DISCo: Deep learning, Instance Segmentation, and Correlations for cell segmentation in calcium imaging

TL;DR

DISCo is a novel deep learning approach that combines temporal pixel correlations and shape information to improve cell segmentation accuracy in calcium imaging videos, outperforming existing models.

Contribution

It introduces a new method that integrates correlation-based and shape-based features for efficient and accurate cell segmentation in calcium imaging data.

Findings

DISCo outperforms all existing models on Neurofinder benchmark.

The method effectively combines temporal correlations with shape information.

DISCo efficiently solves the correlation clustering problem for segmentation.

Abstract

Calcium imaging is one of the most important tools in neurophysiology as it enables the observation of neuronal activity for hundreds of cells in parallel and at single-cell resolution. In order to use the data gained with calcium imaging, it is necessary to extract individual cells and their activity from the recordings. We present DISCo, a novel approach for the cell segmentation in calcium imaging videos. We use temporal information from the recordings in a computationally efficient way by computing correlations between pixels and combine it with shape-based information to identify active as well as non-active cells. We first learn to predict whether two pixels belong to the same cell; this information is summarized in an undirected, edge-weighted grid graph which we then partition. In so doing, we approximately solve the NP-hard correlation clustering problem with a recently proposed greedy algorithm. Evaluating our method on the Neurofinder public benchmark shows that DISCo outperforms all existing models trained on these datasets.