Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT Images
Liver and liver tumor segmentation provides vital biomarkers for surgical planning and hepatic diagnosis. In this paper, we propose and validate a novel level-set method integrating an enhanced edge indicator and an automatically derived initial curve for CT based liver tumor segmentation. At the pr...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9072116/ |
id |
doaj-1a15c208540e4a59a469b2ad9e11edea |
---|---|
record_format |
Article |
spelling |
doaj-1a15c208540e4a59a469b2ad9e11edea2021-03-30T02:11:50ZengIEEEIEEE Access2169-35362020-01-018760567606810.1109/ACCESS.2020.29886479072116Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT ImagesYue Zhang0https://orcid.org/0000-0002-2387-067XBenxiang Jiang1https://orcid.org/0000-0001-5135-7630Jiong Wu2https://orcid.org/0000-0002-8446-6849Dongcen Ji3https://orcid.org/0000-0001-6179-181XYilong Liu4https://orcid.org/0000-0001-9295-7982Yifan Chen5https://orcid.org/0000-0002-2776-9456Ed X. Wu6https://orcid.org/0000-0001-5581-1546Xiaoying Tang7https://orcid.org/0000-0002-7549-6560Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, ChinaDepartment of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, ChinaDepartment of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, ChinaDepartment of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, ChinaLaboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, Hong KongSchool of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, ChinaLaboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, ChinaLiver and liver tumor segmentation provides vital biomarkers for surgical planning and hepatic diagnosis. In this paper, we propose and validate a novel level-set method integrating an enhanced edge indicator and an automatically derived initial curve for CT based liver tumor segmentation. At the preprocessing step, the CT image intensity values were truncated to lie in a fixed range to enhance the image contrast surrounding liver and liver tumor. To remove non-liver tissues for subsequent tumor segmentation, liver was firstly segmented using two convolutional neural networks in a coarse-to-fine manner. A 2D slice-based U-net was used to roughly localize the liver and a 3D patch-based fully convolutional network was used to refine the liver segmentation as well as to roughly localize the liver tumor. A novel level-set method was then presented to further refine the tumor segmentation. Specifically, the probabilistic distribution of the liver tumor was estimated using unsupervised fuzzy c-means clustering, which was then utilized to enhance the edge-detector used in level-set. Effectiveness of the proposed pipeline was validated on two publicly-available datasets. Experimental results identified the superior segmentation performance of the proposed pipeline over state-of-the-art methods.https://ieeexplore.ieee.org/document/9072116/Segmentationconvolutional neural networkliver tumorlevel-setfuzzy c-means |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yue Zhang Benxiang Jiang Jiong Wu Dongcen Ji Yilong Liu Yifan Chen Ed X. Wu Xiaoying Tang |
spellingShingle |
Yue Zhang Benxiang Jiang Jiong Wu Dongcen Ji Yilong Liu Yifan Chen Ed X. Wu Xiaoying Tang Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT Images IEEE Access Segmentation convolutional neural network liver tumor level-set fuzzy c-means |
author_facet |
Yue Zhang Benxiang Jiang Jiong Wu Dongcen Ji Yilong Liu Yifan Chen Ed X. Wu Xiaoying Tang |
author_sort |
Yue Zhang |
title |
Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT Images |
title_short |
Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT Images |
title_full |
Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT Images |
title_fullStr |
Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT Images |
title_full_unstemmed |
Deep Learning Initialized and Gradient Enhanced Level-Set Based Segmentation for Liver Tumor From CT Images |
title_sort |
deep learning initialized and gradient enhanced level-set based segmentation for liver tumor from ct images |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Liver and liver tumor segmentation provides vital biomarkers for surgical planning and hepatic diagnosis. In this paper, we propose and validate a novel level-set method integrating an enhanced edge indicator and an automatically derived initial curve for CT based liver tumor segmentation. At the preprocessing step, the CT image intensity values were truncated to lie in a fixed range to enhance the image contrast surrounding liver and liver tumor. To remove non-liver tissues for subsequent tumor segmentation, liver was firstly segmented using two convolutional neural networks in a coarse-to-fine manner. A 2D slice-based U-net was used to roughly localize the liver and a 3D patch-based fully convolutional network was used to refine the liver segmentation as well as to roughly localize the liver tumor. A novel level-set method was then presented to further refine the tumor segmentation. Specifically, the probabilistic distribution of the liver tumor was estimated using unsupervised fuzzy c-means clustering, which was then utilized to enhance the edge-detector used in level-set. Effectiveness of the proposed pipeline was validated on two publicly-available datasets. Experimental results identified the superior segmentation performance of the proposed pipeline over state-of-the-art methods. |
topic |
Segmentation convolutional neural network liver tumor level-set fuzzy c-means |
url |
https://ieeexplore.ieee.org/document/9072116/ |
work_keys_str_mv |
AT yuezhang deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages AT benxiangjiang deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages AT jiongwu deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages AT dongcenji deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages AT yilongliu deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages AT yifanchen deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages AT edxwu deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages AT xiaoyingtang deeplearninginitializedandgradientenhancedlevelsetbasedsegmentationforlivertumorfromctimages |
_version_ |
1724185598956142592 |