{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T09:51:39Z","timestamp":1775382699083,"version":"3.50.1"},"reference-count":48,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102345"],"award-info":[{"award-number":["62102345"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project for Research on Medical in Jiangsu Commission of Health","award":["Z2020032"],"award-info":[{"award-number":["Z2020032"]}]},{"name":"Xuzhou Key Research and Development Program","award":["KC22117"],"award-info":[{"award-number":["KC22117"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Preoperative classification of brain tumors is critical to developing personalized treatment plans, however existing classification methods rely on manual intervention and often have problems with efficiency and accuracy, which may lead to misdiagnosis or delayed diagnosis in clinical practice and affect the therapeutic effect. We propose a fully automated approach to brain tumor magnetic resonance imaging (MRI) classification, consisted by a feature extractor based on the improved U-Net and a classifier based on convolutional recurrent neural network (CRNN). The encoder of the feature extractor based on dense block, is used to enhance feature propagation and reduce the number of parameters. The decoder uses residual block to reduce the weight of some features for improving the effect of MRI spatial sequence reconstruction, and avoid gradient disappearance. Skip connections between the encoder and the decoder effectively merge\u00a0low-level\u00a0features and high-level features. The extract feature sequence is input into the CRNN-based classifier for final classification. We assessed the performance of our method for grading glioma, glioma isocitrate dehydrogenase1 (IDH1) mutation status classification and pituitary tumor texture classification on two datasets, glioma or pituitary tumors collected in a local affiliated hospital and glioma imaging data from TCIA. Compared with commonly models and new models, our model achieves higher accuracy, with an accuracy of 90.72%, classified glioma IDH1 mutation status with an accuracy of 94.35%, and classified pituitary tumor texture with an accuracy of 94.64%.<\/jats:p>","DOI":"10.1371\/journal.pone.0315631","type":"journal-article","created":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T04:21:13Z","timestamp":1742876473000},"page":"e0315631","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["Brain tumor intelligent diagnosis based on Auto-Encoder and U-Net feature extraction"],"prefix":"10.1371","volume":"20","author":[{"given":"Yaru","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengning","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinting","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingchao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haowen","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kexing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiwen","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhe","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1676-940X","authenticated-orcid":true,"given":"Hong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"issue":"8","key":"pone.0315631.ref001","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1038\/s41571-019-0177-5","article-title":"Challenges to curing primary brain tumours","volume":"16","author":"K Aldape","year":"2019","journal-title":"Nat Rev Clin Oncol"},{"key":"pone.0315631.ref002","volume-title":"Condition [Internet]. 2020 [cited 2024 May 20]","author":"Brain Tumor Center"},{"issue":"1","key":"pone.0315631.ref003","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1186\/s12940-017-0300-y","article-title":"Lifetime occupational exposure to metals and welding fumes, and risk of glioma: a 7-country population-based case-control study","volume":"16","author":"M-E Parent","year":"2017","journal-title":"Environ Health"},{"key":"pone.0315631.ref004","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.cmpb.2017.11.011","article-title":"Histogram analysis of T2*-based pharmacokinetic imaging in cerebral glioma grading","volume":"155","author":"H-S Liu","year":"2018","journal-title":"Comput Methods Programs Biomed"},{"issue":"3","key":"pone.0315631.ref005","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1007\/s11102-016-0706-5","article-title":"Magnetic resonance elastography detects tumoral consistency in pituitary macroadenomas","volume":"19","author":"JD Hughes","year":"2016","journal-title":"Pituitary"},{"key":"pone.0315631.ref006","doi-asserted-by":"crossref","first-page":"106564","DOI":"10.1109\/ACCESS.2020.3000895","article-title":"Glioma grade prediction using wavelet scattering-based radiomics","volume":"8","author":"Q Chen","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0315631.ref007","article-title":"Prediction of Glioma Grade using Intratumoral and Peritumoral Radiomic Features from Multiparametric MRI Images","volume":"1","author":"J Cheng","year":"2020","journal-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics"},{"issue":"2","key":"pone.0315631.ref008","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/s11060-017-2719-y","article-title":"Normalization of ADC does not improve correlation with overall survival in patients with high-grade glioma (HGG)","volume":"137","author":"L Qin","year":"2018","journal-title":"J Neurooncol"},{"issue":"1","key":"pone.0315631.ref009","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1038\/s41598-018-37387-9","article-title":"Multi-Channel 3D Deep Feature Learning for Survival Time Prediction of Brain Tumor Patients Using Multi-Modal Neuroimages","volume":"9","author":"D Nie","year":"2019","journal-title":"Sci Rep"},{"issue":"5","key":"pone.0315631.ref010","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1109\/TCBB.2017.2731849","article-title":"Improving Alzheimer\u2019s Disease Classification by Combining Multiple Measures","volume":"15","author":"J Liu","year":"2018","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"7","key":"pone.0315631.ref011","doi-asserted-by":"crossref","first-page":"3044","DOI":"10.1002\/mp.14168","article-title":"Automated Glioma Grading on Conventional MRI images Using Deep Convolutional Neural Networks","volume":"47","author":"Y Zhuge","year":"2020","journal-title":"Medical Physics"},{"issue":"1","key":"pone.0315631.ref012","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/s11060-018-2841-5","article-title":"Diagnostic performance of apparent diffusion coefficient parameters for glioma grading","volume":"139","author":"Q Wang","year":"2018","journal-title":"J Neurooncol"},{"issue":"5","key":"pone.0315631.ref013","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1002\/jmri.27434","article-title":"Predicting Isocitrate Dehydrogenase (IDH) Mutation Status in Gliomas Using Multiparameter MRI Radiomics Features","volume":"53","author":"H Peng","year":"2021","journal-title":"J Magn Reson Imaging"},{"key":"pone.0315631.ref014","first-page":"1420","article-title":"The correlation of pituitary tumor texture and magnetic resonance imaging scan enhanced performance","volume":"12","author":"X Chen","year":"2014","journal-title":"Chinese Journal of Clinical Oncology and Rehabilitation"},{"issue":"10","key":"pone.0315631.ref015","first-page":"3631","article-title":"Multi-scale generative adversarial network for image super-resolution","volume":"26","author":"D Jiang","year":"2022","journal-title":"Soft Computing"},{"issue":"1","key":"pone.0315631.ref016","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1186\/s12911-020-01163-5","article-title":"Machine learning assisted DSC-MRI radiomics as a tool for glioma classification by grade and mutation status","volume":"20","author":"CH Sudre","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"issue":"10","key":"pone.0315631.ref017","doi-asserted-by":"crossref","first-page":"3500","DOI":"10.3390\/s21103500","article-title":"Classification of Diffuse Glioma Subtype from Clinical-Grade Pathological Images Using Deep Transfer Learning","volume":"21","author":"S Im","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0315631.ref018","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1093\/neuonc\/now121","article-title":"Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas","volume":"19","author":"B Zhang","year":"2017","journal-title":"Neuro Oncol"},{"issue":"2","key":"pone.0315631.ref019","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/neuonc\/noaa177","article-title":"Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics","volume":"23","author":"YS Choi","year":"2021","journal-title":"Neuro Oncol"},{"issue":"1","key":"pone.0315631.ref020","first-page":"8104054","article-title":"Intelligent model for brain tumor identification using deep learning","author":"AH Khan","year":"2022","journal-title":"Applied Computational Intelligence and Soft Computing"},{"key":"pone.0315631.ref021","doi-asserted-by":"crossref","first-page":"122347","DOI":"10.1016\/j.eswa.2023.122347","article-title":"Robust clinical applicable CNN and U-Net based algorithm for MRI classification and segmentation for brain tumor","volume":"238","author":"A Akter","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"pone.0315631.ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/17455030.2024.2366837","article-title":"RobU-Net: a heuristic robust multi-class brain tumor segmentation approaches for MRI scans","author":"SA Qureshi","year":"2024","journal-title":"Waves in Random and Complex Media"},{"key":"pone.0315631.ref023","unstructured":"Jia Z, Chen D. Brain tumor identification and classification of MRI images using deep learning techniques. IEEE Access, 2020."},{"issue":"1","key":"pone.0315631.ref024","doi-asserted-by":"crossref","first-page":"3291","DOI":"10.1038\/s41598-023-30309-4","article-title":"Radiogenomic classification for MGMT promoter methylation status using multi-omics fused feature space for least invasive diagnosis through mpMRI scans","volume":"13","author":"SA Qureshi","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0315631.ref025","doi-asserted-by":"crossref","unstructured":"Saba T, Mohamed AS, El-Affendi M, Amin J, Sharif M. Brain tumor detection using fusion of hand crafted and deep learning features. Cognitive Systems Research, 2020, 59: 221-230.","DOI":"10.1016\/j.cogsys.2019.09.007"},{"key":"pone.0315631.ref026","doi-asserted-by":"crossref","first-page":"104961","DOI":"10.1016\/j.compbiomed.2021.104961","article-title":"LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data","volume":"139","author":"N Faruqui","year":"2021","journal-title":"Comput Biol Med"},{"key":"pone.0315631.ref027","doi-asserted-by":"crossref","first-page":"105539","DOI":"10.1016\/j.compbiomed.2022.105539","article-title":"A classification of MRI brain tumor based on two stage feature level ensemble of deep CNN models","volume":"146","author":"NF Aurna","year":"2022","journal-title":"Comput Biol Med"},{"key":"pone.0315631.ref028","first-page":"311","volume-title":"3D MRI brain tumor segmentation using autoencoder regularization. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4. Springer International Publishing","author":"A Myronenko","year":"2019"},{"key":"pone.0315631.ref029","article-title":"Spatio-temporal learning from longitudinal data for multiple sclerosis lesion segmentation. arXiv 2020, arXiv:2004.03675.","author":"S Denner"},{"issue":"1","key":"pone.0315631.ref030","first-page":"1","article-title":"CXNet-m1: Anomaly detection on chest X-rays with image-based deep learning","volume":"1","author":"S Xu","year":"2018","journal-title":"IEEE Access"},{"issue":"6","key":"pone.0315631.ref031","doi-asserted-by":"crossref","first-page":"2035","DOI":"10.1109\/TMI.2019.2963248","article-title":"Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising","volume":"39","author":"F Fan","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"issue":"10","key":"pone.0315631.ref032","doi-asserted-by":"crossref","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"CE-Net: Context Encoder Network for 2D Medical Image Segmentation","volume":"38","author":"Z Gu","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"pone.0315631.ref033","doi-asserted-by":"crossref","first-page":"111","DOI":"10.3390\/cancers11010111","article-title":"A Review on a Deep Learning Perspective in Brain Cancer Classification","volume":"11","author":"G S Tandel","year":"2019","journal-title":"Cancers (Basel)"},{"key":"pone.0315631.ref034","first-page":"234","volume-title":"U-Net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer International Publishing,","author":"O Ronneberger","year":"2015"},{"key":"pone.0315631.ref035","first-page":"4111","article-title":"Whole Tumor Segmentation from Brain MR images using Multi-view 2D Convolutional Neural Network","author":"R Lahoti","year":"2021","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"pone.0315631.ref036","doi-asserted-by":"crossref","first-page":"106208","DOI":"10.1016\/j.cmpb.2021.106208","article-title":"DFP-ResUNet:Convolutional Neural Network with a Dilated Convolutional Feature Pyramid for Multimodal Brain Tumor Segmentation","volume":"208","author":"J Wang","year":"2021","journal-title":"Comput Methods Programs Biomed"},{"issue":"1","key":"pone.0315631.ref037","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s12880-022-00738-0","article-title":"Improved U-Net3+ with stage residual for brain tumor segmentation","volume":"22","author":"C Qin","year":"2022","journal-title":"BMC Med Imaging"},{"issue":"11","key":"pone.0315631.ref038","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","article-title":"An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition","volume":"39","author":"B Shi","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"pone.0315631.ref039","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1049\/ipr2.12419","article-title":"Medical image segmentation using deep learning: A survey","volume":"16","author":"R Wang","year":"2022","journal-title":"IET Image Processing"},{"key":"pone.0315631.ref040","article-title":"Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556.","author":"K Simonyan"},{"issue":"1","key":"pone.0315631.ref041","first-page":"770","article-title":"Deep residual learning for image recognition","volume":"1","author":"K He","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"pone.0315631.ref042","first-page":"4700","article-title":"Densely connected convolutional networks","author":"G Huang","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"pone.0315631.ref043","doi-asserted-by":"crossref","first-page":"804","DOI":"10.3389\/fnins.2018.00804","article-title":"Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning","volume":"12","author":"Y Yang","year":"2018","journal-title":"Front Neurosci"},{"key":"pone.0315631.ref044","doi-asserted-by":"crossref","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":"S Deepak","year":"2019","journal-title":"Comput Biol Med"},{"issue":"9","key":"pone.0315631.ref045","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1093\/neuonc\/noz095","article-title":"Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network","volume":"21","author":"KS Choi","year":"2019","journal-title":"Neuro Oncol"},{"key":"pone.0315631.ref046","first-page":"9969","article-title":"GhostNetv2: Enhance cheap operation with long-range attention","volume":"35","author":"YH Tang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"07","key":"pone.0315631.ref047","first-page":"60","article-title":"Prediction method of IDH1 mutation status of glioma based on improved EfficientNetV2","volume":"58","author":"H Xu","year":"2023","journal-title":"Journal of Shandong University (Natural Science)"},{"issue":"04","key":"pone.0315631.ref048","first-page":"542","article-title":"Prediction model of glioma P53 gene status under MRI based on CVT-RegNet","volume":"60","author":"Y Zhao","year":"2024","journal-title":"Journal of Nanjing University (Natural Sciences)"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T04:23:10Z","timestamp":1742876590000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315631"}},"subtitle":[],"editor":[{"given":"Azhar","family":"Imran","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":48,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0315631","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,24]]}}}