Staff View: Leveraging u-net architecture for accurate localization in brain tumor segmentation

Leveraging u-net architecture for accurate localization in brain tumor segmentation

This study presents an approach based on deep learning to segment brain tumors in medical imaging accurately. The segmentation of brain tumors plays a crucial role in diagnosing, planning treatments, and monitoring disease progression. However, existing methods have limitations such as time-consumin...

Full description

Saved in:

Bibliographic Details
Main Authors:	Poo, Jeckey Ng Kah, Saealal, Muhammad Salihin, Ibrahim, Mohd Zamri, Yakno, Marlina
Format:	Conference or Workshop Item
Language:	English
Published:	2023
Online Access:	http://eprints.utem.edu.my/id/eprint/27999/1/Leveraging%20U-Net%20architecture%20for%20accurate%20localization%20in%20brain%20tumor%20segmentation.pdf http://eprints.utem.edu.my/id/eprint/27999/ https://ieeexplore.ieee.org/document/10419915
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utem.eprints.27999
record_format	eprints
spelling	my.utem.eprints.279992024-10-16T16:42:43Z http://eprints.utem.edu.my/id/eprint/27999/ Leveraging u-net architecture for accurate localization in brain tumor segmentation Poo, Jeckey Ng Kah Saealal, Muhammad Salihin Ibrahim, Mohd Zamri Yakno, Marlina This study presents an approach based on deep learning to segment brain tumors in medical imaging accurately. The segmentation of brain tumors plays a crucial role in diagnosing, planning treatments, and monitoring disease progression. However, existing methods have limitations such as time-consuming procedures, inadequate accuracy, and delayed detection. The U-Net model architecture, a widely used convolutional neural network (CNN) for medical image segmentation tasks, was employed to segment brain tumors in CT and MRI scans to overcome these challenges. The performance of the U-Net model was evaluated on datasets consisting of 32, 64, and 128 slices, respectively. The results demonstrated the achievement of the highest percentage of mean Intersection Over Union (IOU), with an impressive 80.89% for brain tumor segmentation. These results outperformed other existing methods. The proposed model exhibits the potential to reduce manual segmentation time and subjectivity while enhancing the accuracy of brain tumor diagnosis, treatment planning, and disease monitoring. This research contributes to the field by addressing the problem of brain tumor detection and showcasing the promising results attained using deep learning techniques. This study presents an approach based on deep learning to segment brain tumors in medical imaging accurately. The segmentation of brain tumors plays a crucial role in diagnosing, planning treatments, and monitoring disease progression. However, existing methods have limitations such as time-consuming procedures, inadequate accuracy, and delayed detection. The U-Net model architecture, a widely used convolutional neural network (CNN) for medical image segmentation tasks, was employed to segment brain tumors in CT and MRI scans to overcome these challenges. The performance of the U-Net model was evaluated on datasets consisting of 32, 64, and 128 slices, respectively. The results demonstrated the achievement of the highest percentage of mean Intersection Over Union (IOU), with an impressive 80.89% for brain tumor segmentation. These results outperformed other existing methods. The proposed model exhibits the potential to reduce manual segmentation time and subjectivity while enhancing the accuracy of brain tumor diagnosis, treatment planning, and disease monitoring. This research contributes to the field by addressing the problem of brain tumor detection and showcasing the promising results attained using deep learning techniques. 2023 Conference or Workshop Item PeerReviewed text en http://eprints.utem.edu.my/id/eprint/27999/1/Leveraging%20U-Net%20architecture%20for%20accurate%20localization%20in%20brain%20tumor%20segmentation.pdf Poo, Jeckey Ng Kah and Saealal, Muhammad Salihin and Ibrahim, Mohd Zamri and Yakno, Marlina (2023) Leveraging u-net architecture for accurate localization in brain tumor segmentation. In: 9th IEEE Information Technology International Seminar, ITIS 2023, 18 October 2023through 20 October 2023, Batu Malang. https://ieeexplore.ieee.org/document/10419915
institution	Universiti Teknikal Malaysia Melaka
building	UTEM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknikal Malaysia Melaka
content_source	UTEM Institutional Repository
url_provider	http://eprints.utem.edu.my/
language	English
description	This study presents an approach based on deep learning to segment brain tumors in medical imaging accurately. The segmentation of brain tumors plays a crucial role in diagnosing, planning treatments, and monitoring disease progression. However, existing methods have limitations such as time-consuming procedures, inadequate accuracy, and delayed detection. The U-Net model architecture, a widely used convolutional neural network (CNN) for medical image segmentation tasks, was employed to segment brain tumors in CT and MRI scans to overcome these challenges. The performance of the U-Net model was evaluated on datasets consisting of 32, 64, and 128 slices, respectively. The results demonstrated the achievement of the highest percentage of mean Intersection Over Union (IOU), with an impressive 80.89% for brain tumor segmentation. These results outperformed other existing methods. The proposed model exhibits the potential to reduce manual segmentation time and subjectivity while enhancing the accuracy of brain tumor diagnosis, treatment planning, and disease monitoring. This research contributes to the field by addressing the problem of brain tumor detection and showcasing the promising results attained using deep learning techniques. This study presents an approach based on deep learning to segment brain tumors in medical imaging accurately. The segmentation of brain tumors plays a crucial role in diagnosing, planning treatments, and monitoring disease progression. However, existing methods have limitations such as time-consuming procedures, inadequate accuracy, and delayed detection. The U-Net model architecture, a widely used convolutional neural network (CNN) for medical image segmentation tasks, was employed to segment brain tumors in CT and MRI scans to overcome these challenges. The performance of the U-Net model was evaluated on datasets consisting of 32, 64, and 128 slices, respectively. The results demonstrated the achievement of the highest percentage of mean Intersection Over Union (IOU), with an impressive 80.89% for brain tumor segmentation. These results outperformed other existing methods. The proposed model exhibits the potential to reduce manual segmentation time and subjectivity while enhancing the accuracy of brain tumor diagnosis, treatment planning, and disease monitoring. This research contributes to the field by addressing the problem of brain tumor detection and showcasing the promising results attained using deep learning techniques.
format	Conference or Workshop Item
author	Poo, Jeckey Ng Kah Saealal, Muhammad Salihin Ibrahim, Mohd Zamri Yakno, Marlina
spellingShingle	Poo, Jeckey Ng Kah Saealal, Muhammad Salihin Ibrahim, Mohd Zamri Yakno, Marlina Leveraging u-net architecture for accurate localization in brain tumor segmentation
author_facet	Poo, Jeckey Ng Kah Saealal, Muhammad Salihin Ibrahim, Mohd Zamri Yakno, Marlina
author_sort	Poo, Jeckey Ng Kah
title	Leveraging u-net architecture for accurate localization in brain tumor segmentation
title_short	Leveraging u-net architecture for accurate localization in brain tumor segmentation
title_full	Leveraging u-net architecture for accurate localization in brain tumor segmentation
title_fullStr	Leveraging u-net architecture for accurate localization in brain tumor segmentation
title_full_unstemmed	Leveraging u-net architecture for accurate localization in brain tumor segmentation
title_sort	leveraging u-net architecture for accurate localization in brain tumor segmentation
publishDate	2023
url	http://eprints.utem.edu.my/id/eprint/27999/1/Leveraging%20U-Net%20architecture%20for%20accurate%20localization%20in%20brain%20tumor%20segmentation.pdf http://eprints.utem.edu.my/id/eprint/27999/ https://ieeexplore.ieee.org/document/10419915
_version_	1814061446073417728
score	13.211869

Leveraging u-net architecture for accurate localization in brain tumor segmentation

Similar Items