Exploring Unsupervised Cell Recognition with Prior Self-activation Maps

TL;DR

This paper introduces a label-free method using prior self-activation maps for cell recognition, achieving competitive results without manual annotations and enabling multi-class detection in histological images.

Contribution

The paper proposes a novel label-free approach utilizing self-activation maps and semantic clustering for cell recognition, reducing reliance on costly annotations.

Findings

Achieves competitive performance on histological datasets

Enables multi-class cell detection without manual labels

Potential to reduce labeling effort in medical image analysis

Abstract

The success of supervised deep learning models on cell recognition tasks relies on detailed annotations. Many previous works have managed to reduce the dependency on labels. However, considering the large number of cells contained in a patch, costly and inefficient labeling is still inevitable. To this end, we explored label-free methods for cell recognition. Prior self-activation maps (PSM) are proposed to generate pseudo masks as training targets. To be specific, an activation network is trained with self-supervised learning. The gradient information in the shallow layers of the network is aggregated to generate prior self-activation maps. Afterward, a semantic clustering module is then introduced as a pipeline to transform PSMs to pixel-level semantic pseudo masks for downstream tasks. We evaluated our method on two histological datasets: MoNuSeg (cell segmentation) and BCData (multi-class cell detection). Compared with other fully-supervised and weakly-supervised methods, our method can achieve competitive performance without any manual annotations. Our simple but effective framework can also achieve multi-class cell detection which can not be done by existing unsupervised methods. The results show the potential of PSMs that might inspire other research to deal with the hunger for labels in medical area.