Entropy Bootstrapping for Weakly Supervised Nuclei Detection

TL;DR

This paper introduces an entropy-based weakly supervised method for nuclei detection that significantly reduces labeling effort while maintaining competitive segmentation performance.

Contribution

It proposes a novel entropy bootstrapping approach using point labels to infer full cell masks, reducing annotation workload by 95%.

Findings

Achieves comparable segmentation accuracy with only 5% of full labels

Uses entropy estimation to approximate cell pixel distribution

Demonstrates effectiveness of weak supervision in microscopy segmentation

Abstract

Microscopy structure segmentation, such as detecting cells or nuclei, generally requires a human to draw a ground truth contour around each instance. Weakly supervised approaches (e.g. consisting of only single point labels) have the potential to reduce this workload significantly. Our approach uses individual point labels for an entropy estimation to approximate an underlying distribution of cell pixels. We infer full cell masks from this distribution, and use Mask-RCNN to produce an instance segmentation output. We compare this point--annotated approach with training on the full ground truth masks. We show that our method achieves a comparatively good level of performance, despite a 95% reduction in pixel labels.