Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions.

Journal: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Published Date:

Abstract

Accurate segmentation of lesions is crucial for diagnosis and treatment of early esophageal cancer (EEC). However, neither traditional nor deep learning-based methods up to today can meet the clinical requirements, with the mean Dice score - the most important metric in medical image analysis - hardly exceeding 0.75. In this paper, we present a novel deep learning approach for segmenting EEC lesions. Our method stands out for its uniqueness, as it relies solely on a single input image from a patient, forming the so-called "You-Only-Have-One" (YOHO) framework. On one hand, this "one-image-one-network" learning ensures complete patient privacy as it does not use any images from other patients as the training data. On the other hand, it avoids nearly all generalization-related problems since each trained network is applied only to the same input image itself. In particular, we can push the training to "over-fitting" as much as possible to increase the segmentation accuracy. Our technical details include an interaction with clinical doctors to utilize their expertise, a geometry-based data augmentation over a single lesion image to generate the training dataset (the biggest novelty), and an edge-enhanced UNet. We have evaluated YOHO over an EEC dataset collected by ourselves and achieved a mean Dice score of 0.888, which is much higher as compared to the existing deep-learning methods, thus representing a significant advance toward clinical applications. The code and dataset are available at: https://github.com/lhaippp/YOHO.

Authors

  • Haipeng Li
    Capinfo Company Ltd., Beijing 100010, China.
  • Dingrui Liu
  • Yu Zeng
    School of Environmental Science and Engineering, Guangdong University of Technology, Guangzhou, 510006, PR China.
  • Shuaicheng Liu
    School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan, China.
  • Tao Gan
    Department of Gastroenterology, West China Hospital, Chengdu, Sichuan 610041, China.
  • Nini Rao
    Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu, 610054, China. raonn@uestc.edu.cn.
  • Jinlin Yang
    Department of Gastroenterology, West China Hospital, Chengdu, Sichuan 610041, China.
  • Bing Zeng
    School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan, China.