E$^2$Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scans

TL;DR

This paper introduces E$^2$Net, a two-stage edge-enhanced neural network that improves the accuracy of liver and tumor segmentation on CT scans by explicitly modeling object edges and boundaries.

Contribution

The work presents a novel edge prediction module and deep cross feature fusion for improved segmentation accuracy, especially with limited labeled data.

Findings

E$^2$Net outperforms state-of-the-art methods in liver and tumor segmentation.

The edge supervision improves boundary accuracy.

The framework is efficient and effective with small datasets.

Abstract

Developing an effective liver and liver tumor segmentation model from CT scans is very important for the success of liver cancer diagnosis, surgical planning and cancer treatment. In this work, we propose a two-stage framework for 2D liver and tumor segmentation. The first stage is a coarse liver segmentation network, while the second stage is an edge enhanced network (E$^2$Net) for more accurate liver and tumor segmentation. E$^2$Net explicitly models complementary objects (liver and tumor) and their edge information within the network to preserve the organ and lesion boundaries. We introduce an edge prediction module in E$^2$Net and design an edge distance map between liver and tumor boundaries, which is used as an extra supervision signal to train the edge enhanced network. We also propose a deep cross feature fusion module to refine multi-scale features from both objects and their edges. E$^2$Net is more easily and efficiently trained with a small labeled dataset, and it can be trained/tested on the original 2D CT slices (resolve resampling error issue in 3D models). The proposed framework has shown superior performance on both liver and liver tumor segmentation compared to several state-of-the-art 2D, 3D and 2D/3D hybrid frameworks.