English

Deep Learning Methods for Lung Cancer Segmentation in Whole-slide Histopathology Images -- the ACDC@LungHP Challenge 2019

Image and Video Processing 2020-08-24 v1 Computer Vision and Pattern Recognition

Abstract

Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology) challenge for evaluating different computer-aided diagnosis (CADs) methods on the automatic diagnosis of lung cancer. The ACDC@LungHP 2019 focused on segmentation (pixel-wise detection) of cancer tissue in whole slide imaging (WSI), using an annotated dataset of 150 training images and 50 test images from 200 patients. This paper reviews this challenge and summarizes the top 10 submitted methods for lung cancer segmentation. All methods were evaluated using the false positive rate, false negative rate, and DICE coefficient (DC). The DC ranged from 0.7354±\pm0.1149 to 0.8372±\pm0.0858. The DC of the best method was close to the inter-observer agreement (0.8398±\pm0.0890). All methods were based on deep learning and categorized into two groups: multi-model method and single model method. In general, multi-model methods were significantly better (p\textit{p}<0.010.01) than single model methods, with mean DC of 0.7966 and 0.7544, respectively. Deep learning based methods could potentially help pathologists find suspicious regions for further analysis of lung cancer in WSI.

Keywords

Cite

@article{arxiv.2008.09352,
  title  = {Deep Learning Methods for Lung Cancer Segmentation in Whole-slide Histopathology Images -- the ACDC@LungHP Challenge 2019},
  author = {Zhang Li and Jiehua Zhang and Tao Tan and Xichao Teng and Xiaoliang Sun and Yang Li and Lihong Liu and Yang Xiao and Byungjae Lee and Yilong Li and Qianni Zhang and Shujiao Sun and Yushan Zheng and Junyu Yan and Ni Li and Yiyu Hong and Junsu Ko and Hyun Jung and Yanling Liu and Yu-cheng Chen and Ching-wei Wang and Vladimir Yurovskiy and Pavel Maevskikh and Vahid Khanagha and Yi Jiang and Xiangjun Feng and Zhihong Liu and Daiqiang Li and Peter J. Schüffler and Qifeng Yu and Hui Chen and Yuling Tang and Geert Litjens},
  journal= {arXiv preprint arXiv:2008.09352},
  year   = {2020}
}