REUR: A unified deep framework for signet ring cell detection in low-resolution pathological images

Shuchang Zhang; Ziyang Yuan; Yadong Wang; Yang Bai; Bo Chen; Hongxia Wang

doi:10.1016/j.compbiomed.2021.104711

REUR: A unified deep framework for signet ring cell detection in low-resolution pathological images

Comput Biol Med. 2021 Sep:136:104711. doi: 10.1016/j.compbiomed.2021.104711. Epub 2021 Aug 5.

Authors

Shuchang Zhang¹, Ziyang Yuan², Yadong Wang³, Yang Bai⁴, Bo Chen⁵, Hongxia Wang⁶

Affiliations

¹ Department of Mathematics, National University of Defense Technology, Changsha, China. Electronic address: zhangshuchang19@163.com.
² Department of Mathematics, National University of Defense Technology, Changsha, China. Electronic address: yuanziyang11@nudt.edu.cn.
³ Department of Laboratory Pathology, Baiyun Branch, Nanfang Hospital, Southern Medical University, Guangzhou, China.
⁴ Department of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
⁵ Suzhou Research Center, Institute of Automation, Chinese Academy of Sciences, Suzhou, China.
⁶ Department of Mathematics, National University of Defense Technology, Changsha, China. Electronic address: wanghongxia@nudt.edu.cn.

PMID: 34388466
DOI: 10.1016/j.compbiomed.2021.104711

Abstract

Detecting signet ring cells (SRCs) in pathological images is essential for carcinoma diagnosis. However, it is time consuming for pathologists to detect SRCs manually from pathological images, and the accuracy of detecting them is also relatively low because of their small sizes. Recently, the exploration of deep learning methods in pathology analysis has been widely investigated by researchers. Nevertheless, the automatic detection of SRCs from real pathological images faces two problems. One is that labeled pathological images are insufficient and usually incomplete. The other is that the training data and the real clinical data have a large difference in resolution. Hence, adopting the transfer learning method affects the performance of deep learning methods. To address these two problems, we present a unified framework named REUR [RetinaNet combining USRNet (unfolding super-resolution network) with the RGHMC (revised gradient harmonizing mechanism classification) loss] that can accurately detect SRCs in low-resolution (LR) pathological images. First, the framework with the super-resolution (SR) module can address the difference in resolution between the training data and the real clinical data. Second, the framework with the label correction module can obtain the revised ground-truth labels from noisy examples, which are embedded into the gradient harmonizing mechanism to acquire the RGHMC loss. The results of the numerical experiments showed that the framework can perform better than other one-stage detectors based on the RetinaNet architecture in the high-resolution (HR) noisy dataset. It achieved a kappa value of 0.74 and an accuracy of 0.89 in the test with 27 randomly selected whole slide images (WSIs), and, thus, it can assist pathologists in better analyzing WSIs. The framework provides an essential method in computer-aided diagnosis for medical applications.

Keywords: Computer-assisted diagnosis; Deep learning; Gastric cancer; Medical image processing; Signet ring cell detection.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Carcinoma, Signet Ring Cell*
Deep Learning*
Diagnosis, Computer-Assisted
Humans