Identifying auto-fluorescent artifacts in a multiplexed immunofluorescent image

Inventors

Lorsakul, Auranuch • Nguyen, Trung Kien • Nie, Yao • Shiffman, Smadar • Wang, Xingwei • Zhao, Zuo

Assignees

Ventana Medical Systems Inc

Abstract

Embodiments disclosed herein generally relate to identifying auto-fluorescent artifacts in a multiplexed immunofluorescent image. Particularly, aspects of the present disclosure are directed to accessing a multiplexed immunofluorescent image of a slice of specimen, wherein the multiplexed immunofluorescent image comprises one or more auto-fluorescent artifacts, processing the multiplexed immunofluorescent image using a machine-learning model, wherein an output of the processing corresponds to a prediction that the multiplexed immunofluorescent image includes one or more auto-fluorescent artifacts at one or more particular portions of the multiplexed immunofluorescent image, adjusting subsequent image processing based on the prediction, performing the subsequent image processing, and outputting a result of the subsequent image processing, wherein the result corresponds to a predicted characterization of the specimen.

Core Innovation

The invention provides a computer-implemented method, system, and computer-program product for analyzing a multiplexed immunofluorescent image of a slice of specimen. The multiplexed immunofluorescent image comprises one or more auto-fluorescent artifacts, and a machine-learning model processes the image to generate an output corresponding to a prediction that the image includes one or more auto-fluorescent artifacts at one or more particular portions of the image.

Based on the prediction, subsequent image processing is adjusted and then performed. The adjusted subsequent image processing uses the predicted artifact locations or portions to produce a result corresponding to a predicted characterization of the specimen.

In certain implementations, the subsequent image processing determines, for each region of the multiplexed immunofluorescent image, whether at least one metric exceeds a predefined threshold, where the metric includes part of or is generated from the output of the processing. In certain implementations, the subsequent image processing performs detection and characterization of tumor cells by providing a characterization based on presence, quantity, or size.

Claims Coverage

The document provides three independent claim sets that cover a computer-implemented method, a system with processors and non-transitory computer-readable storage, and a computer-program product. Across these independent claims, there are three main inventive features: artifact prediction in multiplexed immunofluorescent image portions, adjustment of subsequent image processing based on that prediction, and outputting a predicted characterization of the specimen.

All independent claims share the same core coverage: a machine-learning model predicts auto-fluorescent artifacts at particular portions of a multiplexed immunofluorescent image, subsequent image processing is adjusted based on the prediction, and the system outputs a predicted characterization of the specimen.

Stated Advantages

Documented Applications