Ventana Medical Systems, Inc.

Roche Molecular Systems, Inc.

Leland Stanford Junior University

Lockheed Martin Corporation

Hoffmann-la Roche Inc.

The Cleveland Clinic Foundation

The University of Melbourne

Roche Diagnostics Gmbh

F. Hoffmann-la Roche Ag

Srinivas Chukka

Michael S Barnes

Anindya Sarkar

Ting Chen

Joerg Bredno

Quan Yuan

Christophe Chefd'hotel

Kien Nguyen

Olcay Sertel

Mohammad Qadri

Jim F Martin

Kandavel Shanmugam

Bikash Sabata

Pascal Bamford

Junming Zhu

Ellen Suzue

Rebecca C Bowermaster

Wen-Wei Liu

Christophe Chefd'Hotel

Jianxu Chen

David Knowles

Thomas M Grogan

Yao Nie

Harshal Varangaonkar

Scott Charles Evans

Ronald T Kurnik

William Kenneth Day

Gerardo Fernandez

Noemi Sebastiao

Shalini Singh

Suhas Hanmantrao Patil

Lou Dietz

Auranuch Lorsakul

Alisa Tubbs

Sujit Siddheshwar Chivate

Christoph Guetter

Bonnie LaFleur

Crystal Schemp

Elizabeth Little

Raymond Tubbs

XiuZhong Wang

David Wayne Hagan

Angelika Fuchs

Zhou Lan

Chang Xu

Paul Waring

Rebecca Brown

Michael Tin-Lung Chan

Rahul Bhotika

Ken R Turner

Mohamed Amgad Tageldin

Nikolaus Wick

Robert Ochs

William Day

Jim Martin

Christophe CHEFD´HOTEL

Christophe CHEFD'HOTEL

Michael Barnes

Paul Michael Waring

Christophe Chefd´hotel

Xiuzhong Wang

Bonnie Lafleur

The present disclosure provides for image processing systems and methods for analyzing digital images of biological samples stained for the presence of protein and/or nucleic acid biomarkers and detecting and quantifying signals corresponding to one or more biomarkers. The present disclosure also provides systems and methods for the clinical interpretation of dual ISH slides where the cells to score are selected (e.g. by using one or more cell detection and identification algorithms. By detecting, identifying, and selecting cells for assessment, it is believed that subjectivity is reduced or eliminated. The systems and methods also allow for an increased number of cells to be considered for scoring as compared with manual dot counting methods, thereby increasing detection sensitivity, ultimately enabling improved patient care and treatment.

Systems for automated in situ hybridization analysis

Automated systems and methods are presented for retrospectively analyzing clinical trial data. A plurality of image derived from biological samples of patients in a cohort population are accessed. Image features are computed based on the plurality of images. A diagnostic feature metric is derived based on the computed image features. A cut point value is determined by applying a statistical minimization method using the derived diagnostic feature metric and patient outcome data from the cohort population, in which the cut point value identifies a patient in the cohort population as positive or negative for a diagnostic test.

Computational pathology approach for retrospective analysis of tissue-based companion diagnostic driven clinical trial studies

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.

Group sparsity model for image unmixing

The disclosure relates to devices, systems and methods for image registration and annotation. The devices include computer software products for aligning whole slide digital images on a common grid and transferring annotations from one aligned image to another aligned image on the basis of matching tissue structure. The systems include computer-implemented systems such as work stations and networked computers for accomplishing the tissue-structure based image registration and cross-image annotation. The methods include processes for aligning digital images corresponding to adjacent tissue sections on a common grid based on tissue structure, and transferring annotations from one of the adjacent tissue images to another of the adjacent tissue images. The basis for alignment may be a line-based registration process, wherein sets of lines are computed on the boundary regions computed for the two images, where the boundary regions are obtained using information from two domains—soft-weighted foreground images and gradient magnitude images. The binary mask image, based on whose boundary the line features are computed, may be generated by combining two binary masks—a first binary mask is obtained on thresholding a soft-weighted (continuous valued) foreground image, which is computed based on the stain content in an image, while a second binary mask is obtained after thresholding a gradient magnitude domain image, where the gradient is computed from the grayscale image obtained from the color image.

Line-based image registration and cross-image annotation devices, systems and methods

A computer-based specimen analyzer () is configured to detect a level of expression of genes in a cell sample by detecting dots that represent differently stained genes and chromosomes in a cell. The color of the stained genes and the chromosomes is enhanced and filtered to produce a dot mask that defines areas in the image that are genes, chromosomes, or non-genetic material. Metrics are determined for the dots and/or pixels in the image of the cell in areas corresponding to the dots. The metrics are fed to a classifier that separates genes from chromosomes. The results of the classifier are counted to estimate the expression level of genes in the tissue samples.

System and method for detecting gene expression levels in tissue samples

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.

Methods and systems for evaluation of immune cell infiltrate in tumor samples

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.

Assessing risk of breast cancer recurrence

The present disclosure provides for image processing systems and methods for automatically analyzing digital images of biological samples stained for the presence of protein and/or nucleic acid biomarkers () and automatically detecting and quantifying signals corresponding to one or more biomarkers (). The present disclosure also provides systems and methods for the clinical interpretation of dual ISH slides where the cells to score are automatically selected (e.g. by using one or more cell detection and identification algorithms ()). By automatically detecting, identifying, and selecting cells for assessment, it is believed that subjectivity is reduced or eliminated. The automated systems and methods also allow for an increased number of cells to be considered for scoring as compared with manual dot counting methods, thereby in-creasing detection sensitivity, ultimately enabling improved patient care and treatment.

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.

Systems and methods for meso-dissection

The disclosure relates to devices, systems and methods for image registration and annotation. The devices include computer software products for aligning whole slide digital images on a common grid and transferring annotations from one aligned image to another aligned image on the basis of matching tissue structure. The systems include computer-implemented systems such as work stations and networked computers for accomplishing the tissue-structure based image registration and cross-image annotation. The methods include processes for aligning digital images corresponding to adjacent tissue sections on a common grid based on tissue structure, and transferring annotations from one of the adjacent tissue images to another of the adjacent tissue images. The basis for alignment may be a line-based registration process, wherein sets of lines are computed on the boundary regions computed for the two images, where the boundary regions are obtained using information from two domains&#x2014;soft-weighted foreground images and gradient magnitude images. The binary mask image, based on whose boundary the line features are computed, may be generated by combining two binary masks&#x2014;a first binary mask is obtained on thresholding a soft-weighted (continuous valued) foreground image, which is computed based on the stain content in an image, while a second binary mask is obtained after thresholding a gradient magnitude domain image, where the gradient is computed from the grayscale image obtained from the color image.

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.

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.

Convolutional neural networks for locating objects of interest in images of biological samples

Growing community of inventors

San Jose, CA, United States of America

Srinivas Chukka