PGU-net+: Progressive Growing of U-net+ for Automated Cervical Nuclei Segmentation

TL;DR

This paper introduces PGU-net+, a progressive growing U-net model with residual modules that independently extract multi-scale features, significantly improving cervical nuclei segmentation accuracy over previous methods.

Contribution

The paper proposes a novel progressive training strategy with residual modules for multi-scale feature extraction in U-net, enhancing segmentation performance.

Findings

PGU-net+ outperforms state-of-the-art methods on Herlev dataset

The progressive training approach improves segmentation accuracy

Residual modules help in learning shape and residual details separately

Abstract

Automated cervical nucleus segmentation based on deep learning can effectively improve the quantitative analysis of cervical cancer. However, accurate nuclei segmentation is still challenging. The classic U-net has not achieved satisfactory results on this task, because it mixes the information of different scales that affect each other, which limits the segmentation accuracy of the model. To solve this problem, we propose a progressive growing U-net (PGU-net+) model, which uses two paradigms to extract image features at different scales in a more independent way. First, we add residual modules between different scales of U-net, which enforces the model to learn the approximate shape of the annotation in the coarser scale, and to learn the residual between the annotation and the approximate shape in the finer scale. Second, we start to train the model with the coarsest part and then progressively add finer part to the training until the full model is included. When we train a finer part, we will reduce the learning rate of the previous coarser part, which further ensures that the model independently extracts information from different scales. We conduct several comparative experiments on the Herlev dataset. The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.