An experimental study of U-net variants on liver segmentation from CT scans

The liver, a complex and important organ in the human body, is crucial to many physiological processes. For the diagnosis and ongoing monitoring of a wide spectrum of liver diseases, an accurate segmentation of the liver from medical imaging is essential. The importance of liver segmentation in clin...

Full description

Saved in:
Bibliographic Details
Main Authors: Halder Akash, Sau Arup, Majumder Surya, Kaplun Dmitrii, Sarkar Ram
Format: Article
Language:English
Published: De Gruyter 2025-03-01
Series:Journal of Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1515/jisys-2024-0185
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850250157463961600
author Halder Akash
Sau Arup
Majumder Surya
Kaplun Dmitrii
Sarkar Ram
author_facet Halder Akash
Sau Arup
Majumder Surya
Kaplun Dmitrii
Sarkar Ram
author_sort Halder Akash
collection DOAJ
description The liver, a complex and important organ in the human body, is crucial to many physiological processes. For the diagnosis and ongoing monitoring of a wide spectrum of liver diseases, an accurate segmentation of the liver from medical imaging is essential. The importance of liver segmentation in clinical practice is examined in this research, along with the difficulties in attaining accurate segmentation masks, particularly when working with small structures and precise details. This study investigates the performance of ten well-known U-Net models, including Vanilla U-Net, Attention U-Net, V-Net, U-Net 3+, R2U-Net, U2{{\rm{U}}}^{2}-Net, U-Net++, Res U-Net, Swin-U-Net, and Trans-U-Net. These variations have become optimal approaches to liver segmentation, each providing certain benefits and addressing particular difficulties. We have conducted this research on computed tomography scan images from three standard datasets, namely, 3DIRCADb, CHAOS, and LiTS datasets. The U-Net architecture has become a mainstay in contemporary research on medical picture segmentation due to its success in preserving contextual information and capturing fine features. The structural and functional characteristics that help it perform well on liver segmentation tasks even with scant annotated data are well highlighted in this study. The code and additional results can be found in the Github https://github.com/akalder/ComparativeStudyLiverSegmentation.
format Article
id doaj-art-eaa9d71db2144c0a9721bdd99eb952f9
institution OA Journals
issn 2191-026X
language English
publishDate 2025-03-01
publisher De Gruyter
record_format Article
series Journal of Intelligent Systems
spelling doaj-art-eaa9d71db2144c0a9721bdd99eb952f92025-08-20T01:58:18ZengDe GruyterJournal of Intelligent Systems2191-026X2025-03-013411040357110.1515/jisys-2024-0185An experimental study of U-net variants on liver segmentation from CT scansHalder Akash0Sau Arup1Majumder Surya2Kaplun Dmitrii3Sarkar Ram4Department of Computer Science and Engineering, Jadavpur University, Jadavpur, Kolkata, West Bengal 700032, IndiaDepartment of Computer Science and Engineering, Institute of Engineering and Management, Kolkata 700032, IndiaDepartment of Computer Science and Engineering, Heritage Institute of Technology, Kolkata, West Bengal 700107, IndiaDepartment of Automation and Control Processes, Saint Petersburg Electrotechnical University “LETI”, St Petersburg 197022, RussiaDepartment of Computer Science and Engineering, Jadavpur University, Jadavpur, Kolkata, West Bengal 700032, IndiaThe liver, a complex and important organ in the human body, is crucial to many physiological processes. For the diagnosis and ongoing monitoring of a wide spectrum of liver diseases, an accurate segmentation of the liver from medical imaging is essential. The importance of liver segmentation in clinical practice is examined in this research, along with the difficulties in attaining accurate segmentation masks, particularly when working with small structures and precise details. This study investigates the performance of ten well-known U-Net models, including Vanilla U-Net, Attention U-Net, V-Net, U-Net 3+, R2U-Net, U2{{\rm{U}}}^{2}-Net, U-Net++, Res U-Net, Swin-U-Net, and Trans-U-Net. These variations have become optimal approaches to liver segmentation, each providing certain benefits and addressing particular difficulties. We have conducted this research on computed tomography scan images from three standard datasets, namely, 3DIRCADb, CHAOS, and LiTS datasets. The U-Net architecture has become a mainstay in contemporary research on medical picture segmentation due to its success in preserving contextual information and capturing fine features. The structural and functional characteristics that help it perform well on liver segmentation tasks even with scant annotated data are well highlighted in this study. The code and additional results can be found in the Github https://github.com/akalder/ComparativeStudyLiverSegmentation.https://doi.org/10.1515/jisys-2024-0185liver cancerliver segmentationmedical imagingct scanu-netdeep learning
spellingShingle Halder Akash
Sau Arup
Majumder Surya
Kaplun Dmitrii
Sarkar Ram
An experimental study of U-net variants on liver segmentation from CT scans
Journal of Intelligent Systems
liver cancer
liver segmentation
medical imaging
ct scan
u-net
deep learning
title An experimental study of U-net variants on liver segmentation from CT scans
title_full An experimental study of U-net variants on liver segmentation from CT scans
title_fullStr An experimental study of U-net variants on liver segmentation from CT scans
title_full_unstemmed An experimental study of U-net variants on liver segmentation from CT scans
title_short An experimental study of U-net variants on liver segmentation from CT scans
title_sort experimental study of u net variants on liver segmentation from ct scans
topic liver cancer
liver segmentation
medical imaging
ct scan
u-net
deep learning
url https://doi.org/10.1515/jisys-2024-0185
work_keys_str_mv AT halderakash anexperimentalstudyofunetvariantsonliversegmentationfromctscans
AT sauarup anexperimentalstudyofunetvariantsonliversegmentationfromctscans
AT majumdersurya anexperimentalstudyofunetvariantsonliversegmentationfromctscans
AT kaplundmitrii anexperimentalstudyofunetvariantsonliversegmentationfromctscans
AT sarkarram anexperimentalstudyofunetvariantsonliversegmentationfromctscans
AT halderakash experimentalstudyofunetvariantsonliversegmentationfromctscans
AT sauarup experimentalstudyofunetvariantsonliversegmentationfromctscans
AT majumdersurya experimentalstudyofunetvariantsonliversegmentationfromctscans
AT kaplundmitrii experimentalstudyofunetvariantsonliversegmentationfromctscans
AT sarkarram experimentalstudyofunetvariantsonliversegmentationfromctscans