Fast, Simple Calcium Imaging Segmentation with Fully Convolutional Networks

TL;DR

This paper introduces U-Net2DS, a fast, simple fully convolutional network for calcium imaging neuron segmentation that achieves competitive accuracy with minimal preprocessing, making it practical for large-scale analysis.

Contribution

The paper presents U-Net2DS, a novel, efficient deep learning model for automated calcium imaging segmentation that outperforms existing methods in speed and simplicity.

Findings

Ranks third in Neurofinder competition with F1=0.569

Operates on full images at approximately 9,000 images per minute

Requires minimal domain-specific pre/post-processing

Abstract

Calcium imaging is a technique for observing neuron activity as a series of images showing indicator fluorescence over time. Manually segmenting neurons is time-consuming, leading to research on automated calcium imaging segmentation (ACIS). We evaluated several deep learning models for ACIS on the Neurofinder competition datasets and report our best model: U-Net2DS, a fully convolutional network that operates on 2D mean summary images. U-Net2DS requires minimal domain-specific pre/post-processing and parameter adjustment, and predictions are made on full $512\times512$ images at $\approx$9K images per minute. It ranks third in the Neurofinder competition ($F_1=0.569$) and is the best model to exclusively use deep learning. We also demonstrate useful segmentations on data from outside the competition. The model's simplicity, speed, and quality results make it a practical choice for ACIS and a strong baseline for more complex models in the future.