Unsupervised Dense Nuclei Detection and Segmentation with Prior Self-activation Map For Histology Images
This addresses the labor-intensive and costly annotation process in medical image segmentation, particularly for dense objects, though it is incremental as it builds on existing self-supervised techniques.
The paper tackles the problem of dense nuclei detection and segmentation in histology images without manual annotations by proposing a self-supervised learning approach with a Prior Self-activation Module to generate pseudo masks, achieving competitive performance compared to supervised methods on two public datasets.
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.