{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T06:17:20Z","timestamp":1778566640274,"version":"3.51.4"},"reference-count":17,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Radiol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Data scarcity and class imbalance remain critical challenges in medical image analysis, particularly for brain tumor MRI segmentation, where subcomponents such as enhancing tumor, non-enhancing tumor, cystic component, and peritumoral edema are underrepresented. Existing augmentation strategies, from classical geometric transforms to GAN-based and diffusion model-based synthesis, either lack subcomponent-level control or require extensive generative model training, limiting their practicality in low-data settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We propose the Brain Tumor Compositional Augmentation Pipeline (BT-CAP), a subcomponent-aware and anatomically constrained augmentation framework for multi-modal MRI. BT-CAP decomposes tumor subcomponents and recomposes them through a sequence of targeted operations, including isotropic scaling, B-spline deformation, Powell-optimized spatial rearrangement, inpainting, interface smoothing, and constrained edema deformation, applied consistently across all MRI modalities and segmentation masks, producing label-ready augmented volumes without additional annotation. We evaluated augmentation diversity (SSIM, label distribution, intensity variation, centroid displacement) and anatomical plausibility on 50 BraTS-PEDs 2025 cases, yielding 250 augmented volumes, and assessed segmentation performance on the full 256-case dataset using 3-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>BT-CAP achieved a mean SSIM of 0.956\u2009\u00b1\u20090.014 with wide subcomponent volume change ranges and realistic intensity heterogeneity, confirming meaningful structural diversity. By architectural design, all augmented segmentation mask voxels were confined within brain boundaries, and zero overlap between deformed edema and the tumor core was observed across all 250 cases. Segmentation experiments showed mean Dice score improvements of 6%\u20137% for tumor subcomponents and 2%\u20133% for tumor core and whole tumor compared to training without compositional augmentation, with a computational cost of approximately 2\u2005min per case on CPU.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      BT-CAP establishes a new class of compositional augmentation methods that deliver anatomically structured, label-ready, and scalable data generation without generative model training. The framework is applicable to any multi-class segmentation task where data scarcity and structural fidelity are critical, and is openly available at\n                      <jats:ext-link>https:\/\/github.com\/dramintavallaii\/BT-CAP<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fradi.2026.1785108","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:45:00Z","timestamp":1778564700000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["BT-CAP: a subcomponent-aware and anatomically constrained data augmentation framework for multi-modal brain tumor MRI segmentation"],"prefix":"10.3389","volume":"6","author":[{"given":"Amin","family":"Tavallaii","sequence":"first","affiliation":[{"name":"Computational Neurosurgery Lab, Department of Neurosurgery, Macquarie University","place":["Sydney, NSW, Australia"]},{"name":"Iranian Pediatric Neurosurgery Research Center, Tehran University of Medical Sciences","place":["Tehran, Iran"]},{"name":"Department of Neurosurgery, Mashhad University of Medical Sciences","place":["Mashhad, Iran"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shamim","family":"Shah Ghasi","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Mashhad University of Medical Sciences","place":["Mashhad, Iran"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"U-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat Methods"},{"key":"B2","first-page":"234","article-title":"U\u2013Net: \u201cConvolutional networks for biomedical image segmentation\u201d","volume-title":"Medical Image Computing and Computer\u2013Assisted Intervention \u2013 MICCAI 2015Lecture Notes in Computer Science","author":"Ronneberger","year":"2015"},{"key":"B3","first-page":"488","article-title":"nnu-net revisited: a call for rigorous validation in 3d medical image segmentation","author":"Isensee","year":"2024"},{"key":"B4","author":"Kazerooni","year":"2024"},{"key":"B5","doi-asserted-by":"publisher","first-page":"106405","DOI":"10.1016\/j.compbiomed.2022.106405","article-title":"Brain tumor segmentation of MRI images: a comprehensive review on the application of artificial intelligence tools","volume":"152","author":"Ranjbarzadeh","year":"2023","journal-title":"Comput Biol Med"},{"key":"B6","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"B7","first-page":"1","article-title":"The effectiveness of data augmentation in image classification using deep learning","volume":"11","author":"Wang","year":"2017","journal-title":"Convolutional Neural Netw Vis Recognit"},{"key":"B8","doi-asserted-by":"publisher","first-page":"101552","DOI":"10.1016\/j.media.2019.101552","article-title":"Generative adversarial network in medical imaging: a review","volume":"58","author":"Yi","year":"2019","journal-title":"Med Image Anal"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J Big Data"},{"key":"B10","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.neucom.2018.09.013","article-title":"GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification","volume":"321","author":"Frid-Adar","year":"2018","journal-title":"Neurocomputing"},{"key":"B11","author":"Bowles","year":"2018"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1336902","DOI":"10.3389\/fradi.2023.1336902","article-title":"Using a generative adversarial network to generate synthetic MRI images for multi-class automatic segmentation of brain tumors","volume":"3","author":"Raut","year":"2024","journal-title":"Front Radiol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"120041","DOI":"10.1016\/j.neuroimage.2023.120041","article-title":"Carvemix: a simple data augmentation method for brain lesion segmentation","volume":"271","author":"Zhang","year":"2023","journal-title":"NeuroImage"},{"key":"B14","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1007\/978-3-031-18576-2_12","article-title":"Brain imaging generation with latent diffusion models","volume-title":"Deep Generative Models","author":"Pinaya","year":"2022"},{"key":"B15","first-page":"132","article-title":"A 3D generative model of pathological multi-modal MR images and segmentations","author":"Fernandez","year":"2023"},{"key":"B16","doi-asserted-by":"publisher","first-page":"102789","DOI":"10.1016\/j.media.2023.102789","article-title":"Synthseg: segmentation of brain MRI scans of any contrast and resolution without retraining","volume":"86","author":"Billot","year":"2023","journal-title":"Med Image Anal"},{"key":"B17","author":"de Verdier","year":"2024"}],"container-title":["Frontiers in Radiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fradi.2026.1785108\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:45:03Z","timestamp":1778564703000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fradi.2026.1785108\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,12]]},"references-count":17,"alternative-id":["10.3389\/fradi.2026.1785108"],"URL":"https:\/\/doi.org\/10.3389\/fradi.2026.1785108","relation":{},"ISSN":["2673-8740"],"issn-type":[{"value":"2673-8740","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,12]]},"article-number":"1785108"}}