{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:10:31Z","timestamp":1788844231061,"version":"build-2803163510"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Brain tumor classification using magnetic resonance imaging (MRI) is important for computer-aided medical image analysis. However, different brain tumor types may exhibit highly similar grayscale patterns, textures, and boundaries. Conventional convolutional neural networks rely primarily on spatial-domain convolution and do not explicitly model frequency-domain information. Moreover, high-frequency details, such as edges and textures, are often weakened by multi-stage downsampling, while interaction between spatial- and frequency-domain features remains limited. Consequently, fine-grained differences among tumor categories may not be effectively captured.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address these limitations, a Frequency\u2013Spatial Fusion Convolutional Network (FS-FCN) was developed for brain tumor MRI classification. A Parametric Wavelet Downsampling (PWD) module and a Frequency\u2013Spatial Convolution (FSConv) module were incorporated into the convolutional network. Spatial- and frequency-domain information was jointly modeled during multilevel encoding and deep feature learning to improve the preservation and discriminative representation of key structures, local textures, and edge details.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the Cheng Brain Tumor MRI Three-Class Classification Dataset, FS-FCN achieved an average classification accuracy of 98.53% \u00b1 0.35% using five-fold cross-validation. The applicability of the model across different classification settings was further evaluated through a four-class classification experiment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results demonstrate that jointly modeling spatial- and frequency-domain information improves the representation of brain tumor MRI features and provides an effective feature-learning approach for brain tumor MRI classification.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1948996","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:26:10Z","timestamp":1788841570000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FS-FCN: a frequency\u2013spatial fusion convolutional network for brain tumor classification in MR images"],"prefix":"10.3389","volume":"17","author":[{"given":"Kun","family":"Zhang","sequence":"first","affiliation":[{"name":"The First Affiliated Hospital, and College of Clinical Medicine of Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghao","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenna","family":"Chen","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital, and College of Clinical Medicine of Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ganqin","family":"Du","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital, and College of Clinical Medicine of Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"19206","DOI":"10.1038\/s41598-022-22172-6","article-title":"Brain tumor classification based on neural architecture search","volume":"12","author":"Chitnis","year":"2022","journal-title":"Sci Rep"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3390\/cancers17010121","article-title":"Advanced brain tumor classification in MR images using transfer learning and pre-trained deep CNN models","volume":"17","author":"Disci","year":"2025","journal-title":"Cancer"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"e0291200","DOI":"10.1371\/journal.pone.0291200","article-title":"TumorDetNet: a unified deep learning model for brain tumor detection and classification","volume":"18","author":"Ullah","year":"2023","journal-title":"PLoS One"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2309","DOI":"10.1007\/s10278-025-01686-1","article-title":"Lightweight transfer learning models for multi-class brain tumor classification: glioma, meningioma, pituitary tumors, and no tumor MRI screening","volume":"39","author":"Gorenshtein","year":"2026","journal-title":"J Digit Imaging Inform med"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"4172","DOI":"10.3390\/cancers15164172","article-title":"Brain tumor detection based on deep learning approaches and magnetic resonance imaging","volume":"15","author":"Abdusalomov","year":"2023","journal-title":"Cancers"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"29411","DOI":"10.1038\/s41598-025-14901-4","article-title":"Enhanced MRI brain tumor detection using deep learning in conjunction with explainable AI SHAP based diverse and multi feature analysis","volume":"15","author":"Rahman","year":"2025","journal-title":"Sci Rep"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"4709","DOI":"10.1038\/s41598-025-34806-6","article-title":"Multi-class classification of brain tumors using optimized CNN and transfer learning techniques","volume":"16","author":"Anand","year":"2026","journal-title":"Sci Rep"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"103345","DOI":"10.1016\/j.compbiomed.2019.103345","article-title":"Brain tumor classification using deep CNN features via transfer learning","volume":"111","author":"Deepak","year":"2019","journal-title":"Comput Biol Med"},{"key":"ref9","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":"ref10","first-page":"2286","author":"D\u2019Ascoli","year":"2021"},{"key":"ref11","first-page":"1740","author":"Xu","year":"2020"},{"key":"ref12","first-page":"9108","author":"Saeedan","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"782968","DOI":"10.3389\/fnins.2021.782968","article-title":"Deep convolutional neural network with a multi-scale attention feature fusion module for segmentation of multimodal brain tumor","volume":"15","author":"He","year":"2021","journal-title":"Front Neurosci"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"4536","DOI":"10.1109\/TMI.2025.3579213","article-title":"Rethinking brain tumor segmentation from the frequency domain perspective","volume":"44","author":"Shao","year":"2025","journal-title":"IEEE Trans Med Imaging"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"950706","DOI":"10.3389\/fonc.2022.950706","article-title":"MM-UNet: a multimodality brain tumor segmentation network in MRI images","volume":"12","author":"Zhao","year":"2022","journal-title":"Front Oncol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/s10044-017-0597-8","article-title":"Brain tumor classification from multi-modality MRI using wavelets and machine learning","volume":"20","author":"Usman","year":"2017","journal-title":"Pattern Anal Applic"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"185","DOI":"10.18280\/ts.360209","article-title":"SVM-PUK kernel based MRI-brain tumor identification using texture and Gabor wavelets","volume":"36","author":"Chinnam","year":"2019","journal-title":"Traitement Signal"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.3390\/app10061999","article-title":"Classification of brain tumors from MRI images using a convolutional neural network","volume":"10","author":"Bad\u017ea","year":"2020","journal-title":"Appl Sci"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"69215","DOI":"10.1109\/access.2019.2919122","article-title":"Multi-classification of brain tumor images using deep neural network","volume":"7","author":"Sultan","year":"2019","journal-title":"IEEE Access"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.bbe.2018.10.004","article-title":"Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms","volume":"39","author":"Anaraki","year":"2019","journal-title":"Biocybern Biomed Eng"},{"key":"ref21","first-page":"7132","author":"Hu","year":"2018"},{"key":"ref22","first-page":"11531","author":"Wang","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.patrec.2019.11.016","article-title":"Brain tumor classification based on DWT fusion of MRI sequences using convolutional neural network","volume":"129","author":"Amin","year":"2020","journal-title":"Pattern Recogn Lett"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"6971","DOI":"10.1007\/s40747-023-01119-y","article-title":"WRANet: wavelet integrated residual attention U-net network for medical image segmentation","volume":"9","author":"Zhao","year":"2023","journal-title":"Complex Intell Syst"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2025.3601517","article-title":"GSFANet: global spatial\u2013frequency attention network for infrared small target detection","volume":"63","author":"Deng","year":"2025","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2025.3612417","article-title":"Think locally and act globally: a frequency\u2013spatial fusion network for infrared small target detection","volume":"63","author":"Xu","year":"2025","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf Process Manag"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.aci.2018.08.003","article-title":"Classification assessment methods","volume":"17","author":"Tharwat","year":"2021","journal-title":"Appl Comput Inform"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recogn Lett"},{"key":"ref30","first-page":"618","author":"Selvaraju","year":"2017"},{"key":"ref31","first-page":"770","author":"He","year":"2016"},{"key":"ref32","author":"Dosovitskiy","year":"2021"},{"key":"ref33","first-page":"11976","author":"Liu","year":"2022"},{"key":"ref34","first-page":"9992","author":"Liu","year":"2021"},{"key":"ref35","first-page":"10096","author":"Tan","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"106791","DOI":"10.1016\/j.compbiomed.2023.106791","article-title":"MedViT: a robust vision transformer for generalized medical image classification","volume":"157","author":"Manzari","year":"2023","journal-title":"Comput Biol Med"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/s11760-021-02022-0","article-title":"Multi-level attention network: application to brain tumor classification","volume":"16","author":"Shaik","year":"2022","journal-title":"SIViP"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"7498","DOI":"10.3390\/curroncol29100590","article-title":"Classification of brain tumor from magnetic resonance imaging using vision transformers ensembling","volume":"29","author":"Tummala","year":"2022","journal-title":"Curr Oncol"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"2541","DOI":"10.1007\/s00521-022-07742-z","article-title":"An attention-guided convolutional neural network for automated classification of brain tumor from MRI","volume":"35","author":"Saurav","year":"2023","journal-title":"Neural Comput & Applic"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"e22975","DOI":"10.1002\/ima.22975","article-title":"Hybrid-NET: a fusion of DenseNet169 and advanced machine learning classifiers for enhanced brain tumor diagnosis","volume":"34","author":"Khan","year":"2024","journal-title":"Int J Imaging Syst Technol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/s42979-023-02431-7","article-title":"Classification of brain tumors: a comparative approach of shallow and deep neural networks","volume":"5","author":"Montoya","year":"2024","journal-title":"SN Comput Sci"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"529","DOI":"10.3390\/digital4030027","article-title":"MRI-based brain tumor classification using a dilated parallel deep convolutional neural network","volume":"4","author":"Rahman","year":"2024","journal-title":"DIGITAL"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"e0335397","DOI":"10.1371\/journal.pone.0335397","article-title":"IV3TM: inception V3 enabled bidirectional long short-term memory network for brain tumor classification","volume":"20","author":"Alhassan","year":"2025","journal-title":"PLoS One"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"739","DOI":"10.32604\/cmc.2025.059807","article-title":"A global-local parallel dual-branch deep learning model with attention-enhanced feature fusion for brain tumor MRI classification","volume":"83","author":"Li","year":"2025","journal-title":"Comput Mater Contin"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1948996\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:26:11Z","timestamp":1788841571000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1948996\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":44,"alternative-id":["10.3389\/fneur.2026.1948996"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1948996","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"article-number":"1948996"}}