# E2Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scans

arXiv: https://arxiv.org/abs/2007.09791 · HTML: https://mlsanity.com/paper/2007.09791/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [Learning from partially labeled data for multi-organ and tumor segmentation](https://mlsanity.com/paper/2211.06894/) (2022)
- [Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss](https://mlsanity.com/paper/2105.01218/) (2021)
- [Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image Classification](https://mlsanity.com/paper/2208.02851/) (2022)
- [Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection](https://mlsanity.com/paper/2105.01828/) (2021)
- [Towards Simultaneous Segmentation of Liver Tumors and Intrahepatic Vessels via Cross-attention Mechanism](https://mlsanity.com/paper/2302.09785/) (2023)
- [Liver Tumor Screening and Diagnosis in CT with Pixel-Lesion-Patient Network](https://mlsanity.com/paper/2307.08268/) (2023)
- [LIDIA: Precise Liver Tumor Diagnosis on Multi-Phase Contrast-Enhanced CT via Iterative Fusion and Asymmetric Contrastive Learning](https://mlsanity.com/paper/2407.13217/) (2024)
- [Improving Small Lesion Segmentation in CT Scans using Intensity Distribution Supervision: Application to Small Bowel Carcinoid Tumor](https://mlsanity.com/paper/2207.14700/) (2022)
- [Improving Segmentation and Detection of Lesions in CT Scans Using Intensity Distribution Supervision](https://mlsanity.com/paper/2307.05804/) (2023)
- [Super-Resolution Based Patch-Free 3D Image Segmentation with High-Frequency Guidance](https://mlsanity.com/paper/2210.14645/) (2022)
- [PLUS: Plug-and-Play Enhanced Liver Lesion Diagnosis Model on Non-Contrast CT Scans](https://mlsanity.com/paper/2507.03872/) (2025)
- [Sequential Learning on Liver Tumor Boundary Semantics and Prognostic Biomarker Mining](https://mlsanity.com/paper/2103.05170/) (2021)

## Abstract (arXiv)

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 (E2Net) for more accurate liver and tumor segmentation. E2Net 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 E2Net 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. E2Net 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.