Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRI

Abstract Automated segmentation of pediatric brain tumors (PBTs) can support precise diagnosis and treatment monitoring, but it is still poorly investigated in literature. This study proposes two different Deep Learning approaches for semantic segmentation of tumor regions in PBTs from MRI scans. Tw...

Full description

Saved in:
Bibliographic Details
Main Authors: Annachiara Cariola, Elena Sibilano, Andrea Guerriero, Vitoantonio Bevilacqua, Antonio Brunetti
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-07257-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238563299786752
author Annachiara Cariola
Elena Sibilano
Andrea Guerriero
Vitoantonio Bevilacqua
Antonio Brunetti
author_facet Annachiara Cariola
Elena Sibilano
Andrea Guerriero
Vitoantonio Bevilacqua
Antonio Brunetti
author_sort Annachiara Cariola
collection DOAJ
description Abstract Automated segmentation of pediatric brain tumors (PBTs) can support precise diagnosis and treatment monitoring, but it is still poorly investigated in literature. This study proposes two different Deep Learning approaches for semantic segmentation of tumor regions in PBTs from MRI scans. Two pipelines were developed for segmenting enhanced tumor (ET), tumor core (TC), and whole tumor (WT) in pediatric gliomas from the BraTS-PEDs 2024 dataset. First, a pre-trained SegResNet model was retrained with a transfer learning approach and tested on the pediatric cohort. Then, two novel multi-encoder architectures leveraging the attention mechanism were designed and trained from scratch. To enhance the performance on ET regions, an ensemble paradigm and post-processing techniques were implemented. Overall, the 3-encoder model achieved the best performance in terms of Dice Score on TC and WT when trained with Dice Loss and on ET when trained with Generalized Dice Focal Loss. SegResNet showed higher recall on TC and WT, and higher precision on ET. After post-processing, we reached Dice Scores of 0.843, 0.869, 0.757 with the pre-trained model and 0.852, 0.876, 0.764 with the ensemble model for TC, WT and ET, respectively. Both strategies yielded state-of-the-art performances, although the ensemble demonstrated significantly superior results. Segmentation of the ET region was improved after post-processing, which increased test metrics while maintaining the integrity of the data.
format Article
id doaj-art-a8028cbff08f46ca909b5938df5b829a
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a8028cbff08f46ca909b5938df5b829a2025-08-20T04:01:34ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-07257-2Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRIAnnachiara Cariola0Elena Sibilano1Andrea Guerriero2Vitoantonio Bevilacqua3Antonio Brunetti4Department of Electrical and Information Engineering, Polytechnic University of BariDepartment of Electrical and Information Engineering, Polytechnic University of BariDepartment of Electrical and Information Engineering, Polytechnic University of BariDepartment of Electrical and Information Engineering, Polytechnic University of BariDepartment of Electrical and Information Engineering, Polytechnic University of BariAbstract Automated segmentation of pediatric brain tumors (PBTs) can support precise diagnosis and treatment monitoring, but it is still poorly investigated in literature. This study proposes two different Deep Learning approaches for semantic segmentation of tumor regions in PBTs from MRI scans. Two pipelines were developed for segmenting enhanced tumor (ET), tumor core (TC), and whole tumor (WT) in pediatric gliomas from the BraTS-PEDs 2024 dataset. First, a pre-trained SegResNet model was retrained with a transfer learning approach and tested on the pediatric cohort. Then, two novel multi-encoder architectures leveraging the attention mechanism were designed and trained from scratch. To enhance the performance on ET regions, an ensemble paradigm and post-processing techniques were implemented. Overall, the 3-encoder model achieved the best performance in terms of Dice Score on TC and WT when trained with Dice Loss and on ET when trained with Generalized Dice Focal Loss. SegResNet showed higher recall on TC and WT, and higher precision on ET. After post-processing, we reached Dice Scores of 0.843, 0.869, 0.757 with the pre-trained model and 0.852, 0.876, 0.764 with the ensemble model for TC, WT and ET, respectively. Both strategies yielded state-of-the-art performances, although the ensemble demonstrated significantly superior results. Segmentation of the ET region was improved after post-processing, which increased test metrics while maintaining the integrity of the data.https://doi.org/10.1038/s41598-025-07257-2Pediatric brain tumorDeep learningTumor segmentationMRI
spellingShingle Annachiara Cariola
Elena Sibilano
Andrea Guerriero
Vitoantonio Bevilacqua
Antonio Brunetti
Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRI
Scientific Reports
Pediatric brain tumor
Deep learning
Tumor segmentation
MRI
title Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRI
title_full Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRI
title_fullStr Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRI
title_full_unstemmed Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRI
title_short Deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric MRI
title_sort deep learning strategies for semantic segmentation of pediatric brain tumors in multiparametric mri
topic Pediatric brain tumor
Deep learning
Tumor segmentation
MRI
url https://doi.org/10.1038/s41598-025-07257-2
work_keys_str_mv AT annachiaracariola deeplearningstrategiesforsemanticsegmentationofpediatricbraintumorsinmultiparametricmri
AT elenasibilano deeplearningstrategiesforsemanticsegmentationofpediatricbraintumorsinmultiparametricmri
AT andreaguerriero deeplearningstrategiesforsemanticsegmentationofpediatricbraintumorsinmultiparametricmri
AT vitoantoniobevilacqua deeplearningstrategiesforsemanticsegmentationofpediatricbraintumorsinmultiparametricmri
AT antoniobrunetti deeplearningstrategiesforsemanticsegmentationofpediatricbraintumorsinmultiparametricmri