{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:37:53Z","timestamp":1768207073759,"version":"3.49.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012659","name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diffuse midline glioma (DMG) is a fatal tumor that emerges in the brainstem and thalamus. Compared with microsurgery and chemotherapy, radiotherapy is currently regarded as a safer and more effective treatment option. However, mapping radiotherapy target on brain stem is extremely demanding. In the study, we build a deep learning-based diffuse midline glioma with H3K27M alteration radiotherapy target area automatic delineation model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected contrast-enhanced T1-weighted (T1C), T2-weighted, and T2 fluid attenuated inversion recovery (T2-Flair) sequences from patients with DMG and H3K27M alteration from two medical centers to train and test the model. Based on the framework of generative adversarial networks (GANs), we integrated spatial channel attention mechanism and multi-scale feature extraction according to the characteristics of tumor location in the midline region and diverse morphological changes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The training and test sets included 116 and 26 patients, respectively. In the training set, the segmentation performance was best for the T2 sequence model, with a Dice similarity coefficient (DSC) of 0.916, followed by the T2-Flair sequence model, with a DSC of 0.893; and the T1ce sequence model had the lowest segmentation accuracy, with a DSC of 0.802. In the test set, the DSC values for the T1C, T2, and T2-Flair sequence models were 0.750, 0.872, and 0.862, respectively, demonstrating the strong generalizability of the model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We developed DMG with H3K27M alteration automatic segmentation model based on GANs for the first time. It shows excellent automatic segmentation accuracy and generalizability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2025.1602516","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T05:40:49Z","timestamp":1768196449000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A deep learning-based automatic segmentation model for diffuse midline glioma with H3K27M alteration"],"prefix":"10.3389","volume":"15","author":[{"given":"Yong","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tengyun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuekang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3171\/2019.5.PEDS18376","article-title":"The intersect of neurosurgery with diffuse intrinsic pontine glioma","volume":"24","author":"Kuzan-Fischer","year":"2019","journal-title":"J Neurosurg Pediatr"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2015.00237","article-title":"DIPG in Children - What Can We Learn from the Past","volume":"5","author":"Vanan","year":"2015","journal-title":"Front Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-016-1545-1","article-title":"The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary","volume":"131","author":"Louis","year":"2016","journal-title":"Acta Neuropathol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/nature10833","article-title":"Driver mutations in histone H3.3 and chromatin remodelling genes in paediatric glioblastoma","volume":"482","author":"Schwartzentruber","year":"2012","journal-title":"Nature"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1038\/ng.1102","article-title":"Somatic histone H3 alterations in pediatric diffuse intrinsic pontine gliomas and non-brainstem glioblastomas","volume":"44","author":"Wu","year":"2012","journal-title":"Nat Genet"},{"key":"B6","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.ccell.2019.04.004","article-title":"Pervasive H3K27 Acetylation Leads to ERV Expression and a Therapeutic Vulnerability in H3K27M Gliomas","volume":"35","author":"Krug","year":"2019","journal-title":"Cancer Cell"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2176\/nmc.oa.2019-0168","article-title":"Midline Glioma in Adults: Clinicopathological, Genetic, and Epigenetic Analysis","volume":"60","author":"Enomoto","year":"2020","journal-title":"Neurologia Med-Chir"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noab106","article-title":"The 2021 WHO Classification of Tumors of the Central Nervous System: a summary","volume":"23","author":"Louis","year":"2021","journal-title":"Neuro Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1093\/noajnl\/vdaa142","article-title":"Clinical, radiologic, and genetic characteristics of histone H3 K27M-mutant diffuse midline gliomas in adults","volume":"2","author":"Schulte","year":"2020","journal-title":"Neuro-Oncol Adv"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.4103\/IJPM.IJPM_287_20","article-title":"Diffuse midline glioma-H3K27M mutant. A novel entity with a defining and specific IHC marker","volume":"64","author":"Agarwal","year":"2021","journal-title":"Indian J Pathol Microbiol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"5280","DOI":"10.3390\/cancers13215280","article-title":"New Developments in the Pathogenesis, Therapeutic Targeting, and Treatment of H3K27M-Mutant Diffuse Midline Glioma","volume":"13","author":"Argersinger","year":"2021","journal-title":"Cancers"},{"key":"B12","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11912-020-0877-0","article-title":"Targeting and Therapeutic Monitoring of H3K27M-Mutant Glioma","volume":"22","author":"Wierzbicki","year":"2020","journal-title":"Curr Oncol Rep"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.2176\/nmc.ra.2018-0044","article-title":"MGMT Expression Contributes to Temozolomide Resistance in H3K27M-Mutant Diffuse Midline Gliomas and MGMT Silencing to Temozolomide Sensitivity in IDH-Mutant Gliomas","volume":"58","author":"Abe","year":"2018","journal-title":"Neurologia Med-Chir"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/pbc.28011","article-title":"Challenging the indiscriminate use of temozolomide in pediatric high-grade gliomas: A review of past, current, and emerging therapies","volume":"67","author":"Guerra-Garc\u00eda","year":"2020","journal-title":"Pediatr Blood Cancer"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s11864-001-0074-9","article-title":"Pediatric glial tumors","volume":"2","author":"Cohen","year":"2001","journal-title":"Curr Treat Opt Oncol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"88","DOI":"10.2174\/1570159X14666160509123229","article-title":"Diffuse Intrinsic Pontine Glioma: New Pathophysiological Insights and Emerging Therapeutic Targets","volume":"15","author":"Johung","year":"2017","journal-title":"Curr Neuropharmacology"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2017.00495","article-title":"Potential New Therapies for Pediatric Diffuse Intrinsic Pontine Glioma","volume":"8","author":"Long","year":"2017","journal-title":"Front Pharmacol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)","volume":"34","author":"Menze","year":"2015","journal-title":"IEEE Trans Med Imaging"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.03.011","article-title":"Attention-based multimodal glioma segmentation with multi-attention layers for small-intensity dissimilarity","volume":"35","author":"Liu","year":"2023","journal-title":"J King Saud Univ-Comput Inf Sci"},{"key":"B20","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3233\/XST-190552","article-title":"Improving brain tumor segmentation on MRI based on the deep U-net and residual units","volume":"28","author":"Yang","year":"2020","journal-title":"J X-ray Sci Technol"},{"key":"B21","doi-asserted-by":"publisher","first-page":"103766","DOI":"10.1016\/j.compbiomed.2020.103766","article-title":"3D dense connectivity network with atrous convolutional feature pyramid for brain tumor segmentation in magnetic resonance imaging of human heads","volume":"121","author":"Zhou","year":"2020","journal-title":"Comput Biol Med"},{"key":"B22","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1186\/s12883-022-03026-0","article-title":"MRI comparative study of diffuse midline glioma, H3 K27-altered and glioma in the midline without H3 K27-altered","volume":"22","author":"Zhao","year":"2022","journal-title":"BMC Neurol"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.02314","article-title":"The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification","author":"Baid","year":"2021"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.2196\/27414","article-title":"Accuracy of Using Generative Adversarial Networks for Glaucoma Detection: Systematic Review and Bibliometric Analysis","volume":"23","author":"Saeed","year":"2021","journal-title":"J Med Internet Res"},{"key":"B25","doi-asserted-by":"publisher","first-page":"105063","DOI":"10.1016\/j.compbiomed.2021.105063","article-title":"Generative adversarial networks in medical image segmentation: A review","volume":"140","author":"Xun","year":"2022","journal-title":"Comput Biol Med"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.632","article-title":"Image-to-Image Translation with Conditional Adversarial Networks","author":"Isola","year":"2017"},{"key":"B27","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s12938-019-0682-x","article-title":"Retinal image synthesis from multiple-landmarks input with generative adversarial networks","volume":"18","author":"Yu","year":"2019","journal-title":"Biomed Eng Online"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun ACM"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1109\/ICIP40778.2020.9190882","article-title":"Retinal Vessel Segmentation Under Extreme Low Annotation: A Gan Based Semi-Supervised Approach","author":"Lahiri","year":"2020"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-00928-1_48","article-title":"Concurrent Spatial and Channel \u2018Squeeze & Excitation\u2019 in Fully Convolutional Networks","volume-title":"Medical Image Computing and Computer Assisted Intervention","author":"Roy","year":""},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-023-02965-1","article-title":"mResU-Net: multi-scale residual U-Net-based brain tumor segmentation from multimodal MRI","volume":"62","author":"Li","year":"2023","journal-title":"Med Biol Eng Comput"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.660","article-title":"Pyramid Scene Parsing Network","author":"Zhao","year":"2017"},{"key":"B33","article-title":"CBAM: Convolutional Block Attention\u00a0Module. Computer Vision","volume-title":"ECCV 2018","author":"Woo","year":""},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-24274-9_20","article-title":"CBAM-GAN: Generative Adversarial Networks Based on Convolutional Block Attention Module","volume-title":"Artificial Intelligence and Security","author":"Ma","year":""},{"key":"B35","article-title":"Decoupled Weight Decay Regularization","author":"Loshchilov","year":"2017"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1109\/34.232073","article-title":"Comparing images using the Hausdorff distance","volume":"15","author":"Huttenlocher","year":"1993","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.586197","article-title":"Multimodal Glioma Image Segmentation Using Dual Encoder Structure and Channel Spatial Attention Block","volume":"14","author":"Su","year":"2020","journal-title":"Front Neurosci"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3220902","article-title":"An Attention-Guided CNN Framework for Segmentation and Grading of Glioma Using 3D MRI Scans","volume":"20","author":"Tripathi","year":"2023","journal-title":"IEEE-ACM Trans Comput Biol Bioinf"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst Long Beach Calif USA: Curran Assoc Inc"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.2174\/1573405616666201231100623","article-title":"An Automatic Glioma Segmentation System Using a Multilevel Attention Pyramid Scene Parsing Network","volume":"17","author":"Zhang","year":"2021","journal-title":"Curr Med Imaging"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2020.495075","article-title":"Improvement of Multiparametric MR Image Segmentation by Augmenting the Data With Generative Adversarial Networks for Glioma Patients","volume":"14","author":"Carver","year":"2021","journal-title":"Front Comput Neurosci"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1602516\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T05:40:52Z","timestamp":1768196452000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1602516\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":41,"alternative-id":["10.3389\/fonc.2025.1602516"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1602516","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1602516"}}