ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation

Background: Automatic segmentation of liver regions as well as liver lesions such as hepatocellular carcinoma (HCC) from computed tomography (CT) images is critical for accurate diagnosis and therapy planning. With the advent of deep learning techniques such as transformers, computer-aided diagnosti...

Full description

Saved in:
Bibliographic Details
Main Authors: Chukwuemeka Clinton Atabansi, Hui Li, Sheng Wang, Jing Nie, Haijun Liu, Bo Xu, Xichuan Zhou, Dewei Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Translational Engineering in Health and Medicine
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11072178/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849430123464359936
author Chukwuemeka Clinton Atabansi
Hui Li
Sheng Wang
Jing Nie
Haijun Liu
Bo Xu
Xichuan Zhou
Dewei Li
author_facet Chukwuemeka Clinton Atabansi
Hui Li
Sheng Wang
Jing Nie
Haijun Liu
Bo Xu
Xichuan Zhou
Dewei Li
author_sort Chukwuemeka Clinton Atabansi
collection DOAJ
description Background: Automatic segmentation of liver regions as well as liver lesions such as hepatocellular carcinoma (HCC) from computed tomography (CT) images is critical for accurate diagnosis and therapy planning. With the advent of deep learning techniques such as transformers, computer-aided diagnostic tools (CADs) have the potential to increase the accuracy of liver tumor diagnosis, progression, and treatment planning. However, two major challenges remain: 1) existing models struggle to extract robust spatial features for accurate liver and liver lesion segmentation, and 2) publicly available liver datasets with HCC annotations are limited. Methods: We first present a new liver dataset acquired from Chongqing University Cancer Hospital (CCH-LHCC-CT) with HCC annotations. Second, we developed a novel deep learning architecture (ICT-Net), which is constructed based on a pretrained transformer encoder in conjunction with an advanced feature upscaling and enhanced convolution-transformer decoder formation. Results: We performed liver and liver tumor segmentation on the CCH-LHCC-CT and three public CT liver datasets. The proposed ICT-Net architecture achieves superior accuracy (higher ACC/DSC/IoU, lower HD95) across all datasets. Conclusions: We construct a novel deep-learning architecture that produces robust information for liver and liver tumor segmentation. The statistical and visual results demonstrate that the proposed ICT-Net outperforms other existing approaches investigated in this study in terms of ACC, DSC, and IoU. Clinical Translation Statement: ICT-Net enhances surgical planning accuracy through precise tumor margin delineation and improves therapy response assessment reliability, which holds meaningful promise to support more precise and effective clinical therapeutic strategies for patients with HCC.
format Article
id doaj-art-e1d4ffdcf9eb4506b6702506e148b394
institution Kabale University
issn 2168-2372
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Translational Engineering in Health and Medicine
spelling doaj-art-e1d4ffdcf9eb4506b6702506e148b3942025-08-20T03:28:06ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722025-01-011331032210.1109/JTEHM.2025.358647011072178ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region SegmentationChukwuemeka Clinton Atabansi0https://orcid.org/0000-0003-1136-2210Hui Li1https://orcid.org/0000-0001-7287-2690Sheng Wang2Jing Nie3https://orcid.org/0000-0001-9872-9286Haijun Liu4https://orcid.org/0000-0001-5782-4543Bo Xu5https://orcid.org/0000-0001-8693-3060Xichuan Zhou6https://orcid.org/0000-0002-3304-3045Dewei Li7School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaDepartment of Hepatobiliary Pancreatic Tumor Center, Chongqing University Cancer Hospital, Chongqing, ChinaDepartment of Hepatobiliary Pancreatic Tumor Center, Chongqing University Cancer Hospital, Chongqing, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaChongqing Key Laboratory for Intelligent Oncology in Breast Cancer (iCQBC), Chongqing University Cancer Hospital, Chongqing, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing, ChinaDepartment of Hepatobiliary Pancreatic Tumor Center, Chongqing University Cancer Hospital, Chongqing, ChinaBackground: Automatic segmentation of liver regions as well as liver lesions such as hepatocellular carcinoma (HCC) from computed tomography (CT) images is critical for accurate diagnosis and therapy planning. With the advent of deep learning techniques such as transformers, computer-aided diagnostic tools (CADs) have the potential to increase the accuracy of liver tumor diagnosis, progression, and treatment planning. However, two major challenges remain: 1) existing models struggle to extract robust spatial features for accurate liver and liver lesion segmentation, and 2) publicly available liver datasets with HCC annotations are limited. Methods: We first present a new liver dataset acquired from Chongqing University Cancer Hospital (CCH-LHCC-CT) with HCC annotations. Second, we developed a novel deep learning architecture (ICT-Net), which is constructed based on a pretrained transformer encoder in conjunction with an advanced feature upscaling and enhanced convolution-transformer decoder formation. Results: We performed liver and liver tumor segmentation on the CCH-LHCC-CT and three public CT liver datasets. The proposed ICT-Net architecture achieves superior accuracy (higher ACC/DSC/IoU, lower HD95) across all datasets. Conclusions: We construct a novel deep-learning architecture that produces robust information for liver and liver tumor segmentation. The statistical and visual results demonstrate that the proposed ICT-Net outperforms other existing approaches investigated in this study in terms of ACC, DSC, and IoU. Clinical Translation Statement: ICT-Net enhances surgical planning accuracy through precise tumor margin delineation and improves therapy response assessment reliability, which holds meaningful promise to support more precise and effective clinical therapeutic strategies for patients with HCC.https://ieeexplore.ieee.org/document/11072178/Vision transformerliver segmentationhepatocellular carcinoma segmentationliver cancer diagnosisCT images
spellingShingle Chukwuemeka Clinton Atabansi
Hui Li
Sheng Wang
Jing Nie
Haijun Liu
Bo Xu
Xichuan Zhou
Dewei Li
ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation
IEEE Journal of Translational Engineering in Health and Medicine
Vision transformer
liver segmentation
hepatocellular carcinoma segmentation
liver cancer diagnosis
CT images
title ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation
title_full ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation
title_fullStr ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation
title_full_unstemmed ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation
title_short ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation
title_sort ict net an integrated convolution and transformer based network for complex liver and liver tumor region segmentation
topic Vision transformer
liver segmentation
hepatocellular carcinoma segmentation
liver cancer diagnosis
CT images
url https://ieeexplore.ieee.org/document/11072178/
work_keys_str_mv AT chukwuemekaclintonatabansi ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation
AT huili ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation
AT shengwang ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation
AT jingnie ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation
AT haijunliu ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation
AT boxu ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation
AT xichuanzhou ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation
AT deweili ictnetanintegratedconvolutionandtransformerbasednetworkforcomplexliverandlivertumorregionsegmentation