Abstract: Presented herein are systems and methods for detecting labels in biomedical images. A computing system having one or more processors coupled with memory may identify, from a data source, a biomedical image having a first plurality of pixels in a first color representation. The computing system may convert the first plurality of pixels from the first color representation to a second color representation to generate a second plurality of pixels. The computing system may identify, from the second plurality of pixels, a subset of pixels having a color value satisfying a threshold value. The computing system may detect the biomedical image as having at least one label based at least on a number of pixels in the subset of pixels satisfying a threshold count. The computing system may store, in one or more data structures, an indication for the biomedical image as having the at least one label.

Abstract: Described are embodiments of a scalable system for processing whole slide images (WSIs). The system may heavily utilize parallel processing on both central processing units (CPUs) and graphics processing units (GPUs). Images may be decoded on a GPU. Reads may be unbuffered with a low memory footprint. Compute Unified Device Architecture (CUD A) operations may be employed to eliminate many inefficiencies in traditional WSI processing libraries.

Abstract: The present disclosure is directed to systems and methods for identifying regions of interest (ROIs) in images. A computing system may identify an image including an annotation defining an ROI. The image may have a plurality of pixels in a first color space. The computing system may convert the plurality of pixels from the first color space to a second color space to differentiate the annotation from the ROI. The computing system may select a first subset of pixels corresponding to the annotation based at least on a color value of the first subset of pixels in the second color space. The computing system may identify a second subset of pixels included in the ROI from the image using the first subset of pixels. The computing system may store an association between the second subset of pixels and the ROI defined by the annotation in the image.

Abstract: Presented herein are systems and methods of classifying biomedical images. A computing system may identify a first plurality of tiles from a first biomedical image of a first sample. The computing system may determine a first category for the first sample by applying the plurality of tiles to a classification model. The classification model may include a tile encoder to determine, based on the first plurality of tiles, a corresponding plurality of feature vectors in a feature space. The classification model may include a clusterer to select a subset of feature vectors from the plurality of feature vectors based on a plurality of centroids defined in the feature space. The classification model may include an aggregator to generate, based on the subset of feature vectors, the first category for the sample. The computing system may store an association between the first category and the first biomedical image.

Abstract: The present disclosure is directed to systems and methods for identifying regions of interest (ROIs) in images. A computing system may identify an image including an annotation defining an ROI. The image may have a plurality of pixels in a first color space. The computing system may convert the plurality of pixels from the first color space to a second color space to differentiate the annotation from the ROI. The computing system may select a first subset of pixels corresponding to the annotation based at least on a color value of the first subset of pixels in the second color space. The computing system may identify a second subset of pixels included in the ROI from the image using the first subset of pixels. The computing system may store an association between the second subset of pixels and the ROI defined by the annotation in the image.

Abstract: The present disclosure is directed to systems and methods of maintaining databases of biomedical images. A server may aggregate digital pathology records from data sources onto a database. Each record may be generated by a data source using a format, and may identify a biomedical image of a sample and data identifying a subject from which the sample is obtained. The server may receive, from a client device, a query identifying a criterion. The server may access the database to identify a subset of records using the criterion. For each record of the subset, the server may identify a data source that generated the record. The server may select a de-identification policy to apply based on the data source. The server may modify the data in the record according to the de-identification policy and the format. The server may provide, to the client device, the de-identified record.

Abstract: Described herein are systems and methods of determining primary sites from biomedical images. A computing system may identify a first biomedical image of a first sample from one of a primary site or a secondary site associated with a condition in a first subject. The computing system may apply the first biomedical image to a site prediction model comprising a plurality of weights to determine the primary site for the condition. The computing system may store an association between the first biomedical image and the primary site determined using the site prediction model.

Abstract: Described are embodiments of a scalable system for processing whole slide images (WSIs). The system may heavily utilize parallel processing on both central processing units (CPUs) and graphics processing units (GPUs). Images may be decoded on a GPU. Reads may be unbuffered with a low memory footprint. Compute Unified Device Architecture (CUD A) operations may be employed to eliminate many inefficiencies in traditional WSI processing libraries.

Abstract: Described herein are systems and methods of determining primary sites from biomedical images. A computing system may identify a first biomedical image of a first sample from one of a primary site or a secondary site associated with a condition in a first subject. The computing system may apply the first biomedical image to a site prediction model comprising a plurality of weights to determine the primary site for the condition. The computing system may store an association between the first biomedical image and the primary site determined using the site prediction model.

Abstract: The present disclosure is directed to systems and methods for identifying regions of interest (ROIs) in images. A computing system may identify an image including an annotation defining an ROI. The image may have a plurality of pixels in a first color space. The computing system may convert the plurality of pixels from the first color space to a second color space to differentiate the annotation from the ROI. The computing system may select a first subset of pixels corresponding to the annotation based at least on a color value of the first subset of pixels in the second color space. The computing system may identify a second subset of pixels included in the ROI from the image using the first subset of pixels. The computing system may store an association between the second subset of pixels and the ROI defined by the annotation in the image.

Abstract: Described herein are systems and methods of determining primary sites from biomedical images. A computing system may identify a first biomedical image of a first sample from one of a primary site or a secondary site associated with a condition in a first subject. The computing system may apply the first biomedical image to a site prediction model comprising a plurality of weights to determine the primary site for the condition. The computing system may store an association between the first biomedical image and the primary site determined using the site prediction model.