A brain tumor segmentation enhancement in MRI images using U-Net and transfer learning

Abstract This paper presents a novel transfer learning approach for segmenting brain tumors in Magnetic Resonance Imaging (MRI) images. Using Fluid-Attenuated Inversion Recovery (FLAIR) abnormality segmentation masks and MRI scans from The Cancer Genome Atlas’s (TCGA’s) lower-grade glioma collection...

Full description

Saved in:
Bibliographic Details
Main Authors: Amin Pourmahboubi, Nazanin Arsalani Saeed, Hamed Tabrizchi
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01837-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738579071205376
author Amin Pourmahboubi
Nazanin Arsalani Saeed
Hamed Tabrizchi
author_facet Amin Pourmahboubi
Nazanin Arsalani Saeed
Hamed Tabrizchi
author_sort Amin Pourmahboubi
collection DOAJ
description Abstract This paper presents a novel transfer learning approach for segmenting brain tumors in Magnetic Resonance Imaging (MRI) images. Using Fluid-Attenuated Inversion Recovery (FLAIR) abnormality segmentation masks and MRI scans from The Cancer Genome Atlas’s (TCGA’s) lower-grade glioma collection, our proposed approach uses a VGG19-based U-Net architecture with fixed pretrained weights. The experimental findings, which show an Area Under the Curve (AUC) of 0.9957, F1-Score of 0.9679, Dice Coefficient of 0.9679, Precision of 0.9541, Recall of 0.9821, and Intersection-over-Union (IoU) of 0.9378, show how effective the proposed framework is. According to these metrics, the VGG19-powered U-Net outperforms not only the conventional U-Net model but also other variants that were compared and used different pre-trained backbones in the U-Net encoder. Clinical trial registration Not applicable as this study utilized existing publicly available dataset and did not involve a clinical trial.
format Article
id doaj-art-998dc213b9334d67a2fd9cceadeda838
institution DOAJ
issn 1471-2342
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-998dc213b9334d67a2fd9cceadeda8382025-08-20T03:06:31ZengBMCBMC Medical Imaging1471-23422025-07-0125112410.1186/s12880-025-01837-4A brain tumor segmentation enhancement in MRI images using U-Net and transfer learningAmin Pourmahboubi0Nazanin Arsalani Saeed1Hamed Tabrizchi2Department of Computer Science, Faculty of Mathematics, Statistics, and Computer Science, University of TabrizDepartment of Biology, Faculty of Natural Science, University of TabrizDepartment of Computer Science, Faculty of Mathematics, Statistics, and Computer Science, University of TabrizAbstract This paper presents a novel transfer learning approach for segmenting brain tumors in Magnetic Resonance Imaging (MRI) images. Using Fluid-Attenuated Inversion Recovery (FLAIR) abnormality segmentation masks and MRI scans from The Cancer Genome Atlas’s (TCGA’s) lower-grade glioma collection, our proposed approach uses a VGG19-based U-Net architecture with fixed pretrained weights. The experimental findings, which show an Area Under the Curve (AUC) of 0.9957, F1-Score of 0.9679, Dice Coefficient of 0.9679, Precision of 0.9541, Recall of 0.9821, and Intersection-over-Union (IoU) of 0.9378, show how effective the proposed framework is. According to these metrics, the VGG19-powered U-Net outperforms not only the conventional U-Net model but also other variants that were compared and used different pre-trained backbones in the U-Net encoder. Clinical trial registration Not applicable as this study utilized existing publicly available dataset and did not involve a clinical trial.https://doi.org/10.1186/s12880-025-01837-4Brain tumor segmentationConvolutional neural networks (CNNs)Deep learningMagnetic resonance imaging (MRI)Medical image analysisNeuroimaging
spellingShingle Amin Pourmahboubi
Nazanin Arsalani Saeed
Hamed Tabrizchi
A brain tumor segmentation enhancement in MRI images using U-Net and transfer learning
BMC Medical Imaging
Brain tumor segmentation
Convolutional neural networks (CNNs)
Deep learning
Magnetic resonance imaging (MRI)
Medical image analysis
Neuroimaging
title A brain tumor segmentation enhancement in MRI images using U-Net and transfer learning
title_full A brain tumor segmentation enhancement in MRI images using U-Net and transfer learning
title_fullStr A brain tumor segmentation enhancement in MRI images using U-Net and transfer learning
title_full_unstemmed A brain tumor segmentation enhancement in MRI images using U-Net and transfer learning
title_short A brain tumor segmentation enhancement in MRI images using U-Net and transfer learning
title_sort brain tumor segmentation enhancement in mri images using u net and transfer learning
topic Brain tumor segmentation
Convolutional neural networks (CNNs)
Deep learning
Magnetic resonance imaging (MRI)
Medical image analysis
Neuroimaging
url https://doi.org/10.1186/s12880-025-01837-4
work_keys_str_mv AT aminpourmahboubi abraintumorsegmentationenhancementinmriimagesusingunetandtransferlearning
AT nazaninarsalanisaeed abraintumorsegmentationenhancementinmriimagesusingunetandtransferlearning
AT hamedtabrizchi abraintumorsegmentationenhancementinmriimagesusingunetandtransferlearning
AT aminpourmahboubi braintumorsegmentationenhancementinmriimagesusingunetandtransferlearning
AT nazaninarsalanisaeed braintumorsegmentationenhancementinmriimagesusingunetandtransferlearning
AT hamedtabrizchi braintumorsegmentationenhancementinmriimagesusingunetandtransferlearning