CVLGApr 22, 2022

EmbedTrack -- Simultaneous Cell Segmentation and Tracking Through Learning Offsets and Clustering Bandwidths

arXiv:2204.10713v240 citationsh-index: 42
Originality Incremental advance
AI Analysis

This addresses automated cell behavior analysis in biomedical imaging, offering an integrated deep learning solution for a domain-specific task.

The authors tackled simultaneous cell segmentation and tracking in microscopy images by developing EmbedTrack, a CNN that predicts pixel offsets to cell centers and clustering bandwidths, achieving top-3 performance on 7 out of 9 datasets from the Cell Tracking Challenge, including three top-1 results.

A systematic analysis of the cell behavior requires automated approaches for cell segmentation and tracking. While deep learning has been successfully applied for the task of cell segmentation, there are few approaches for simultaneous cell segmentation and tracking using deep learning. Here, we present EmbedTrack, a single convolutional neural network for simultaneous cell segmentation and tracking which predicts easy to interpret embeddings. As embeddings, offsets of cell pixels to their cell center and bandwidths are learned. We benchmark our approach on nine 2D data sets from the Cell Tracking Challenge, where our approach performs on seven out of nine data sets within the top 3 contestants including three top 1 performances. The source code is publicly available at https://git.scc.kit.edu/kit-loe-ge/embedtrack.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes