{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:58:38Z","timestamp":1790791118474,"version":"4.1.0"},"reference-count":47,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Major Science and Technology Projects of Henan Province","award":["221100210500"],"award-info":[{"award-number":["221100210500"]}]},{"DOI":"10.13039\/501100004609","name":"Foundation of Henan Educational Committee","doi-asserted-by":"publisher","award":["24A320004"],"award-info":[{"award-number":["24A320004"]}],"id":[{"id":"10.13039\/501100004609","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Medical and Health Research Project in Luoyang","award":["2001027A"],"award-info":[{"award-number":["2001027A"]}]},{"name":"Construction Project of Improving Medical Service Capacity of Provincial Medical Institutions in Henan Province","award":["2017-51"],"award-info":[{"award-number":["2017-51"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Due to the substantial impact of brain tumors on human health, precise identification of tumor types is vital for patient prognosis and guiding treatment decisions. Magnetic Resonance Imaging (MRI) technology, owing to its non-invasive nature and high resolution, is indispensable in accurately classifying brain tumor types. However, manual interpretation of MRI images is not only time-consuming and labor-intensive but also susceptible to subjective bias. Hence, many automatic brain tumor diagnosis systems utilizing deep learning techniques have been developed. This paper introduces an advanced modularized Convolutional Neural Network (CNN) that incorporates ConvDAtt block, Complementary Information (CI) downsampling block, and Spatial Pyramid Pooling (SPP) block. Firstly, the ConvDAtt block combines convolution, depth-separable convolution and Coordinated Attention (CA) mechanism. The module alleviates the gradient vanishing problem in deep neural network training, enhancing the training stability and performance of the model. In the ConvDAtt block, the CA mechanism can not only capture information across channels, but also sense direction and position sensitive information, improving the accuracy of the model\u2019s identification of objects of interest. Secondly, the CI block is a downsampling block with convolution and pooling functions. In the CI block, there is a complementary relationship between the pooling layer and the convolution layer, which is mainly reflected in two aspects, feature extraction and dimensionality reduction, enlargement of receptive field. Moreover, the complementary relationship can solve the problem of information loss in the process of downsampling, while also significantly reducing computational cost. Thirdly, the SPP block extracts features from different scales of the input data and integrates these features, thus enhancing the performance of the network, and enhancing the robustness of the model. The combination of ConvDAtt block, CI block and SPP block can effectively extract the information features and discriminant features of brain tumor MRI images, which has the advantages of parameter reduction, stable training and clear structure.<\/jats:p>","DOI":"10.1371\/journal.pone.0343457","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:31:53Z","timestamp":1790789513000},"page":"e0343457","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["An efficient brain tumor classification system with accurate recognition and complementary downsampling blocks"],"prefix":"10.1371","volume":"21","author":[{"given":"Jincan","family":"Zhang","sequence":"first","affiliation":[{"name":"Henan University of Science and Technology","place":["Luoyang, China"],"department":["College of Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanqi","family":"Cai","sequence":"additional","affiliation":[{"name":"Henan University of Science and Technology","place":["Luoyang, China"],"department":["College of Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"XingHua","family":"Tan","sequence":"additional","affiliation":[{"name":"Henan University of Science and Technology","place":["Luoyang, China"],"department":["College of Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8824-6926","authenticated-orcid":true,"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":"Xin","family":"Zhao","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"}]},{"given":"Hongwei","family":"Jiang","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":"340","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"issue":"4","key":"pone.0343457.ref001","doi-asserted-by":"crossref","first-page":"2036","DOI":"10.1007\/s12559-022-10096-2","article-title":"Tumor localization and classification from MRI of brain using deep convolution neural network and salp swarm algorithm","volume":"16","author":"J Alyami","year":"2023","journal-title":"Cogn Comput"},{"issue":"5","key":"pone.0343457.ref002","doi-asserted-by":"crossref","first-page":"624","DOI":"10.3390\/diagnostics15050624","article-title":"Learning architecture for brain tumor classification based on deep convolutional neural network: classic and ResNet50","volume":"15","author":"RR Ali","year":"2025","journal-title":"Diagnostics (Basel)"},{"issue":"3","key":"pone.0343457.ref003","doi-asserted-by":"crossref","first-page":"867","DOI":"10.3390\/pr13030867","article-title":"Automatic active contour algorithm for detecting early brain tumors in comparison with AI detection","volume":"13","author":"M Almijalli","year":"2025","journal-title":"Processes"},{"key":"pone.0343457.ref004","doi-asserted-by":"crossref","first-page":"12027","DOI":"10.1007\/s13369-023-08607-w","article-title":"Transfer learning-based deep feature extraction framework using fine-tuned EfficientNet B7 for multiclass brain tumor classification","volume":"49","author":"A Ghosh","year":"2023","journal-title":"Arab J Sci Eng"},{"issue":"11","key":"pone.0343457.ref005","doi-asserted-by":"crossref","first-page":"9069","DOI":"10.1007\/s00521-022-06929-8","article-title":"An improved hybrid classification of brain tumor MRI images based on conglomeration feature extraction techniques","volume":"34","author":"T Bansal","year":"2022","journal-title":"Neural Comput & Applic"},{"issue":"5","key":"pone.0343457.ref006","doi-asserted-by":"crossref","first-page":"3015","DOI":"10.1007\/s11831-024-10065-y","article-title":"Machine learning and computer vision based methods for cancer classification: A systematic review","volume":"31","author":"SB Mukadam","year":"2024","journal-title":"Arch Computat Methods Eng"},{"key":"pone.0343457.ref007","doi-asserted-by":"crossref","first-page":"103257","DOI":"10.1016\/j.jbi.2019.103257","article-title":"Comparison of machine learning algorithms for clinical event prediction (risk of coronary heart disease)","volume":"97","author":"J-J Beunza","year":"2019","journal-title":"J Biomed Inform"},{"key":"pone.0343457.ref008","doi-asserted-by":"crossref","DOI":"10.2196\/52322","article-title":"Machine learning approaches to predict symptoms in people with cancer: systematic review","volume":"10","author":"N Zeinali","year":"2024","journal-title":"JMIR Cancer"},{"issue":"2","key":"pone.0343457.ref009","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.dsp.2009.07.002","article-title":"Hybrid intelligent techniques for MRI brain images classification","volume":"20","author":"E-SA El-Dahshan","year":"2010","journal-title":"Digital Signal Processing"},{"key":"pone.0343457.ref010","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.mri.2019.05.028","article-title":"A review on brain tumor diagnosis from MRI images: Practical implications, key achievements, and lessons learned","volume":"61","author":"MK Abd-Ellah","year":"2019","journal-title":"Magn Reson Imaging"},{"key":"pone.0343457.ref011","first-page":"012016","article-title":"Classification of brain tumors using deep features extracted using CNN","volume":"1172","author":"S Basheera","year":"2019","journal-title":"J Phys: Conf Ser"},{"key":"pone.0343457.ref012","doi-asserted-by":"crossref","unstructured":"Santamaria BC, Carreno EC, Barrera AG. Classification of Primary Brain Tumors Using Convolutional Neural Network (CNN). In: 2022 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI), 2022. 1\u20136. https:\/\/doi.org\/10.1109\/colcaci56938.2022.9905365","DOI":"10.1109\/ColCACI56938.2022.9905365"},{"issue":"14","key":"pone.0343457.ref013","doi-asserted-by":"crossref","first-page":"4915","DOI":"10.3390\/app10144915","article-title":"Incremental dilations using CNN for brain tumor classification","volume":"10","author":"SS Roy","year":"2020","journal-title":"Appl Sci"},{"issue":"19","key":"pone.0343457.ref014","doi-asserted-by":"crossref","first-page":"57409","DOI":"10.1007\/s11042-023-17712-9","article-title":"Image classification of intracranial tumor using deep residual learning technique","volume":"83","author":"GV Sagar","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"pone.0343457.ref015","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.neucom.2022.11.039","article-title":"Brain tumor categorization from imbalanced MRI dataset using weighted loss and deep feature fusion","volume":"520","author":"S Deepak","year":"2023","journal-title":"Neurocomputing"},{"issue":"6","key":"pone.0343457.ref016","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.3390\/s21062222","article-title":"MRI-based brain tumor classification using ensemble of deep features and machine learning classifiers","volume":"21","author":"J Kang","year":"2021","journal-title":"Sensors (Basel)"},{"key":"pone.0343457.ref017","doi-asserted-by":"crossref","first-page":"2141","DOI":"10.31557\/APJCP.2023.24.6.2141","article-title":"Brain tumor classification based on improved stacked ensemble deep learning methods","volume":"24","author":"ZHN Al-Azzwi","year":"2023","journal-title":"Asian Pacific J Cancer Prevention"},{"issue":"4","key":"pone.0343457.ref018","article-title":"Detection of MRI brain tumor using residual skip block based modified MobileNet model","volume":"28","author":"SUR Khan","year":"2025","journal-title":"Cluster Comput"},{"key":"pone.0343457.ref019","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/s12539-023-00571-1","article-title":"BMRI-NET: A deep stacked ensemble model for multi-class brain tumor classification from MRI images","volume":"15","author":"S Asif","year":"2023","journal-title":"Interdiscip Sci Comput Life Sci"},{"key":"pone.0343457.ref020","article-title":"Transfer learning-based deep feature extraction framework using fine-tuned EfficientNet B7 for multiclass brain tumor classification","author":"A Ghosh","year":"2023","journal-title":"Arab J Sci Eng"},{"issue":"1","key":"pone.0343457.ref021","doi-asserted-by":"crossref","first-page":"711","DOI":"10.32604\/cmc.2023.038176","article-title":"Effectiveness of Deep learning models for brain tumor classification and segmentation","volume":"76","author":"M Irfan","year":"2023","journal-title":"Computers, Materials & Continua"},{"issue":"19","key":"pone.0343457.ref022","doi-asserted-by":"crossref","first-page":"57643","DOI":"10.1007\/s11042-023-17760-1","article-title":"Ensemble coupled convolution network for three-class brain tumor grade classification","volume":"83","author":"BV Isunuri","year":"2023","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"pone.0343457.ref023","doi-asserted-by":"crossref","first-page":"955","DOI":"10.3390\/electronics12040955","article-title":"Classifying brain tumors on magnetic resonance imaging by using convolutional neural networks","volume":"12","author":"MA G\u00f3mez-Guzm\u00e1n","year":"2023","journal-title":"Electronics"},{"key":"pone.0343457.ref024","doi-asserted-by":"crossref","first-page":"5535505","DOI":"10.1155\/ijbi\/5535505","article-title":"Brain tumour detection using VGG-Based feature extraction with modified DarkNet-53 model","volume":"2025","author":"S Trisheela","year":"2025","journal-title":"Int J Biomed Imaging"},{"key":"pone.0343457.ref025","doi-asserted-by":"crossref","first-page":"63857","DOI":"10.1109\/ACCESS.2025.3555638","article-title":"Transforming brain tumor detection empowering multi-class classification with vision transformers and EfficientNetV2","volume":"13","author":"A Tariq","year":"2025","journal-title":"IEEE Access"},{"key":"pone.0343457.ref026","doi-asserted-by":"crossref","first-page":"119123","DOI":"10.1016\/j.ins.2023.119123","article-title":"Patch merging refiner embedding UNet for image denoising","volume":"641","author":"J Li","year":"2023","journal-title":"Inf Sci"},{"key":"pone.0343457.ref027","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.ins.2020.02.067","article-title":"DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection","volume":"522","author":"Z Huang","year":"2020","journal-title":"Inf Sci"},{"key":"pone.0343457.ref028","first-page":"1899","article-title":"Automated grading of gliomas using deep learning in digital pathology images: A modular approach with ensemble of convolutional neural networks","volume":"2015","author":"MG Ertosun","year":"2015","journal-title":"AMIA Annu Symp Proc"},{"key":"pone.0343457.ref029","first-page":"3","article-title":"ConvNet-CA: A lightweight attention-based CNN for brain disease detection.","author":"H Zhu","year":"2022","journal-title":"Artificial intelligence in neuroscience: Affective analysis and health applications, pt I. Cham: Springer International Publishing Ag"},{"issue":"10","key":"pone.0343457.ref030","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0140381","article-title":"Enhanced performance of brain tumor classification via tumor region augmentation and partition","volume":"10","author":"J Cheng","year":"2015","journal-title":"PLoS One"},{"key":"pone.0343457.ref031","author":"S Bhuvaji","year":"2020","journal-title":"Brain Tumor Classification (MRI). Kaggle"},{"issue":"22","key":"pone.0343457.ref032","doi-asserted-by":"crossref","first-page":"8917","DOI":"10.3390\/s22228917","article-title":"Evaluation of preprocessing methods on independent medical hyperspectral databases to improve analysis","volume":"22","author":"B Martinez-Vega","year":"2022","journal-title":"Sensors (Basel)"},{"issue":"4","key":"pone.0343457.ref033","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1007\/s12539-023-00585-9","article-title":"A novel deep learning model for medical image segmentation with convolutional neural network and transformer","volume":"15","author":"Z Zhang","year":"2023","journal-title":"Interdiscip Sci"},{"key":"pone.0343457.ref034","doi-asserted-by":"crossref","first-page":"107429","DOI":"10.1016\/j.apacoust.2020.107429","article-title":"Predicting fetal hypoxia using common spatial pattern and machine learning from cardiotocography signals","volume":"167","author":"W Alsaggaf","year":"2020","journal-title":"Applied Acoustics"},{"key":"pone.0343457.ref035","doi-asserted-by":"crossref","first-page":"83","DOI":"10.3389\/fncom.2019.00083","article-title":"Data augmentation for brain-tumor segmentation: A review","volume":"13","author":"J Nalepa","year":"2019","journal-title":"Front Comput Neurosci"},{"issue":"5","key":"pone.0343457.ref036","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1093\/jrsssc\/qlad057","article-title":"Hierarchical confusion matrix for classification performance evaluation","volume":"72","author":"K Riehl","year":"2023","journal-title":"J R Stat Soc Sers C-Appl Stat"},{"key":"pone.0343457.ref037","doi-asserted-by":"crossref","first-page":"223","DOI":"10.18280\/ts.420120","article-title":"Brain tumor classification in MRI using hybrid ASA-based deep learning and Masi-entropy multilayer thresholding segmentation with sunflower optimization","volume":"42","author":"K Balasuburamani","year":"2025","journal-title":"TS"},{"issue":"4","key":"pone.0343457.ref038","doi-asserted-by":"crossref","first-page":"710","DOI":"10.3390\/electronics14040710","article-title":"Improved EfficientNet architecture for multi-grade brain tumor detection","volume":"14","author":"A Ishaq","year":"2025","journal-title":"Electronics"},{"key":"pone.0343457.ref039","doi-asserted-by":"crossref","first-page":"204","DOI":"10.12913\/22998624\/193627","article-title":"An ensemble transfer learning model for brain tumors classification using convolutional neural networks","volume":"18","author":"B Sterniczuk","year":"2024","journal-title":"Adv Sci Technol Res J"},{"issue":"30","key":"pone.0343457.ref040","doi-asserted-by":"crossref","first-page":"36453","DOI":"10.1007\/s11042-024-19657-z","article-title":"Developing diverse ensemble architectures for automatic brain tumor classification","volume":"84","author":"G Bogacsovics","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"pone.0343457.ref041","doi-asserted-by":"crossref","first-page":"9981","DOI":"10.1109\/ACCESS.2025.3526684","article-title":"Combined oriented data augmentation method for brain MRI images","volume":"13","author":"A Suliman Farhan","year":"2025","journal-title":"IEEE Access"},{"issue":"10","key":"pone.0343457.ref042","doi-asserted-by":"crossref","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":"AM Alhassan","year":"2025","journal-title":"PLoS One"},{"issue":"1","key":"pone.0343457.ref043","doi-asserted-by":"crossref","first-page":"27911","DOI":"10.1038\/s41598-024-77523-2","article-title":"Brain tumor diagnosis in MRI scans images using Residual\/Shuffle Network optimized by augmented Falcon Finch optimization","volume":"14","author":"X Guo","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0343457.ref044","doi-asserted-by":"crossref","first-page":"105421","DOI":"10.1016\/j.bspc.2023.105421","article-title":"ARM-Net: Attention-guided residual multiscale CNN for multiclass brain tumor classification using MR images","volume":"87","author":"TK Dutta","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"issue":"5","key":"pone.0343457.ref045","doi-asserted-by":"crossref","first-page":"3913","DOI":"10.11591\/eei.v14i5.10706","article-title":"Few-shot brain tumor classification: meta- vs metric-learning comparison","volume":"14","author":"S Akhmetzhanova","year":"2025","journal-title":"Bulletin EEI"},{"issue":"1","key":"pone.0343457.ref046","article-title":"Classification of brain tumors: A comparative approach of shallow and deep neural networks","volume":"5","author":"SF\u00c1 Montoya","year":"2024","journal-title":"SN COMPUT SCI"},{"key":"pone.0343457.ref047","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","volume":"128","author":"RR Selvaraju","year":"2020","journal-title":"Int J Comput Vis"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:32:04Z","timestamp":1790789524000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343457"}},"subtitle":[],"editor":[{"given":"Ali Mohammad","family":"Alqudah","sequence":"first","affiliation":[{"name":"University of Manitoba","place":["CANADA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":47,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0343457","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}