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

TL;DR

This paper introduces a novel deep learning method called YOHO that segments early esophageal cancer lesions from a single patient image, achieving high accuracy and addressing privacy and generalization issues.

Contribution

The paper presents the YOHO framework, a single-image deep learning approach that enhances lesion segmentation accuracy while preserving patient privacy and avoiding generalization problems.

Findings

Achieved a mean Dice score of 0.888 on EEC dataset.

Introduced a geometry-based rendering technique for training data generation.

Utilized an edge-enhanced UNet for improved segmentation.

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 approach stands out for its uniqueness, as it relies solely on a single image coming from one 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 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 physicians to utilize their expertise, a geometry-based rendering of a single lesion image to generate the training set (the \emph{biggest} novelty), and an edge-enhanced UNet. We have evaluated YOHO over an EEC data-set created by ourselves and achieved a mean Dice score of 0.888, which represents a significant advance toward clinical applications.