{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:53:55Z","timestamp":1776844435687,"version":"3.51.2"},"reference-count":41,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":21,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"tdm","delay-in-days":21,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate segmentation of brain tumors in magnetic resonance imaging is essential for diagnosis, treatment planning, and surgical guidance. Although deep learning-based segmentation methods have achieved strong performance, their clinical adoption remains limited due to the lack of reliable uncertainty estimation. To address this challenge, we propose an uncertainty-aware framework for multi-class brain tumor sub-region segmentation and evaluate it across several U-Net variants. The study investigates how architectural design choices influence segmentation accuracy and prediction reliability. Specifically, we analyze Attention U-Net, Residual U-Net, squeeze-attention U-Net, and convolutional block attention module U-Net, each incorporating distinct attention mechanisms and feature reuse strategies. All architectures are integrated within a unified Bayesian inference framework using Monte Carlo dropout at test time to approximate posterior sampling. This approach enables pixel-wise and class-specific estimation of epistemic uncertainty along with segmentation outputs. Experiments conducted on the BraTS 2020 dataset show that segmentation accuracy across U-Net variants remains competitive for whole tumor, tumor core, and enhancing tumor regions. However, the generated uncertainty maps reveal distinct spatial patterns, particularly near ambiguous tumor boundaries and anatomically complex regions. These findings demonstrate that uncertainty-aware evaluation provides complementary insights beyond conventional accuracy metrics, improving model interpretability and reliability. Clinically, the integration of Bayesian uncertainty estimation with multiple U-Net backbones produces interpretable segmentation results accompanied by pixel-wise confidence information. Such uncertainty maps can assist radiologists in identifying low-confidence regions, supporting more informed decision-making, reducing inter-observer variability, and increasing trust in automated brain tumor segmentation systems.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae5ca9","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T22:47:32Z","timestamp":1775688452000},"page":"025076","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-aware multi-class brain tumor segmentation using Bayesian U-Net variants"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6119-8297","authenticated-orcid":false,"given":"Rahul","family":"Pal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0476-4783","authenticated-orcid":true,"given":"Sanoj","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0282-3372","authenticated-orcid":true,"given":"Gaurav","family":"Bhatnagar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,4,22]]},"reference":[{"key":"bpexae5ca9bib1","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1016\/j.procs.2015.08.057","type":"journal-article","article-title":"Improved edge detection algorithm for brain tumor segmentation","volume":"58","author":"Aslam","year":"2015","journal-title":"Proc. Comput. Sci."},{"key":"bpexae5ca9bib2","article-title":"The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification","author":"Baid","year":"2021","type":"preprint"},{"key":"bpexae5ca9bib3","author":"Bakas","year":"2017","type":"book"},{"key":"bpexae5ca9bib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2017.117","type":"journal-article","article-title":"Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","author":"Bakas","year":"2017","journal-title":"Sci. Data"},{"key":"bpexae5ca9bib5","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018","type":"preprint"},{"key":"bpexae5ca9bib6","doi-asserted-by":"publisher","DOI":"10.36227\/techrxiv.175492140.09803812\/v1","type":"journal-article","article-title":"Trust-refined U-Net ensemble for uncertainty-aware brain tumor segmentation","author":"Bhamboo","year":"2025","journal-title":"TechRxiv."},{"key":"bpexae5ca9bib7","article-title":"Variance-penalized MC-dropout as a learned smoothing prior for brain tumour segmentation","author":"Chowdhury","year":"2026","type":"preprint"},{"key":"bpexae5ca9bib8","doi-asserted-by":"publisher","first-page":"5310","DOI":"10.1109\/JBHI.2021.3109301","type":"journal-article","article-title":"Self-supervised multi-modal hybrid fusion network for brain tumor segmentation","volume":"26","author":"Fang","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"bpexae5ca9bib9","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1417208","type":"journal-article","article-title":"The peritumoral edema index and related mechanisms influence the prognosis of GBM patients","volume":"14","author":"Fang","year":"2024","journal-title":"Front. Oncol."},{"key":"bpexae5ca9bib10","first-page":"pp 3874","type":"conference-proceedings","article-title":"Multitask learning approach for lung nodule segmentation and classification in CT images","author":"Fernandes","year":"2023"},{"key":"bpexae5ca9bib11","first-page":"p 2","type":"conference-proceedings","article-title":"Dropout as a Bayesian approximation: insights and applications","volume":"vol 1","author":"Gal","year":"2015"},{"key":"bpexae5ca9bib12","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0068","type":"journal-article","article-title":"Inductive biases for deep learning of higher-level cognition","volume":"478","author":"Goyal","year":"2022","journal-title":"Proc. R. Soc. A"},{"key":"bpexae5ca9bib13","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.media.2016.05.004","type":"journal-article","article-title":"Brain tumor segmentation with deep neural networks","volume":"35","author":"Havaei","year":"2017","journal-title":"Med. Image Anal."},{"key":"bpexae5ca9bib14","first-page":"pp 327","type":"conference-proceedings","article-title":"Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-Net neural networks: a BraTS 2020 challenge solution","author":"Henry","year":"2020"},{"key":"bpexae5ca9bib15","doi-asserted-by":"publisher","first-page":"1030","DOI":"10.1109\/TMI.2019.2940555","type":"journal-article","article-title":"Automated muscle segmentation from clinical CT using Bayesian U-Net for personalized musculoskeletal modeling","volume":"39","author":"Hiasa","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae5ca9bib16","doi-asserted-by":"publisher","first-page":"92615","DOI":"10.1109\/ACCESS.2019.2927433","type":"journal-article","article-title":"Brain tumor segmentation using multi-cascaded convolutional neural networks and conditional random field","volume":"7","author":"Hu","year":"2019","journal-title":"IEEE Access"},{"key":"bpexae5ca9bib17","first-page":"pp 483","type":"conference-proceedings","article-title":"Segmenting medical images: from UNet to Res-UNet and nnUNet","author":"Huang","year":"2024"},{"key":"bpexae5ca9bib18","first-page":"pp 106","type":"conference-proceedings","article-title":"HNF-Netv2 for brain tumor segmentation using multi-modal MR imaging","author":"Jia","year":"2021"},{"key":"bpexae5ca9bib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108159","type":"journal-article","article-title":"Delving deep into spatial pooling for squeeze-and-excitation networks","volume":"121","author":"Jin","year":"2022","journal-title":"Pattern Recognit."},{"key":"bpexae5ca9bib20","article-title":"Bayesian neural networks for 2D MRI segmentation","author":"Konathala","year":"2023","type":"preprint"},{"key":"bpexae5ca9bib21","first-page":"pp 189","type":"conference-proceedings","article-title":"Glioma segmentation with cascaded UNet","author":"Lachinov","year":"2018"},{"key":"bpexae5ca9bib22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.59275\/j.melba.2022-354b","type":"journal-article","article-title":"Qu-BraTS: MICCAI BraTS 2020 challenge on quantifying uncertainty in brain tumor segmentation-analysis of ranking scores and benchmarking results","volume":"1","author":"Mehta","year":"2022","journal-title":"J. Mach. Learn. Biomed. Imaging"},{"key":"bpexae5ca9bib23","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","type":"journal-article","article-title":"The multimodal brain tumor image segmentation benchmark (BraTS)","volume":"34","author":"Menze","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae5ca9bib24","article-title":"Bayesian neural networks","author":"Mullachery","year":"2018","type":"preprint"},{"key":"bpexae5ca9bib25","first-page":"pp 1","type":"conference-proceedings","article-title":"Brain tumor segmentation using thresholding, morphological operations and extraction of features of tumor","author":"Murthy","year":"2014"},{"key":"bpexae5ca9bib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101557","type":"journal-article","article-title":"Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation","volume":"59","author":"Nair","year":"2020","journal-title":"Med. Image Anal."},{"key":"bpexae5ca9bib27","article-title":"Attention U-Net: learning where to look for the pancreas","author":"Oktay","year":"2018","type":"preprint"},{"key":"bpexae5ca9bib28","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1109\/TVCG.2010.208","type":"journal-article","article-title":"Uncertainty-aware guided volume segmentation","volume":"16","author":"Prassni","year":"2010","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"bpexae5ca9bib29","first-page":"pp 234","type":"conference-proceedings","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"bpexae5ca9bib30","first-page":"pp 44","type":"conference-proceedings","article-title":"Uncertainty quantification using variational inference for biomedical image segmentation","author":"Sagar","year":"2022"},{"key":"bpexae5ca9bib31","doi-asserted-by":"publisher","DOI":"10.2174\/0115734056344235241217155930","type":"journal-article","article-title":"Advanced CNN architecture for brain tumor segmentation and classification using BraTS-goat 2024 dataset","volume":"21","author":"Satushe","year":"2025","journal-title":"Curr. Med. Imaging"},{"key":"bpexae5ca9bib32","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystems.2020.104226","type":"journal-article","article-title":"A novel method for segmenting brain tumor using modified watershed algorithm in MRI image with FPGA","volume":"198","author":"Sivakumar","year":"2020","journal-title":"Biosystems"},{"key":"bpexae5ca9bib33","first-page":"pp 433","type":"conference-proceedings","article-title":"Boundary-aware fully convolutional network for brain tumor segmentation","author":"Shen","year":"2017"},{"key":"bpexae5ca9bib34","first-page":"pp 1","type":"conference-proceedings","article-title":"Uncertainty-aware brain tumor segmentation in MRI: a Res-UNet framework with Monte Carlo dropout","author":"Varma","year":"2025"},{"key":"bpexae5ca9bib35","first-page":"pp 109","type":"conference-proceedings","article-title":"TransBTS: multimodal brain tumor segmentation using transformer","author":"Wang","year":"2021"},{"key":"bpexae5ca9bib36","first-page":"pp 3","type":"conference-proceedings","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"bpexae5ca9bib37","first-page":"pp 292","type":"conference-proceedings","article-title":"Brain tumor segmentation to calculate percentage tumor using MRI","author":"Wulandari","year":"2018"},{"key":"bpexae5ca9bib38","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-26096-z","type":"journal-article","article-title":"Risk-aware survival time prediction from whole slide pathological images","volume":"12","author":"Xu","year":"2022","journal-title":"Sci. Rep."},{"key":"bpexae5ca9bib39","first-page":"pp 13065","type":"conference-proceedings","article-title":"Squeeze-and-attention networks for semantic segmentation","author":"Zhong","year":"2020"},{"key":"bpexae5ca9bib40","first-page":"pp 3","type":"conference-proceedings","article-title":"UNet++: a nested U-Net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"bpexae5ca9bib41","type":"journal-article","article-title":"Brain Tumor Segmentation (BraTS2020)","author":"Awsaf","year":"2020","journal-title":"Kaggle"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T06:39:34Z","timestamp":1776839974000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae5ca9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4,22]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae5ca9","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]},"assertion":[{"value":"Uncertainty-aware multi-class brain tumor segmentation using Bayesian U-Net variants","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-03-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-04-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-04-22","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}