Lung Tumor Segmentation in Medical Imaging Using U-NET

Tumors are a deadly condition often triggered by a range of abnormal modifications and genetic abnormalities. Early tumor diagnosis is essential due to the highly concerned nature of the disease. Early detection and treatment of tumors can significantly reduce mortality rates. This paper presents a...

Full description

Saved in:
Bibliographic Details
Main Authors: J Jayapradha, Su-Cheng Haw, Naveen Palanichamy, Senthil Kumar Thillaigovindhan, Mutaz Al-Tarawneh
Format: Article
Language:English
Published: MMU Press 2025-02-01
Series:Journal of Informatics and Web Engineering
Subjects:
Online Access:https://journals.mmupress.com/index.php/jiwe/article/view/1359
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850191762524471296
author J Jayapradha
Su-Cheng Haw
Naveen Palanichamy
Senthil Kumar Thillaigovindhan
Mutaz Al-Tarawneh
author_facet J Jayapradha
Su-Cheng Haw
Naveen Palanichamy
Senthil Kumar Thillaigovindhan
Mutaz Al-Tarawneh
author_sort J Jayapradha
collection DOAJ
description Tumors are a deadly condition often triggered by a range of abnormal modifications and genetic abnormalities. Early tumor diagnosis is essential due to the highly concerned nature of the disease. Early detection and treatment of tumors can significantly reduce mortality rates. This paper presents a model for tumor segmentation in medical imaging that uses the U-NET architecture to increase precision. The model’s encoding and decoding processes have been applied with skip connections to boost performance while simplifying model training. Images were cropped around the lower abdominal regions, and all images used in the study were then resized to 256*256 pixels for standardization. The proposed model deals with the class imbalance using data augmentation and oversampling. The experiments achieved a dice score of 0.853±0.02; F-score of 0.905±0.02; and a sensitivity of 0.897±0.02, compared with various existing models. As part of the model’s application, the pytorch-lightning library is used to successfully identify lung cancer scans, thereby proving to be a precise and efficient method of tumor identification. Accordingly, the study emphasizes the accuracy and speed of the applied model as a useful instrument for the earliest detection of tumors. The proposed approach helps to achieve more relevant and accurate segmentation and thus provides enhancements in medical images analysis if such challenges as an imbalance data set are well handled.
format Article
id doaj-art-3e3de85b95c9462bb538875cadaf80a4
institution OA Journals
issn 2821-370X
language English
publishDate 2025-02-01
publisher MMU Press
record_format Article
series Journal of Informatics and Web Engineering
spelling doaj-art-3e3de85b95c9462bb538875cadaf80a42025-08-20T02:14:46ZengMMU PressJournal of Informatics and Web Engineering2821-370X2025-02-014114015110.33093/jiwe.2025.4.1.111359Lung Tumor Segmentation in Medical Imaging Using U-NETJ Jayapradha0https://orcid.org/0000-0002-2548-9135Su-Cheng Haw1Naveen Palanichamy2Senthil Kumar Thillaigovindhan3Mutaz Al-Tarawneh4SRM Institute of Science and Technology, IndiaMultimedia University, MalaysiaMultimedia University, MalaysiaSRM Institute of Science and Technology, IndiaMutah University, JordanTumors are a deadly condition often triggered by a range of abnormal modifications and genetic abnormalities. Early tumor diagnosis is essential due to the highly concerned nature of the disease. Early detection and treatment of tumors can significantly reduce mortality rates. This paper presents a model for tumor segmentation in medical imaging that uses the U-NET architecture to increase precision. The model’s encoding and decoding processes have been applied with skip connections to boost performance while simplifying model training. Images were cropped around the lower abdominal regions, and all images used in the study were then resized to 256*256 pixels for standardization. The proposed model deals with the class imbalance using data augmentation and oversampling. The experiments achieved a dice score of 0.853±0.02; F-score of 0.905±0.02; and a sensitivity of 0.897±0.02, compared with various existing models. As part of the model’s application, the pytorch-lightning library is used to successfully identify lung cancer scans, thereby proving to be a precise and efficient method of tumor identification. Accordingly, the study emphasizes the accuracy and speed of the applied model as a useful instrument for the earliest detection of tumors. The proposed approach helps to achieve more relevant and accurate segmentation and thus provides enhancements in medical images analysis if such challenges as an imbalance data set are well handled.https://journals.mmupress.com/index.php/jiwe/article/view/1359lung tumoru-netpytorch-lightningsegmentationdata augmentation
spellingShingle J Jayapradha
Su-Cheng Haw
Naveen Palanichamy
Senthil Kumar Thillaigovindhan
Mutaz Al-Tarawneh
Lung Tumor Segmentation in Medical Imaging Using U-NET
Journal of Informatics and Web Engineering
lung tumor
u-net
pytorch-lightning
segmentation
data augmentation
title Lung Tumor Segmentation in Medical Imaging Using U-NET
title_full Lung Tumor Segmentation in Medical Imaging Using U-NET
title_fullStr Lung Tumor Segmentation in Medical Imaging Using U-NET
title_full_unstemmed Lung Tumor Segmentation in Medical Imaging Using U-NET
title_short Lung Tumor Segmentation in Medical Imaging Using U-NET
title_sort lung tumor segmentation in medical imaging using u net
topic lung tumor
u-net
pytorch-lightning
segmentation
data augmentation
url https://journals.mmupress.com/index.php/jiwe/article/view/1359
work_keys_str_mv AT jjayapradha lungtumorsegmentationinmedicalimagingusingunet
AT suchenghaw lungtumorsegmentationinmedicalimagingusingunet
AT naveenpalanichamy lungtumorsegmentationinmedicalimagingusingunet
AT senthilkumarthillaigovindhan lungtumorsegmentationinmedicalimagingusingunet
AT mutazaltarawneh lungtumorsegmentationinmedicalimagingusingunet