Detecting helicobacter pylori in whole slide images via weakly supervised multi-task learning
- PDF / 6,341,614 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 53 Downloads / 238 Views
Detecting helicobacter pylori in whole slide images via weakly supervised multi-task learning Yongquan Yang 1 & Yiming Yang 1 & Yong Yuan 1 & Jiayi Zheng 2 & Zheng Zhongxi 1 Received: 18 September 2019 / Revised: 12 May 2020 / Accepted: 4 June 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Due to the difficulty to accurately define the morphologies of Helicobacter Pylori (H. pylori) and the complexity of dealing with the whole slide images (WSIs), no computer-aided solution has currently been presented for detecting H. pylori infection in WSIs. We present the first image semantic segmentation solution for the computeraided detection of H. pylori in WSIs. The solution only requires polygon annotations as weak supervision, which roughly, instead of pixel-level accurately, label the H. pylori infected areas in WSIs. We propose a new weakly supervised multi-task learning framework (WSMLF) that aims to improve the segmentation performance by more effectively exploiting the weak supervision. To make more effective usage of the weak supervision, we extract multiple inaccurate targets representing different modes of the true target from the available weak annotations. For improvement of the segmentation performance, we design a weakly supervised multi-task learning algorithm that can automatically learn from the weighted summarization of the extracted multiple inaccurate targets. These two advances constitute the resulting technique WSMLF. Introducing the proposed WSMLF to several common deep image semantic segmentation approaches for the detection of H. pylori in WSIs, we observe that WSMLF can enable these approaches to achieve more reasonable segmentation results, which eventually improve the detection performance of H. pylori by at most 6%. WSMLF provides new thoughts for more effectively employing weak supervision to achieve more effective results for image semantic segmentation. Keywords Helicobacter pylori . Image semantic segmentation . Multi-task learning . Weakly supervised learning
Yongquan Yang and Yiming Yang contributed equally to this work.
* Zheng Zhongxi [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
1 Introduction Background Helicobacter pylori (H. pylori) infection is believed to play a central role in the pathobiology of gastric cancer [47], which is one of the most common malignancies with an estimated one million cases around the world in 2012 [38]. H. pylori induces atrophic gastritis and intestinal metaplasia that would eventually result in the gastric cancer. The International Agency for Research on Cancer has categorized H. pylori as a definite carcinogen [19], due to the risk of gastric cancer in H. pylori-infected patients and the decreased incidence of gastric cancer following H. pylori eradication [48]. Method to detection of H. pylori infection Several methods for testing H. pylori have been proposed, including invasive and noninvasive tests [13]. The typical invasiv
Data Loading...
