Characterizing Cell Health Using Machine Learning

A machine learning-based approach using microscopic images and pixel-level classification enhances cell health characterization in living cells, addressing the limitations of existing methods by providing accurate scoring and high-throughput analysis.

JP2026506878APending Publication Date: 2026-02-27AKON THERAPEUTICS INC
0 Cites 0 Cited by

Patent Information

Application Number
JP2025545175
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-02-09
Filing Date
2024-02-08
Publication Date
2026-02-27

AI Technical Summary

Technical Problem

Existing methods for characterizing protein movement in living cells are limited by interactions with their dense surroundings, making it difficult to analyze cellular phenomena under physiologically relevant conditions with minimal confounding factors.

Method used

A machine learning-based approach using microscopic images of fluorescently labeled cells, trained with varying compound concentrations and environmental conditions, to assign cell health scores through pixel-level classification and ensemble models, enabling high-throughput single-molecule tracking (SMT) for enhanced characterization.

Benefits of technology

The method provides accurate cell health scoring and characterization under physiologically relevant conditions, minimizing confounding factors and enabling high-throughput analysis of cellular dynamics.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

A sequence of microscopic images, each comprising an array of pixels, visualizing fluorescently labeled cellular components within live cells is received. These images are segmented to identify one or more cells visualized within the images. A machine learning model assigns a cell health score and / or cell health subtype score to each pixel of a particular cell. The cell health scores and / or cell health subtype scores based on these pixels are used to calculate a total cell health score and / or total cell health subtype score for each cell. Data characterizing the calculated scores is provided to a consuming application or process.
Need to check novelty before this filing date? Find Prior Art