# Unsupervised Dense Nuclei Detection and Segmentation with Prior Self-activation Map For Histology Images

Source: [Unsupervised Dense Nuclei Detection and Segmentation with Prior Self-activation Map For Histology Images](<https://www.sota2.com/research/paper/68fa6daa1e209131cea3b517>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:40:22.216Z

Authors: Pingyi Chen, Chenglu Zhu, Zhongyi Shui, Jiatong Cai, Sunyi Zheng, Shichuan Zhang, Lin Yang

Published: 2022-10-14T14:34:26.000Z

## Abstract

The success of supervised deep learning models in medical image segmentation relies on detailed annotations. However, labor-intensive manual labeling is costly and inefficient, especially in dense object segmentation. To this end, we propose a self-supervised learning based approach with a Prior Self-activation Module (PSM) that generates self-activation maps from the input images to avoid labeling costs and further produce pseudo masks for the downstream task. To be specific, we firstly train a neural network using self-supervised learning and utilize the gradient information in the shallow layers of the network to generate self-activation maps. Afterwards, a semantic-guided generator is then introduced as a pipeline to transform visual representations from PSM to pixel-level semantic pseudo masks for downstream tasks. Furthermore, a two-stage training module, consisting of a nuclei detection network and a nuclei segmentation network, is adopted to achieve the final segmentation. Experimental results show the effectiveness on two public pathological datasets. Compared with other fully-supervised and weakly-supervised methods, our method can achieve competitive performance without any manual annotations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.07862>)

[PDF](<https://arxiv.org/pdf/2210.07862.pdf>)
