{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T06:10:15Z","timestamp":1783923015538,"version":"3.55.0"},"reference-count":59,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"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. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Detecting brain lesions using Artificial Intelligence methods has been a focus of prior research, with numerous datasets supporting this task to improve clinical results. However, evaluation metrics and reported results often summarise overall performance without considering variations in lesion size. In clinical practice, the detection of small tumours is particularly critical for early diagnosis and treatment effectiveness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study evaluates the performance of Artificial Intelligence models on established datasets with a specific focus on lesion identification and lesion size. We introduce a novel Deep Learning model tailored to detect small brain tumours in Magnetic Resonance Imaging, integrating a clinically defined \u201csmall tumour\u201d concept into both the training and evaluation processes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed approach demonstrates robust performance, achieving loss values ranging from 1.5 to 11.1 and Dice Scores between 96.3% and 98.1% across multiple datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The main contribution of this work is the incorporation of clinically meaningful lesion-size information into model development and assessment. These findings suggest that explicitly considering small tumours can improve the clinical relevance of Artificial Intelligence systems for brain lesion detection and support earlier diagnosis and more effective treatment planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2026.1833713","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:33:27Z","timestamp":1783920807000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the detection of small brain lesions in magnetic resonance using deep learning"],"prefix":"10.3389","volume":"20","author":[{"given":"Alberto","family":"Nogales","sequence":"first","affiliation":[{"name":"CEIEC, Research Institute, Universidad Francisco de Vitoria","place":["Pozuelo de Alarc\u00f3n, Spain"]},{"name":"University of Alcal\u00e1 (UAH) Computer Science Department","place":["Alcal\u00e1 de Henares, Spain"]},{"name":"Instituto Ram\u00f3n y Cajal para la Investigaci\u00f3n en Salud (IRYCIS), Biomedical Data Science and Engineering Group, IRYCIS","place":["Madrid, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel \u00c1ngel","family":"Sicilia","sequence":"additional","affiliation":[{"name":"University of Alcal\u00e1 (UAH) Computer Science Department","place":["Alcal\u00e1 de Henares, Spain"]},{"name":"Instituto Ram\u00f3n y Cajal para la Investigaci\u00f3n en Salud (IRYCIS), Biomedical Data Science and Engineering Group, IRYCIS","place":["Madrid, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolina","family":"de la Pinta","sequence":"additional","affiliation":[{"name":"Radiation Oncology Department, Ram\u00f3n y Cajal Hospital, Biomarkers and Therapeutic Targets Group, IRYCIS","place":["Madrid, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Garc\u00eda-Barriocanal","sequence":"additional","affiliation":[{"name":"University of Alcal\u00e1 (UAH) Computer Science Department","place":["Alcal\u00e1 de Henares, Spain"]},{"name":"Instituto Ram\u00f3n y Cajal para la Investigaci\u00f3n en Salud (IRYCIS), Biomedical Data Science and Engineering Group, IRYCIS","place":["Madrid, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c1lvaro J.","family":"Garc\u00eda-Tejedor","sequence":"additional","affiliation":[{"name":"CEIEC, Research Institute, Universidad Francisco de Vitoria","place":["Pozuelo de Alarc\u00f3n, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego","family":"Guadalupe","sequence":"additional","affiliation":[{"name":"CEIEC, Research Institute, Universidad Francisco de Vitoria","place":["Pozuelo de Alarc\u00f3n, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"108105","DOI":"10.1016\/j.compeleceng.2022.108105","article-title":"A deep learning approach for brain tumor classification using MRI images","volume":"101","author":"Aamir","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"ref2","first-page":"2623","author":"Akiba","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.3390\/diagnostics12081812","article-title":"Breast cancer detection in mammography images using deep convolutional neural networks and fuzzy ensemble modeling techniques","volume":"12","author":"Altameem","year":"2022","journal-title":"Diagnostics"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"109353","DOI":"10.1016\/j.compbiomed.2024.109353","article-title":"LATUP-net: a lightweight 3D attention U-net with parallel convolutions for brain tumor segmentation","volume":"184","author":"Alwadee","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"3161","DOI":"10.1007\/s40747-021-00563-y","article-title":"Brain tumor detection and classification using machine learning: a comprehensive survey","volume":"8","author":"Amin","year":"2022","journal-title":"Complex Intell. Syst."},{"key":"ref6","volume-title":"The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification","author":"Baid","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.future.2020.08.005","article-title":"ABCDM: an attention-based bidirectional CNN-RNN deep model for sentiment analysis","volume":"115","author":"Basiri","year":"2021","journal-title":"Futur. Gener. Comput. Syst."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"15849","DOI":"10.1073\/pnas.1903070116","article-title":"Reconciling modern machine-learning practice and the classical bias--variance trade-off","volume":"116","author":"Belkin","year":"2019","journal-title":"Proc. Natl. Acad. Sci."},{"key":"ref9","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"066","DOI":"10.1055\/s-0040-1716673","article-title":"Size matters: rethinking of the sizing classification of pituitary adenomas based on the rates of surgery: a multi-institutional retrospective study of 29,651 patients","volume":"83","author":"Bhimani","year":"2022","journal-title":"J. Neurol. Surg. B Skull Base"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"6113","DOI":"10.3390\/cancers13236113","article-title":"Object detection improves tumour segmentation in MR images of rare brain tumours","volume":"13","author":"Chegraoui","year":"2021","journal-title":"Cancers (Basel)"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e0140381","DOI":"10.1371\/journal.pone.0140381","article-title":"Enhanced performance of brain tumor classification via tumor region augmentation and partition","volume":"10","author":"Cheng","year":"2015","journal-title":"PLoS One"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"106876","DOI":"10.1016\/j.bspc.2024.106876","article-title":"CFNet: automatic multi-modal brain tumor segmentation through hierarchical coarse-to-fine fusion and feature communication","volume":"99","author":"Cheng","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"153","DOI":"10.3390\/healthcare9020153","article-title":"A deep learning approach for brain tumor classification and segmentation using a multiscale convolutional neural network","volume":"9","author":"D\u00edaz-Pernas","year":"2021","journal-title":"Healthcare"},{"key":"ref15","volume-title":"Data from LGG-1p19qDeletion (Version 2)","author":"Erickson","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1038\/s41597-026-06753-y","article-title":"BRISC: annotated dataset for brain tumor segmentation and classification","volume":"13","author":"Fateh","year":"2026","journal-title":"Sci. Data"},{"key":"ref17","first-page":"64","volume-title":"Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation Using Holistic Convolutional Networks","author":"Fidon","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1093\/neuonc\/noae049","article-title":"Challenges, limitations, and pitfalls of PET and advanced MRI in patients with brain tumors: a report of the PET\/RANO group","volume":"26","author":"Galldiks","year":"2024","journal-title":"Neuro-Oncology"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.prro.2022.10.013","article-title":"ISRS technical guidelines for stereotactic radiosurgery: treatment of small brain metastases (\u22641 cm in diameter)","volume":"13","author":"Grishchuk","year":"2023","journal-title":"Pract. Radiat. Oncol."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.media.2016.05.004","article-title":"Brain tumor segmentation with deep neural networks","volume":"35","author":"Havaei","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref21","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"He","year":"2014"},{"key":"ref22","first-page":"88","article-title":"Resonancia magn\u00e9tica funcional: evoluci\u00f3n y avances en cl\u00ednica","volume":"13","author":"Hern\u00e1ndez","year":"2009","journal-title":"Tecnura"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"4806","DOI":"10.1109\/ACCESS.2019.2962617","article-title":"The real-world-weight cross-entropy loss function: modeling the costs of mislabeling","volume":"8","author":"Ho","year":"2020","journal-title":"IEEE Access"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"12","DOI":"10.6004\/jnccn.2023.0002","article-title":"NCCN guidelines\u00ae insights: central nervous system cancers, version 2.2022","volume":"21","author":"Horbinski","year":"2023","journal-title":"J. Natl. Compr. Cancer Netw."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1016\/j.ijrobp.2019.03.052","article-title":"Initial SRS for patients with 5 to 15 brain metastases: results of a multi-institutional experience","volume":"104","author":"Hughes","year":"2019","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.1100350","article-title":"The efficacy of preoperative MRI features in the diagnosis of meningioma WHO grade and brain invasion","volume":"12","author":"Jiang","year":"2023","journal-title":"Front. Oncol."},{"key":"ref27","volume-title":"Magnetic Resonance Spectroscopy for Brain Tumors","author":"Jordan","year":"2003"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1109\/SIBIRCON48586.2019.8958121","volume-title":"2019 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)","author":"Karimov","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"2178","DOI":"10.3174\/ajnr.A3104","article-title":"Characterizing hypervascular and hypovascular metastases and normal bone marrow of the spine using dynamic contrast-enhanced MR imaging","volume":"33","author":"Khadem","year":"2012","journal-title":"Am. J. Neuroradiol."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"565","DOI":"10.3390\/diagnostics10080565","article-title":"Multimodal brain tumor classification using deep learning and robust feature selection: a machine learning application for radiologists","volume":"10","author":"Khan","year":"2020","journal-title":"Diagnostics"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1038\/s41597-024-03350-9","article-title":"A multi-institutional meningioma MRI dataset for automated multi-sequence image segmentation","volume":"11","author":"LaBella","year":"2024","journal-title":"Sci. Data"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"8512","DOI":"10.3390\/app13148512","article-title":"An improved multi-scale feature fusion for skin lesion segmentation","volume":"13","author":"Liu","year":"2023","journal-title":"Appl. Sci."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.jmir.2020.04.004","article-title":"Location and diameter of intracranial meningioma as predictors of peritumoral brain oedema and mass effect","volume":"51","author":"Liyanage","year":"2020","journal-title":"J. Med. Imaging Radiat. Sci."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"29263","DOI":"10.1038\/s41598-024-80548-2","article-title":"Effective Alzheimer\u2019s disease detection using enhanced Xception blending with snapshot ensemble","volume":"14","author":"Mahanty","year":"2024","journal-title":"Sci. Rep."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1093\/neuonc\/noy159","article-title":"Outcomes following stereotactic radiosurgery for small to medium-sized brain metastases are exceptionally dependent upon tumor size and prescribed dose","volume":"21","author":"Moraes","year":"2019","journal-title":"Neuro-Oncology"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"7790","DOI":"10.3390\/app10217790","article-title":"Multi-task learning for small brain tumor segmentation from MRI","volume":"10","author":"Ngo","year":"2020","journal-title":"Appl. Sci."},{"key":"ref37","first-page":"269","author":"Noori","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"55135","DOI":"10.1109\/ACCESS.2020.2978629","article-title":"A deep learning model based on concatenation approach for the diagnosis of brain tumor","volume":"8","author":"Noreen","year":"2020","journal-title":"IEEE Access"},{"key":"ref39","volume-title":"Attention U-Net: Learning where to Look for the Pancreas","author":"Oktay","year":"2018"},{"key":"ref40","volume-title":"The Cancer Genome Atlas Low Grade Glioma Collection (TCGA-LGG) (Version 3)","author":"Pedano","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"14481","DOI":"10.1038\/s41598-019-51147-3","article-title":"Diagnosing brain tumours by routine blood tests using machine learning","volume":"9","author":"Podnar","year":"2019","journal-title":"Sci. Rep."},{"key":"ref42","first-page":"234","article-title":"Optimizing intersection-over-union in deep neural networks for image segmentation","author":"Rahman","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1038\/s41597-024-03021-9","article-title":"A large open access dataset of brain metastasis 3D segmentations on MRI with clinical and imaging information","volume":"11","author":"Ramakrishnan","year":"2024","journal-title":"Sci. Data"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"11551","DOI":"10.1007\/s11042-024-19333-2","article-title":"Brain tumour detection using machine and deep learning: a systematic review","volume":"84","author":"Rasool","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.3390\/electronics11071146","article-title":"A hybrid deep learning-based approach for brain tumor classification","volume":"11","author":"Raza","year":"2022","journal-title":"Electronics (Basel)."},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","volume-title":"arXiv","author":"Ronneberger","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"237","DOI":"10.3390\/computers13090237","article-title":"Evaluating the impact of filtering techniques on deep learning-based brain tumour segmentation","volume":"13","author":"Rosa","year":"2024","journal-title":"Computers"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1093\/neuonc\/noac188","article-title":"EANO - EURACAN - SNO guidelines on circumscribed astrocytic gliomas, glioneuronal, and neuronal tumors","volume":"24","author":"Rud\u00e0","year":"2022","journal-title":"Neuro-Oncology"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.1002\/jemt.23688","article-title":"Brain tumor detection and multi-classification using advanced deep learning techniques","volume":"84","author":"Sadad","year":"2021","journal-title":"Microsc. Res. Tech."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"965","DOI":"10.3390\/cancers15030965","article-title":"MR intensity normalization methods impact sequence specific radiomics prognostic model performance in primary and recurrent high-grade glioma","volume":"15","author":"Salome","year":"2023","journal-title":"Cancers (Basel)"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/RBME.2022.3185292","article-title":"Image segmentation for MR brain tumor detection using machine learning: a review","volume":"16","author":"Soomro","year":"2023","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"viii207","DOI":"10.1093\/neuonc\/noae165.0817","article-title":"NIMG-53. MRI-based radiomics for differentiation between perifocal edema and non-contrast-enhancing glioblastoma foci","volume":"26","author":"Thiele","year":"2024","journal-title":"Neuro-Oncology"},{"key":"ref53","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/s12938-022-01022-6","article-title":"Feature extraction from MRI ADC images for brain tumor classification using machine learning techniques","volume":"21","author":"Vijithananda","year":"2022","journal-title":"Biomed. Eng. Online"},{"key":"ref55","doi-asserted-by":"publisher","first-page":"4091","DOI":"10.1109\/TSP.2006.881190","article-title":"The Gaussian mixture probability hypothesis density filter","volume":"54","author":"Vo","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1200\/JCO.21.02314","article-title":"Treatment for brain metastases: ASCO-SNO-ASTRO guideline","volume":"40","author":"Vogelbaum","year":"2022","journal-title":"J. Clin. Oncol."},{"key":"ref57","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1007\/s10278-024-00981-7","article-title":"From CNN to transformer: a review of medical image segmentation models","volume":"37","author":"Yao","year":"2024","journal-title":"J Imaging Inf. Med."},{"key":"ref58","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015","journal-title":"arXiv"},{"key":"ref59","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1002\/mrm.22147","article-title":"Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme","volume":"62","author":"Zacharaki","year":"2009","journal-title":"Magn. Reson. Med."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1833713\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:33:30Z","timestamp":1783920810000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1833713\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":59,"alternative-id":["10.3389\/fnins.2026.1833713"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1833713","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]},"article-number":"1833713"}}