University of Texas System

Institute for Systems Biology

The State University of New York

The Texas A&m University System

Ilya Shmulevich

Wei Zhang

Ashish Sharma

Edward R Dougherty

Adrian Ozinsky

Tahsin M Kurc

Joel Haskin Saltz

Tianhao Zhao

Arvind Rao

Pekka Ruusuvuori

Rebecca Batiste

John Van Arnam

Jyrki Juhani Selinummi

Pankaj Singh

Rajarsi Gupta

Le Hou

Alexander Lazar

Vu Nguyen

Vesteinn Thorsson

Dimitrios Samaras

A system associated with quantifying a density level of tumor-infiltrating lymphocytes, based on prediction of reconstructed TIL information associated with tumoral tissue image data during pathology analysis of the tissue image data is disclosed. The system receives digitized diagnostic and stained whole-slide image data related to tissue of a particular type of tumoral data. Defined are regions of interest that represents a portion of, or a full image of the whole-slide image data. The image data is encoded into segmented data portions based on convolutional autoencoding of objects associated with the collection of image data. The density of tumor-infiltrating lymphocytes is determined of bounded segmented data portions for respective classification of the regions of interest. A classification label is assigned to the regions of interest. It is determined whether an assigned classification label is above a pre-determined threshold probability value of lymphocyte infiltrated. The threshold probability value is adjusted in order to re-assign the classification label to the regions of interest based on a varied sensitivity level of density of lymphocyte infiltrated. A trained classification model is generated based on the re-assigned classification labels to the regions of interest associated with segmented data portions using the adjusted threshold probability value. An unlabeled image data set is received to iteratively classify the segmented data portions based on a lymphocyte density level associated with portions of the unlabeled image data set, using the trained classification model. Tumor-infiltrating lymphocyte representations are generated based on prediction of TIL information associated with classified segmented data portions. A refined TIL representation based on prediction of the TIL representations is generated using the adjusted threshold probability value associated with the classified segmented data portions. A corresponding method and computer-readable device are also disclosed.

System and method to quantify tumor-infiltrating lymphocytes (TILs) for clinical pathology analysis based on prediction, spatial analysis, molecular correlation, and reconstruction of TIL information identified in digitized tissue images

A system and method for automatically observing and counting cells without using a stain or a fluorescent material. The system includes an optical microscope having a sensor that provides an electrical signal representative of a field of view. The microscope is motorized so as to allow automatic change of focus. A sample containing cells to be analyzed is provided. No stain or fluorescent substance is used. When the microscope is operated in a deliberately out-of-focus condition, cells appear to have either a bright or a dark spot that can be used to report the number of cells in the sample. The intensity variation detected in images acquired in different focal planes is used to identify cell shapes using image analysis software such as CellProfiler. A result is reported in any convenient format, such as a false color image.

Automated analysis of images using bright field microscopy

Embodiments of the invention encompass methods for modeling of complex systems, which include, but are not limited to gene regulatory networks, biological systems, and the like. Other embodiments of the invention include the development of computational tools for the identification and discovery of potential targets for therapeutic intervention in diseases such as cancer. The embodiments discussed utilize methods that model the potential effect of individual genes on the global dynamical network behavior, both from the view of random gene mutation as well as intervention in order to elicit desired network behavior.

Probabilistic boolean networks

Growing community of inventors

Seattle, WA, United States of America

Ilya Shmulevich