SRPN: similarity-based region proposal networks for nuclei and cells detection in histology images

TL;DR

This paper introduces SRPN, a similarity-based region proposal network that enhances nuclei and cell detection in histology images by learning discriminative features, leading to state-of-the-art results.

Contribution

The paper proposes a novel similarity learning module within RPNs, improving classification accuracy for dense object detection in histology images.

Findings

SRPN outperforms existing methods on MoNuSeg benchmark.

SRPN achieves state-of-the-art results on signet ring cell detection.

Similarity learning significantly boosts classification performance.

Abstract

The detection of nuclei and cells in histology images is of great value in both clinical practice and pathological studies. However, multiple reasons such as morphological variations of nuclei or cells make it a challenging task where conventional object detection methods cannot obtain satisfactory performance in many cases. A detection task consists of two sub-tasks, classification and localization. Under the condition of dense object detection, classification is a key to boost the detection performance. Considering this, we propose similarity based region proposal networks (SRPN) for nuclei and cells detection in histology images. In particular, a customized convolution layer termed as embedding layer is designed for network building. The embedding layer is added into the region proposal networks, enabling the networks to learn discriminative features based on similarity learning. Features obtained by similarity learning can significantly boost the classification performance compared to conventional methods. SRPN can be easily integrated into standard convolutional neural networks architectures such as the Faster R-CNN and RetinaNet. We test the proposed approach on tasks of multi-organ nuclei detection and signet ring cells detection in histological images. Experimental results show that networks applying similarity learning achieved superior performance on both tasks when compared to their counterparts. In particular, the proposed SRPN achieve state-of-the-art performance on the MoNuSeg benchmark for nuclei segmentation and detection while compared to previous methods, and on the signet ring cell detection benchmark when compared with baselines. The sourcecode is publicly available at: https://github.com/sigma10010/nuclei_cells_det.