Work

AI enabled live-dead cell viability classification and motion forecasting

Year: 2026

Type: software

Abstract: This repository contains an AI-based framework that segments live vs dead cells from quantitative phase imaging (QPI) data and forecast their future movement. The framework combines a self-attention UNet(for segmentation) with a transformer(for dynamic cell tracking), building upon our paper: [AI-enabled live-dead cell viability classification and motion forecasting]

Source: Code Ocean

DOI: 10.24433/co.8858065.v1

Authors: Anzhe Cheng, Chenzhong Yin, Lamba, Michael A.S., Sertorio, Mathieu, Maldonado, Jorge, Sathler, Alexandre R., Chang, Yu, Catalin Chiritescu, Best-Popescu, Catherine A., Ionascu, Dan, Kotov}, Nicholas, Nazarian, Shahin, Bogdan, Paul

Institution: University of Southern California

Language: English

Topic: Cell Image Analysis Techniques

Subfield: Biophysics

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: green

OpenAlex ID: W7127080416

Cites:

Cited by:

Related to: