Weakly supervised nuclei segmentation based on pseudo label correction and uncertainty denoising.
Journal:
Artificial intelligence in medicine
PMID:
40174353
Abstract
Nuclei segmentation plays a vital role in computer-aided histopathology image analysis. Numerous fully supervised learning approaches exhibit amazing performance relying on pathological image with precisely annotations. Whereas, it is difficult and time-consuming in accurate manual labeling on pathological images. Hence, this paper presents a two-stage weakly supervised model including coarse and fine phases, which can achieve nuclei segmentation on whole slide images using only point annotations. In the coarse segmentation step, Voronoi diagram and K-means cluster results are generated based on the point annotations to supervise the training network. In order to cope with the different imaging conditions, an image adaptive clustering pseudo label algorithm is proposed to adapt the color distribution of different images. A Multi-scale Feature Fusion (MFF) module is designed in the decoder to better fusion the feature outputs. Additionally, to reduce the interference of erroneous cluster label, an Exponential Moving Average for cluster label Correction (EMAC) strategy is proposed. After the first step, an uncertainty estimation pseudo label denoising strategy is introduced to denoise Voronoi diagram and adaptive cluster label. In the fine segmentation step, the optimized labels are used for training to obtain the final predicted probability map. Extensive experiments are performed on MoNuSeg and TNBC public benchmarks, which demonstrate our proposed method is superior to other existing nuclei segmentation methods based on point labels. Codes are available at: https://github.com/SSL-droid/WNS-PLCUD.