Dynamic Pseudo Label Optimization in Point-Supervised Nuclei Segmentation

TL;DR

DoNuSeg tackles the annotation burden in nuclei instance segmentation by converting point labels into high-quality pseudo-labels through dynamic CAM selection across encoder blocks and CAM-guided contrastive learning. The method decouples detection and semantic segmentation while leveraging location priors from points, optimizing pseudo-labels via $ ext{L}_{det}$, $ ext{L}_{seg}$, $ ext{L}_{loc}$, $ ext{L}_{dcs}$, and $ ext{L}_{ccl}$. On CryoNuSeg, ConSeP, and TNBC, DoNuSeg consistently outperforms state-of-the-art point-supervised methods, with notable gains in AJI, DQ, and PQ, and robust ablation results confirm the benefits of dynamic CAM selection and CAM-guided contrastive learning. The approach reduces labeling cost while delivering competitive, or superior, nuclei instance segmentation performance, which is impactful for pathological image analysis and tumor microenvironment studies.

Abstract

Deep learning has achieved impressive results in nuclei segmentation, but the massive requirement for pixel-wise labels remains a significant challenge. To alleviate the annotation burden, existing methods generate pseudo masks for model training using point labels. However, the generated masks are inevitably different from the ground truth, and these dissimilarities are not handled reasonably during the network training, resulting in the subpar performance of the segmentation model. To tackle this issue, we propose a framework named DoNuSeg, enabling \textbf{D}ynamic pseudo label \textbf{O}ptimization in point-supervised \textbf{Nu}clei \textbf{Seg}mentation. Specifically, DoNuSeg takes advantage of class activation maps (CAMs) to adaptively capture regions with semantics similar to annotated points. To leverage semantic diversity in the hierarchical feature levels, we design a dynamic selection module to choose the optimal one among CAMs from different encoder blocks as pseudo masks. Meanwhile, a CAM-guided contrastive module is proposed to further enhance the accuracy of pseudo masks. In addition to exploiting the semantic information provided by CAMs, we consider location priors inherent to point labels, developing a task-decoupled structure for effectively differentiating nuclei. Extensive experiments demonstrate that DoNuSeg outperforms state-of-the-art point-supervised methods. The code is available at https://github.com/shinning0821/MICCAI24-DoNuSeg.

Figures (5)

• Figure 1: (a) image input; (b) ground truth; (c) Voronoi label; (d) cluster label; (e) LSM label; (f) our initial label $M$; (g) our optimized label $P$. In (b)-(g), red, dark gray and light gray pixels denote nuclei, background and ignored areas, respectively.
• Figure 2: Overview of our DoNuSeg method, which utilizes a Dynamic CAM Selection (DCS) module and a CAM-guided Contrastive Learning (CCL) module to dynamically select and optimize pseudo labels.
• Figure 3: Backbone structure of DoNuSeg. The detection and segmentation head takes hierarchical feature levels in the decoder as their input.
• Figure 4: Visualization comparison of segmentation results on three datasets. Red and black circles indicate the false negative (FN) and false positive (FP) errors. Green circles denote how DoNuSeg corrects these errors.
• Figure 5: Effects (%) of different $r$ and $d$ when generating $M$ on CryoNuSeg.