Hybrid Cascaded Neural Network for Liver Lesion Segmentation

Raunak Dey, Yi Hong
9/11/2019
eess.IVcs.CVcs.LG

Official code: raun1/ISBI-2020-LITS_Hybrid_Comp_Net (10 stars, MIT, last commit 2020-05-23).

Abstract

Automatic liver lesion segmentation is a challenging task while having a significant impact on assisting medical professionals in the designing of effective treatment and planning proper care. In this paper we propose a cascaded system that combines both 2D and 3D convolutional neural networks to effectively segment hepatic lesions. Our 2D network operates on a slice by slice basis to segment the liver and larger tumors, while we use a 3D network to detect small lesions that are often missed in a 2D segmentation design. We employ this algorithm on the LiTS challenge obtaining a Dice score per case of 68.1%, which performs the best among all non pre-trained models and the second best among published methods. We also perform two-fold cross-validation to reveal the over- and under-segmentation issues in the LiTS annotations.

View on arXivView PDF

Code Implementations(1)

raun1/ISBI-2020-LITS_Hybrid_Comp_NetOfficial100%
MIT
102PythonSep 10, 20196 years agoMIT

Similar Papers

Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks

94% match1 repo3012017

Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields

93% match1 repo3012016

Detection-aided liver lesion segmentation using deep learning

91% match1 repo992017

Attention-based CT Scan Interpolation for Lesion Segmentation of Colorectal Liver Metastases

87% match2023

Multi-target and multi-stage liver lesion segmentation and detection in multi-phase computed tomography scans

87% match2024

Research on Tumors Segmentation based on Image Enhancement Method

86% match2024

Cite this paper

@article{dey2019hybrid,
  title  = {Hybrid Cascaded Neural Network for Liver Lesion Segmentation},
  author = {Raunak Dey and Yi Hong},
  year   = {2019},
  eprint = {1909.04797},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1909.04797}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1909.04797.svg)](https://codeofpaper.com/paper/1909.04797)

Discussion