Abstract: The present disclosure is directed, among other things, to automated systems and methods for analyzing, storing, and/or retrieving information associated with biological objects having irregular shapes. In some embodiments, the systems and methods partition an input image into a plurality of sub-regions based on localized colors, textures, and/or intensities in the input image, wherein each sub-region represents biologically meaningful data.

Abstract: Convolutional neural networks for detecting objects of interest within images of biological specimens are disclosed. Also disclosed are systems and methods of training and using such networks, one method including: obtaining a sample image and at least one of a set of positive points and a set of negative points, wherein each positive point identifies a location of one object of interest within the sample image, and each negative point identifies a location of one object of no-interest within the sample image; obtaining one or more predefined characteristics of objects of interest and/or objects of no-interest, and based on the predefined characteristics, generating a boundary map comprising a positive area around each positive point the set of positive points, and/or a negative area around each negative point in the set of negative points; and training the convolutional neural network using the sample image and the boundary map.

Abstract: The present disclosure relates to computer-implement techniques for cell localization and classification. Particularly, aspects of the present disclosure are directed to accessing an image for a biological sample, where the image depicts cells comprising a staining pattern of a biomarker; inputting the image into a machine learning model; encoding, by the machine learning model, the image into a feature representation comprising extracted discriminative features; combining, by the machine learning model, feature and spatial information of the cells and the staining pattern of the biomarker through a sequence of up-convolutions and concatenations with the extracted discriminative features from the feature representation; and generating, by the machine learning model, two or more segmentation masks for the biomarker in the image based on the combined feature and spatial information of the cells and the staining pattern of the biomarker.

Abstract: A method for transferring digital pathology annotations between images of a tissue sample may include identifying a first set of points for a geometric feature of a first image of a section of a tissue sample; identifying a corresponding second set of points for a corresponding geometric feature of a second image of a same tissue sample, the second image being an image of another section of the tissue sample; determining coordinates of the first set of points and coordinates of the second set of points; determining a transformation between the first set of points and the second set of points; and applying the transformation to a set of digital pathology annotations on the first image to transfer the set of digital pathology annotations within the first image to the second image.

Abstract: A system and method for treatment of biological samples is disclosed. In some embodiments, an automated biological sample staining system (100), comprising at least one microfluidic reagent applicator (118); at least one bulk fluid applicator (116); at least one fluid aspirator; at least one sample substrate holder; at least one relative motion system; and a control system (102) that is programmed to execute at least one staining protocol on a sample mounted on a substrate that is held in the at least one sample substrate holder.

Abstract: A machine learning model is accessed that is configured to use one or more parameters to process images to generate labels. The machine learning model is executed to transform at least part of each of at least one digital pathology image into a plurality of predicted labels; and generate a confidence metric for each of the plurality of predicted labels. An interface is availed that depicts the at least part of the at least one digital pathology image and that differentially represents predicted labels based on corresponding confidence metrics. In response to availing of the interface, label input is received that confirms, rejects, or replaces at least one of the plurality of predicted labels. The one or more parameters of the machine learning model are updated based on the label input.

Abstract: Methods, systems, and apparatuses for detecting and describing heterogeneity in a cell sample are disclosed herein. A plurality of fields of view (FOV) are generated for one or more areas of interest (AOI) within an image of the cell sample are generated. Hyperspectral or multispectral data from each FOV is organized into an image stack containing one or more z-layers, with each z-layer containing intensity data for a single marker at each pixel in the FOV. A cluster analysis is applied to the image stacks, wherein the clustering algorithm groups pixels having a similar ratio of detectable marker intensity across layers of the z-axis, thereby generating a plurality of clusters having similar expression patterns.

Abstract: Described herein are computer-implemented methods for analysis of a tissue sample. An example method includes: annotating the whole tumor regions or set of tumorous sub-regions either on a biomarker image or an H&E image (e.g. from an adjacent serial section of the biomarker image); registering at least a portion of the biomarker image to the H&E image; detecting different cellular and regional tissue structures within the registered H&E image; computing a probability map based on the different detected structures within the registered H&E image; deriving nuclear metrics from each of the biomarker and H&E images; deriving probability metrics from the probability map; and classifying tumor nuclei in the biomarker image based on the computed nuclear and probability metrics.

Abstract: Disclosed herein is a method of acquiring a high-resolution scan of a biological sample disposed on a substrate with a scanning device, the method comprising: receiving, on a graphical user interface, a first user input corresponding to user configurable scanning settings; receiving, on a graphical user interface, a second user input to initiate scanning based on the received series of user inputs corresponding to user configurable scanning settings; and displaying, on the graphical user interface, a visualization of one or more placeholders populated with one or more of scanning operation status information, image data, and at least a portion of the user configurable scanning settings.

Abstract: In one aspect of the present disclosure is a targeted sequencing workflow where an input sample comprising a sufficient quantity of genomic material is provided such minimal or no amplification cycles are utilized prior to sequencing.

Abstract: The subject disclosure presents systems and computer-implemented methods for evaluating a tissue sample that has been removed from a subject. A change in speed of the energy traveling through the sample is evaluated to monitor changes in the biological sample during processing. The rate of change in the speed of the energy is correlated with the extent of diffusion. A system for performing the method can include a transmitter that outputs the energy and a receiver configured to detect the transmitted energy. A time-of-flight of acoustic waves and rate of change thereof is monitored to determine an optimal time for soaking the tissue sample in a fixative.

Abstract: A method is disclosed that permits calculation of reagent concentrations (in SI units) over time and space within a tissue sample as the sample is immersed in the reagent and the reagent diffuses into the tissue sample. The disclosed method has yielded the surprising result that once a formaldehyde concentration at all points within a tissue sample exceeds about 90 mM during a cold step of a cold+hot fixation protocol, the hot step of the fixation protocol can be commenced to provide reliable detection of molecular targets and preservation of tissue morphology in downstream analyses.

Abstract: A method, system, and computer program product for an image visualization system (120) that includes a contextually adaptive digital pathology interface. At least one image of a biological sample stained for the presence of one or more biomarkers is obtained (300). The image is displayed on a display screen at a first zoom level (310), in which a first subset of user selectable elements are contemporaneously displayed (320). As a result of user input, the image being is displayed at a second zoom level (330), in which a second subset of user selectable elements are contemporaneously displayed with the image (340). The one or more elements within the second subset of user selectable elements are disabled or hidden at the first zoom level, or one or more elements within the first subset of user selectable elements are disabled or hidden at the second zoom level.

Abstract: A method and system are described for processing tissues according to particular processing protocols that are established based on time-of-flight measurements as a processing fluid is diffused into a tissue sample. In one embodiment, measurement of the time it takes about 70% ethanol to diffuse into a tissue sample is used to predict the time it will take to diffuse other processing fluids into the same or similar tissue samples. Advantageously, the disclosed method and system can reduce overall processing times and help ensure that only samples that require similar processing conditions are batched together.

Abstract: An aldehyde fixative solution at a first temperature is caused to contact a tissue sample for a first time period, additionally an aldehyde fixative solution is caused to contact the tissue sample at a second temperature higher than the first temperature for a second time period. The first time period typically ranges from about 15 minutes up to about 4 hours, and the first temperature typically is from greater than 0° C. to at least 15° C. The second temperature typically is from greater than about 22° C. to about 55° C., and the second time period ranges from about 1 hour to about 4 hours. Using this process, improved tissue morphology and IHC staining as well as superior preservation of post-translation modification signals have been accomplished in approximately 4 hours compared to 24 hours for room temperature protocols, and more even morphology and antigen preservation are observed.

Abstract: Systems and methods for automatically excluding artifacts from an analysis of a biological specimen image are disclosed. An exemplary method includes obtaining an immunohistochemistry (IHC) image and a control image, determining whether the control image includes one or more artifacts, upon a determination that the control image includes one or more artifacts, identifying one or more artifact regions within the IHC image by mapping the one or more artifacts from the control image to the IHC image, and performing image analysis of the IHC image where any identified artifact regions are excluded from the image analysis.

Abstract: The present application provides for systems and methods for detecting and estimating signals corresponding to one or more biomarkers in biological samples stained for the presence of protein and/or nucleic acid biomarkers. On particular aspect is directed to a method of estimating an amount of signal corresponding to at least one biomarker in an image of a biological sample. The method includes detecting isolated spots in a first image, deriving an optical density value of a representative isolated spot based on signal features from the detected isolated spots, estimating a number of predictive spots in signal aggregates in each of a plurality of sub-regions based on the derived optical density value of the representative isolated spot, and storing the estimated number of predictive spots and detected isolated spots in each of the plurality of generated sub-regions in a database.

Abstract: A method for fixing a biological sample includes delivering energy through a biological sample that has been removed from a subject, while fixing the biological sample. A change in speed of the energy traveling through the biological sample is evaluated to monitor the progress of the fixation. A system for performing the method can include a transmitter that outputs the energy and a receiver configured to detect the transmitted energy. A computing device can evaluate the speed of the energy based on signals from the receiver.

Abstract: Automated system configured to perform and methods for performing one or more slide processing operations on slides bearing biological samples. The system and methods enable high sample throughput while also minimizing or limiting the potential for cross-contamination of slides. The automated systems can include features that facilitate consistency, controllability of processing time, and/or processing temperature.

Abstract: Efficient methods for identifying biomarkers are described. The method may include identifying a tumor area. The method may further include identifying a plurality of regions. The method may also include defining, for each region, a bounding area for the region that encompasses the region. The method may include determining, for each region of a first subset of the plurality of regions, that the region is to be ascribed to the tumor, where the bounding area is fully within the tumor area. The method may further include determining, for each region of a second subset of the plurality of regions, whether to ascribe the region to the tumor based on an intersection of the region and the tumor area. The method may also include accessing a metric characterizing a biological observation and generating a result based on the metrics. The result may be used as a biomarker.