Abstract: Aspects of the present disclosure pertain to systems and methods for enhancing brightfield or darkfield images to better enable nucleus detection. In some embodiments, the systems and methods described herein are useful for identifying membrane stain biomarkers as well as nuclear/cytoplasm stain biomarkers in stained images of biological samples. In some embodiments, the presently disclosed systems and methods enable quick and accurate nucleus detection in stained images of biological samples, especially for original stained images of biological samples where the nuclei appear faint.

Abstract: Techniques for obtaining a synthetic histochemically stained image from a multiplexed immunofluorescence (MPX) image may include producing an N-channel input image that is based on information from each of M channels of an MPX image of a tissue section, where M and N are positive integers and N is less than or equal to M; and generating a synthetic image by processing the N-channel input image using a generator network, the generator network having been trained using a training data set that includes a plurality of pairs of images. The synthetic image depicts a tissue section stained with at least one histochemical stain. Each pair of images of the plurality of pairs of images includes an N-channel image, produced from an MPX image of a first section of a tissue, and an image of a second section of the tissue stained with the at least one histochemical stain.

Abstract: A method includes accessing a digital pathology image that depicts tumor cells sampled from a subject. A plurality of patches may be selected from the digital pathology image, wherein each of the patches depicts tumor cells. A mutation prediction may be generated for each of the patches, wherein the mutation prediction represents a prediction of a likelihood that an actionable mutation appears in the patch. Based on the plurality of mutation predictions, a prognostic prediction related to one or more treatment regimens for the subject may be generated. The prognostic prediction may be based on determining one or more mutational contexts of the digital pathology image as an unknown driver or a tumor suppressor, an oncogene driver mutation, or a gene fusion.

Abstract: Systems and methods relate to predicting disease progression by processing digital pathology images using neural networks. A digital pathology image that depicts a specimen stained with one or more stains is accessed. The specimen may have been collected from a subject. A set of patches are defined for the digital pathology image. Each patch of the set of patches depicts a portion of the digital pathology image. For each patch of the set of patches and using an attention-score neural network, an attention score is generated. The attention-score neural network may have been trained using a loss function that penalized attention-score variability across patches in training digital pathology images labeled to indicate no or low subsequent disease progression. Using a result-prediction neural network and the attention scores, a result is generated that represents a prediction of whether or an extent to which a disease of the subject will progress.

Abstract: The present disclosure relates to automated systems and methods adapted to quickly and accurately train a neural network to detect and/or classify cells and/or nuclei. The present disclosure also relates to automated systems and methods for using a trained cell detection and classification engine, such as one including a neural network, to classify cells within an unlabeled image.

Abstract: A method for analyzing an image of a tissue section may include obtaining a plurality of image locations, each corresponding to a different one of a plurality of biological structures; obtaining a plurality of locations of a first biomarker in the image; and calculating a distance transform array for at least a portion of the image that includes the plurality of seed locations. The method may include, for each of the plurality of seed locations and based on information from the first distance transform array, detecting whether the first biomarker is expressed at the seed location, and storing, to a data structure associated with the seed location, an indication of whether expression of the first biomarker at the seed location was detected. The method may include detecting, based on the stored indications, co-localization of at least two phenotypes in at least a portion of the tissue section.

Abstract: The present disclosure relates to techniques for obtaining a synthetic immunohistochemistry (IHC) image from a histochemically stained image. Particularly, aspects of the present disclosure are directed to accessing an input image that depicts a tissue section that has been stained with at least one histochemical stain; generating a synthetic image by processing the input image using a trained generator network; and outputting the synthetic image. The synthetic image depicts a tissue section that has been stained with at least one IHC stain that targets a first antigen, and techniques may also include receiving an input that is based on a level of expression of a first antigen from the synthetic image and/or generating, from the synthetic image, a value that is based on a level of expression of the first antigen.

Abstract: Disclosed herein are systems and methods for of assessing stain titer levels. An exemplary method includes generating a set of field of views for the image or the region of the image, selecting field of views from the set of field of views that meet predefined criteria, creating a series of patches within each of the selected field of views, retaining patches from the series of patches that meet predefined criteria indicative of a presence of the stain for which the titer is to be estimated, deriving stain color features and stain intensity features pertaining to the stain from the retained patches, estimating a titer score for each of the retained patches based on the stain color features and the stain intensity features, and calculating a weighted average score for the titer of the stain based on the estimated titer score for each of the retained patches.

Abstract: Methods and systems can include: accessing a digital pathology image; generating, using a first machine-learning model, a segmented image that identifies at least: a predicted diseased region and a background region in the digital pathology image; detecting depictions of a set of cells in the digital pathology image; generating, using a second machine-learning model, a cell classification for each cell of the set of cells, wherein the cell classification is selected from a set of potential classifications that indicate which, if any, of a set of biomarkers are expressed in the cell; detecting that a subset of the set of cells are within the background region; and updating the cell classification for each cell of at least some cells in the subset to be a background classification that was not included in the set of potential classifications.

Abstract: Embodiments disclosed herein generally relate to identifying auto-fluorescent artifacts in a multiplexed immunofluorescent image. Particularly, aspects of the present disclosure are directed to accessing a multiplexed immunofluorescent image of a slice of specimen, wherein the multiplexed immunofluorescent image comprises one or more auto-fluorescent artifacts, processing the multiplexed immunofluorescent image using a machine-learning model, wherein an output of the processing corresponds to a prediction that the multiplexed immunofluorescent image includes one or more auto-fluorescent artifacts at one or more particular portions of the multiplexed immunofluorescent image, adjusting subsequent image processing based on the prediction, performing the subsequent image processing, and outputting a result of the subsequent image processing, wherein the result corresponds to a predicted characterization of the specimen.

Abstract: Disclosed herein are systems and methods for of assessing stain titer levels. An exemplary method includes generating a set of field of views for the image or the region of the image, selecting field of views from the set of field of views that meet predefined criteria, creating a series of patches within each of the selected field of views, retaining patches from the series of patches that meet predefined criteria indicative of a presence of the stain for which the titer is to be estimated, deriving stain color features and stain intensity features pertaining to the stain from the retained patches, estimating a titer score for each of the retained patches based on the stain color features and the stain intensity features, and calculating a weighted average score for the titer of the stain based on the estimated titer score for each of the retained patches.

Abstract: The present disclosure relates to techniques for transforming digital pathology images obtained by different slide scanners into a common format for image analysis. Particularly, aspects of the present disclosure are directed to obtaining a source image of a biological specimen, the source image is generated from a first type of scanner, inputting into a generator model a randomly generated noise vector and a latent feature vector from the source image as input data, generating, by the generator model, a new image based on the input data, inputting into a discriminator model the new image, generating, by the discriminator model, a probability for the new image being authentic or fake, determining whether the new image is authentic or fake based on the generated probability, and outputting the new image when the image is authentic.

Abstract: A method and system for classifying field of view (FOV) images of histological slides into various categories that include certain stain patterns, artifacts, and/or other features of interest are provided herein. Few-shot learning (e.g., a prototypical network) techniques are used to train a deep convolutional neural network using a small number of training samples for a small number of image classes for classifying stain images belonging to a larger number of image classes.

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 multiplex image is accessed that depicts a particular slice of a particular sample stained with two or more dyes. Using a Generator network, a predicted singleplex image is generated that depicts the particular slice of the particular sample stained with each of the expressing biomarkers. The Generator network may have been trained by training a machine-learning model using a set of training multiplex images and a set of training singleplex images. Each of the set of training multiplex images depicted a slice of a sample stained with two or more dyes. Each of the set of training singleplex images depicted a slice of a sample stained with a single dye. The machine-learning model included a Discriminator network configured to discriminate whether a given image was generated by the Generator network or was a singleplex image of a real slide. The method further includes outputs the predicted singleplex image.

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.

Abstract: Disclosed herein are systems and methods for of assessing stain titer levels. An exemplary method includes generating a set of field of views for the image or the region of the image, selecting field of views from the set of field of views that meet predefined criteria, creating a series of patches within each of the selected field of views, retaining patches from the series of patches that meet predefined criteria indicative of a presence of the stain for which the titer is to be estimated, deriving stain color features and stain intensity features pertaining to the stain from the retained patches, estimating a titer score for each of the retained patches based on the stain color features and the stain intensity features, and calculating a weighted average score for the titer of the stain based on the estimated titer score for each of the retained patches.

Abstract: The present disclosure relates to techniques for segmenting and detecting cells within image data using transfer learning and a multi-task scheduler. Particularly, aspects of the present disclosure are directed to accessing a plurality of images of one or more cells, extracting three labels from the plurality of images, where the three labels are extracted using a Voronoi transformation, a local clustering, and application of repel code, training, by a multi-task scheduler, a convolutional neural network model based on three loss functions corresponding to the three labels, generating, by the convolutional neural network model, a nuclei probability map and a background probability map for each of the plurality of images based on the training with the three loss functions, and providing the nuclei probability map and the background probability map.

Abstract: Disclosed herein are systems and methods for normalizing the titer of a first stain to a titer of the same stain in a template image. Also disclosed are methods of assessing stain titer levels.

Abstract: An image analysis system for analyzing biological specimen images is disclosed. The system may include: a superpixel generator configured to obtain a biological specimen image and group pixels of the biological specimen image into a plurality of superpixels; a feature extractor configured to extract, from each superpixel in the plurality of superpixels, a feature vector comprising a plurality of image features; a clustering engine configured to assign the plurality of superpixels to a predefined number of clusters, each cluster being characterized by a centroid vector of feature vectors of superpixels assigned to the cluster; and a storage interface configured to store, for each superpixel in the plurality of superpixels, clustering information identifying the one cluster to which the superpixel is assigned. The system may also include a graph engine configured construct a graph based on the stored information, and use the graph to perform a graph-based image processing task.