Bending Loss Regularized Network for Nuclei Segmentation in Histopathology Images
This addresses a specific bottleneck in medical image analysis for histopathology, but it is incremental as it builds on existing segmentation approaches.
The paper tackles the challenge of segmenting overlapped nuclei in histopathology images by proposing a bending loss regularized network, which outperforms six state-of-the-art methods on metrics like Aggregate Jaccard Index and Dice.
Separating overlapped nuclei is a major challenge in histopathology image analysis. Recently published approaches have achieved promising overall performance on public datasets; however, their performance in segmenting overlapped nuclei are limited. To address the issue, we propose the bending loss regularized network for nuclei segmentation. The proposed bending loss defines high penalties to contour points with large curvatures, and applies small penalties to contour points with small curvature. Minimizing the bending loss can avoid generating contours that encompass multiple nuclei. The proposed approach is validated on the MoNuSeg dataset using five quantitative metrics. It outperforms six state-of-the-art approaches on the following metrics: Aggregate Jaccard Index, Dice, Recognition Quality, and Pan-optic Quality.