University of Southern California

California Institute of Technology

Darryl Shibata

Emil Paskalev Kartalov

Clive R Taylor

David B Agus

Fei Sha

Lawrence A Wade

Rishi Raghav Rawat

Daniel Lee Ruderman

Histologic classification of pathology specimens through machine learning is a nascent field which offers tremendous potential to improve cancer medicine. Its utility has been limited, in part because of differences in tissue preparation and the relative paucity of well-annotated images. We introduce tissue recognition, an unsupervised learning problem analogous to human face recognition, in which the goal is to identify individual tumors using a learned set of histologic features. This feature set is the 'tissue fingerprint.' Because only specimen identities are matched to fingerprints, constructing an algorithm for producing them is a self-learning task that does not need image metadata annotations. Here, we provide an algorithm for self-learning tissue fingerprints, that, in conjunction with color normalization, can match hematoxylin and eosin stained tissues to one of 104 patients with 93% accuracy. We applied this identification network's internal representation as a tissue fingerprint for use in predicting the molecular status of an individual tumor (breast cancer clinical estrogen receptor (ER) status). We describe a fingerprint-based classifier that predicts ER status from whole-slides with high accuracy (AUROC=0.90), and is an improvement over traditional transfer learning approaches. The use of tissue fingerprinting for digital pathology as a concise but meaningful histopathologic image representation enables a new range of machine learning algorithms leading to increased information for clinical decision making in patient management.

Histopathology classification through machine self-learning of 'tissue fingerprints'

Provided herein are devices and methods for the micro-isolation of biological cellular material. A micro-isolation apparatus described can comprise a photomask that protects regions of interest against DNA-destroying illumination. The micro-isolation apparatus can further comprise photosensitive material defining access wells following illumination and subsequent developing of the photosensitive material. The micro-isolation apparatus can further comprise a chambered microfluidic device comprising channels providing access to wells defined in photosensitive material. The micro-isolation apparatus can comprise a chambered microfluidic device without access wells defined in photosensitive material where valves control the flow of gases or liquids through the channels of the microfluidic device. Also included are methods for selectively isolating cellular material using the apparatuses described herein, as are methods for biochemical analysis of individual regions of interest of cellular material using the devices described herein. Further included are methods of making masking arrays useful for the methods described herein.

Methods and devices for micro-isolation, extraction, and/or analysis of microscale components

Growing community of inventors

Rolling Hills Estates, CA, United States of America

Darryl Shibata