Robust Nucleus Detection with Partially Labeled Exemplars

TL;DR

This paper introduces a region-proposal module for Mask R-CNN that enables effective nucleus detection using only partially labeled training data, significantly reducing annotation effort while maintaining high accuracy.

Contribution

It proposes a novel region-proposal method utilizing decomposed self-attention for few-exemplar learning in nucleus detection, reducing the need for fully annotated datasets.

Findings

Achieves comparable detection accuracy with only 25% of nuclei annotated

Utilizes self-attention to propagate labels to unlabeled regions

Enables iterative dataset annotation and correction

Abstract

Quantitative analysis of cell nuclei in microscopic images is an essential yet challenging source of biological and pathological information. The major challenge is accurate detection and segmentation of densely packed nuclei in images acquired under a variety of conditions. Mask R-CNN-based methods have achieved state-of-the-art nucleus segmentation. However, the current pipeline requires fully annotated training images, which are time consuming to create and sometimes noisy. Importantly, nuclei often appear similar within the same image. This similarity could be utilized to segment nuclei with only partially labeled training examples. We propose a simple yet effective region-proposal module for the current Mask R-CNN pipeline to perform few-exemplar learning. To capture the similarities between unlabeled regions and labeled nuclei, we apply decomposed self-attention to learned features. On the self-attention map, we observe strong activation at the centers and edges of all nuclei, including unlabeled nuclei. On this basis, our region-proposal module propagates partial annotations to the whole image and proposes effective bounding boxes for the bounding box-regression and binary mask-generation modules. Our method effectively learns from unlabeled regions thereby improving detection performance. We test our method with various nuclear images. When trained with only 1/4 of the nuclei annotated, our approach retains a detection accuracy comparable to that from training with fully annotated data. Moreover, our method can serve as a bootstrapping step to create full annotations of datasets, iteratively generating and correcting annotations until a predetermined coverage and accuracy are reached. The source code is available at https://github.com/feng-lab/nuclei.