanged from one organization (hospital, practice, or individual physician) to another organization through a set of interconnected dispatcher services. In a cloud model, a plurality of dispatchers may be connected through a Global Dispatcher, both facilitating the addition of new organizations to the cloud and allowing for the addressing of studies from any organization in the cloud to any organization, group or individual in the cloud. By this means, the originating organization may obtain the desired level of care through the selection of recipient organizations, groups and individuals according to the organization's existing criteria. Efficiency in diagnosis is improved through the addressing of a study to a plurality of qualified recipients, as the first recipient with an appropriate, available resource may review and provide a diagnosis for the study.

A digital slide analysis system comprises an algorithm server that maintains or has access to a plurality of image processing and analysis routines. The algorithm server additionally has access to a plurality of digital slide images. The algorithm server executes a selected routine on an identified digital slide and provides the resulting data. Prior to the application of selected routine, the system employs a digital pre-processing module to create a metadata mask that reduces undesirable image data such that the image data processed by the selected routine has an improved signal to noise ratio. The pre-processing module uses a classifier that may be implemented as a pattern recognition module, for example. Undesirable image data is therefore excluded from the image data that is processed by the digital pathology image processing and analysis routine, which significantly improves the digital pathology image analysis.

The invention discloses a cell detection method based on a sliding window and depth structure extraction features. The cell detection method is used for automatically detecting cells by utilizing depth model extraction features and then applying a sliding window technology to a pathological section image. The cell detection method comprises the following steps: section image blocking, training of stacked and sparse self-coding of a feature extraction model, detector training, scanning of a large image by the sliding window and cell position labeling. According to the cell detection method, the large section image is used as a search object, the positions of cells in the image can be found more accurately, faster and completely by adopting a new method of combining a detector and the sliding window, and a good detection effect can be achieved for some unobvious cells in the image. The automatic cell detection method disclosed by the invention can be used for assisting a clinical doctor in carrying out quantitative evaluation on digital pathological sections and accurately and rapidly carrying out clinical diagnosis, so that the diagnosis difference of different observers or one observer at different time periods is reduced.

An optical microscope digital image processing emulator or emulation is described in which a user input device is used to assist in the emulation of an operation of an optical microscope in a digital image processing system. The emulator or emulation is programmable via a library of processing functions stored in memory. The input device is adapted to generate control signals based on a user input, and to transfer the control signals to a processor, the processor being adapted to alter one or more parameters of the processing functions based on the control signals.

Embodiments of the present invention emulate the same control and responsiveness found with an optical microscope on a digital pathology computer system, thereby improving the workflow of pathology specialists by allowing better and faster control over the way images are presented.

The invention pertains to the field of image processing in digital pathology. It notably proposes a method for processing a first digital image, representing a sample in a region, and which image has been acquired from the sample by means of a microscopic imaging system (1) and is stored in a multi-resolution image data structure (80), comprising the steps of:—retrieving (104) a sub-region of the first digital image at a first resolution, —executing (105) a transform function on the retrieved sub-region, the transform function modifying a content of the sub-region according to at least one metric derived from a second resolution representation of the first digital image.

A novel and useful method and system of optimized image compression of digital pathology slide images. The optimized image compression mechanism exploits the special color properties of the stained tissue represented by the digital pathology slides and provides an image compression algorithm having improved rate-distortion performance. Optimized color transforms are pre-computed using training sets of pathology slide image scan data for each stain type. The optimized color transforms are used to compress input slide image scans resulting in more efficient image streaming enabling users to review extremely large digital slide scans from any connected location, such as in a hospital, satellite center, home or on a mobile telephone.

A method for annotating a tissue slide image, a system and a method performed by a computing system for detecting pathological anomalies in a digital pathology image are disclosed. The method performed by a computing system for detecting pathological anomalies in a digital pathology image includes providing a digital pathology image to the computing system and analyzing the digital pathology image using an identification module arranged on the computing system. The identification module uses a machine learning module to execute recognizing an object containing an abnormal image pattern using an identification model loaded in said identification module and identifying whether the abnormal image pattern corresponds to a pathological anomaly using the identification model.

The invention relates to a space orientation computing method for a numerical control bracket, which comprises the following steps of: 1, processing three-dimensional digital analogy of each part; 2, defining a fixed mechanism and a moving mechanism in each digital analogy; 3, setting a drive command for a multiple axis movements of a numerical control bracket; 4, simulating whether each axis movement accords with an actual condition; 5, correcting a movement zero point of the digital analogy of the numerical control bracket; 6, enabling a spindle axes of an automatic drilling and riveting machine to be coincident with a normal line of a riveting point and the riveting point to be coincident with the center of a pressure foot bush; 7, refreshing the digital analogy; 8, figuring out data of five axes of the numerical digital bracket and data of a lifting position and a rotating angle of a lower riveting head under the condition of automatic drilling and riveting on any point on the surface of an airplane; 9, carrying out collision checking and batch output on space orientation data; and 10, carrying out numerical control programming to ensure that the automatic drilling and riveting machine continuously operates. According to the space orientation computing method, the numerical control system can automatically operate according to the space orientation data, and the airplane on the numerical control bracket meets the working requirements of the automatic drilling and riveting machine on the space.

A slide storage, retrieval, transfer and scanning system for a slide scanner presents multiple components which work together in an automated fashion to streamline slide scanning in digital pathology. A slide storage assembly stores several slide baskets and can deliver a particular basket through a rotation mechanism. A slide basket transfer assembly retrieves the basket from the slide storage assembly and transfers the basket to a secondary location, where a slide transfer assembly retrieves a single slide from the basket and delivers the slide to a slide scanning stage for scanning.

The disclosed technology brings histopathology into the operating theatre, to enable real-time intra-operative digital pathology. The disclosed technology utilizes confocal imaging devices image, in the operating theatre, “optical slices” of fresh tissue—without the need to physically slice and otherwise process the resected tissue as required by frozen section analysis (FSA). The disclosed technology, in certain embodiments, includes a simple, operating-table-side digital histology scanner, with the capability of rapidly scanning all outer margins of a tissue sample (e.g., resection lump, removed tissue mass). Using point-scanning microscopy technology, the disclosed technology, in certain embodiments, precisely scans a thin “optical section” of the resected tissue, and sends the digital image to a pathologist rather than the real tissue, thereby providing the pathologist with the opportunity to analyze the tissue intra-operatively. Thus, the disclosed technology provides digital images with similar information content as FSA, but faster and without destroying the tissue sample itself.

The present invention discloses a digital pathology whole slice image retrieval method, and the method is used in a digital pathology whole slice image database. The method comprises: extracting positions of dispersed SIFT feature points and SIFT feature vectors on a digital pathology whole slice image in the database; using an LDA model to obtain a high-level semantic feature value for each SIFT feature point; using an overlapping sliding window method to select alternative regions, and collecting statistics of semantic feature values of all the SIFT feature points in each alternative region, so as to obtain semantic representation vectors of the alternative region; and taking a query image as a region, using the same method to obtain the semantic representation vector of the query image, calculating cosine distances between the semantic representation vector of the query image and semantic representation vectors of all the alternative regions, sorting the distances, and returning to multiple regions with smallest distance. The method disclosed by the present invention can provide diagnosis reference information for the pathologist, and can be used for a digital pathology whole slice image database management and query system and computer-aided diagnosis.