Weak-to-Strong Generalization Enables Fully Automated De Novo Training of Multi-head Mask-RCNN Model for Segmenting Densely Overlapping Cell Nuclei in Multiplex Whole-slice Brain Images

TL;DR

This paper introduces a fully automated, weak-to-strong generalization approach for training a multi-head Mask-RCNN model that accurately segments overlapping cell nuclei in multiplex whole-slide images without human annotations.

Contribution

The authors propose a novel weak-to-strong generalization methodology enabling de novo training of a multi-head Mask-RCNN for nuclei segmentation across different imaging protocols without manual labels.

Findings

Significant improvement over five existing methods in benchmarks.

Effective pseudo-label correction and coverage expansion demonstrated.

Automated self-diagnosis metrics for segmentation quality introduced.

Abstract

We present a weak to strong generalization methodology for fully automated training of a multi-head extension of the Mask-RCNN method with efficient channel attention for reliable segmentation of overlapping cell nuclei in multiplex cyclic immunofluorescent (IF) whole-slide images (WSI), and present evidence for pseudo-label correction and coverage expansion, the key phenomena underlying weak to strong generalization. This method can learn to segment de novo a new class of images from a new instrument and/or a new imaging protocol without the need for human annotations. We also present metrics for automated self-diagnosis of segmentation quality in production environments, where human visual proofreading of massive WSI images is unaffordable. Our method was benchmarked against five current widely used methods and showed a significant improvement. The code, sample WSI images, and high-resolution segmentation results are provided in open form for community adoption and adaptation.