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: 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: Automated systems and methods for determining the variability between derived expression scores for a series of biomarkers between different identified cell clusters in a whole slide image are presented. The variability between derived expression scores may be a derived inter-marker heterogeneity metric.

Abstract: Immune context scores are calculated for tumor tissue samples using continuous scoring functions. Feature metrics for at least one immune cell marker are calculated for a region or regions of interest, the feature metrics including at least a quantitative measure of human CD3 or total lymphocyte counts. A continuous scoring function is then applied to a feature vector including the feature metric and at least one additional metric related to an immunological biomarker, the output of which is an immune context score. The immune context score may then be plotted as a function of a diagnostic or treatment metric, such as a prognostic metric (e.g. overall survival, disease-specific survival, progression-free survival) or a predictive metric (e.g. likelihood of response to a particular treatment course). The immune context score may then be incorporated into diagnostic and/or treatment decisions.

Abstract: A tissue analysis system and method for the spectral deconvolution of a RGB digital image obtained from a stained biological tissue sample, by estimating the stain component images that are obtained from a staining system configuration, where the reference stain vectors are assumed to be sampled from a known color distribution. The prior knowledge of stain variability of the staining system is adopted as initial reference stain vectors and statistical distribution of their variability. Based on the initial reference stain vectors distribution, the tissue analysis system determines both the reference stain vectors and stain component images of the input image. The image is then deconvoluted based on the reference stain vectors and stain component images.

Abstract: The subject disclosure presents systems and computer-implemented methods for assessing a risk of cancer recurrence in a patient based on a holistic integration of large amounts of prognostic information for said patient into a single comparative prognostic dataset. A risk classification system may be trained using the large amounts of information from a cohort of training slides from several patients, along with survival data for said patients. For example, a machine-learning-based binary classifier in the risk classification system may be trained using a set of granular image features computed from a plurality of slides corresponding to several cancer patients whose survival information is known and input into the system. The trained classifier may be used to classify image features from one or more test patients into a low-risk or high-risk group.

Abstract: 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.

Abstract: The subject disclosure presents systems and computer-implemented methods for assessing a risk of cancer recurrence in a patient based on a holistic integration of large amounts of prognostic information for said patient into a single comparative prognostic dataset. A risk classification system may be trained using the large amounts of information from a cohort of training slides from several patients, along with survival data for said patients. For example, a machine-learning-based binary classifier in the risk classification system may be trained using a set of granular image features computed from a plurality of slides corresponding to several cancer patients whose survival information is known and input into the system. The trained classifier may be used to classify image features from one or more test patients into a low-risk or high-risk group.

Abstract: 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.

Abstract: Heterogeneity for biomarkers in a tissue sample can be calculated. A heterogeneity score can be combined with an immunohistochemistry combination score to provide breast cancer recurrence prognosis. Heterogeneity can be based on percent positivity determinations for a plurality of biomarkers according to how many cells in the sample stain positive. An immunohistochemistry combination score can be calculated. An imaging tool can support a digital pathologist workflow that includes designating fields of view in an image of the tissue sample. Based on the fields of view, a heterogeneity metric can be calculated and combined with an immunohistochemistry combination score to generate a breast cancer recurrence prognosis score.

Abstract: Immune context scores are calculated for tumor tissue samples using continuous scoring functions. Feature metrics for at least one immune cell marker are calculated for a region or regions of interest, the feature metrics including at least a quantitative measure of human CD3 or total lymphocyte counts. A continuous scoring function is then applied to a feature vector including the feature metric and at least one additional metric related to an immunological biomarker, the output of which is an immune context score. The immune context score may then be plotted as a function of a diagnostic or treatment metric, such as a prognostic metric (e.g. overall survival, disease-specific survival, progression-free survival) or a predictive metric (e.g. likelihood of response to a particular treatment course). The immune context score may then be incorporated into diagnostic and/or treatment decisions.

Abstract: The subject disclosure presents systems and methods for improved meso-dissection of biological specimens and tissue slides including importing one or more reference slides with annotations, using inter-marker registration algorithms to automatically map the annotations to an image of a milling slide, and dissecting the annotated tissue from the selected regions in the milling slide for analysis, while concurrently tracking the data and analysis using unique identifiers such as bar codes.

Abstract: Heterogeneity for biomarkers in a tissue sample can be calculated. A heterogeneity score can be combined with an immunohistochemistry combination score to provide breast cancer recurrence prognosis. Heterogeneity can be based on percent positivity determinations for a plurality of biomarkers according to how many cells in the sample stain positive. An immunohistochemistry combination score can be calculated. An imaging tool can support a digital pathologist workflow that includes designating fields of view in an image of the tissue sample. Based on the fields of view, a heterogeneity metric can be calculated and combined with an immunohistochemistry combination score to generate a breast cancer recurrence prognosis score.

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 subject disclosure provides systems, computer-implemented methods, and clinical workflows for meso-dissection of biological specimens and tissue slides by incorporating annotation and inter-marker registration modules within digital pathology imaging and meso-dissection (or milling) systems. Images of a reference slide a milling slide may be acquired using the same imaging system, with the annotations on the image associated with the milling slide being based on the inter-marker registration. Each image along with its respective annotations and meta-data may be associated with a project or a case, and stored in an image management system. A same-marker registration may be used to map annotations from the annotated image of the milling slide to a live image of the milling slide. The milling slide may be milled based on the annotations, with milled tissue output into a contained that is labeled in association with the labeled input slides.

Abstract: Systems and methods described herein relate, among other things, to unmixing more than three stains, while preserving the biological constraints of the biomarkers. Unlimited numbers of markers may be unmixed from a limited-channel image, such as an RGB image, without adding any mathematical complicity to the model. Known co-localization information of different biomarkers within the same tissue section enables defining fixed upper bounds for the number of stains at one pixel. A group sparsity model may be leveraged to explicitly model the fractions of stain contributions from the co-localized biomarkers into one group to yield a least squares solution within the group. A sparse solution may be obtained among the groups to ensure that only a small number of groups with a total number of stains being less than the upper bound are activated.

Abstract: The subject disclosure presents systems and methods for improved meso-dissection of biological specimens and tissue slides including importing one or more reference slides with annotations, using inter-marker registration algorithms to automatically map the annotations to an image of a milling slide, and dissecting the annotated tissue from the selected regions in the milling slide for analysis, while concurrently tracking the data and analysis using unique identifiers such as bar codes.

Abstract: This disclosure describes methods, kits, and systems for scoring the immune response to cancer through examination of tissue infiltrating lymphocytes (TILs). Methods of scoring the immune response in cancer using tissue infiltrating lymphocytes include detecting CD3, CD8, CD20, and FoxP3 within the sample and scoring the detection manually or scoring the digital images of the staining with the aid of image analysis and algorithms.

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 subject disclosure provides systems, computer-implemented methods, and clinical workflows for meso-dissection of biological specimens and tissue slides by incorporating annotation and inter-marker registration modules within digital pathology imaging and meso-dissection (or milling) systems. Images of a reference slide a milling slide may be acquired using the same imaging system, with the annotations on the image associated with the milling slide being based on the inter-marker registration. Each image along with its respective annotations and meta-data may be associated with a project or a case, and stored in an image management system. A same-marker registration may be used to map annotations from the annotated image of the milling slide to a live image of the milling slide. The milling slide may be milled based on the annotations, with milled tissue output into a contained that is labeled in association with the labeled input slides.