{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:03:04Z","timestamp":1787022184745,"version":"build-2736575974"},"reference-count":58,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"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":["62402034"],"award-info":[{"award-number":["62402034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4244082"],"award-info":[{"award-number":["4244082"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Transformer-based deep learning architectures have achieved notable success across various medical image analysis tasks, driven by the global modeling capabilities of the self-attention mechanism. However, Transformer-based methods exhibit significant computational complexity and a large number of parameters, rendering them challenging to apply effectively in practical medical scenarios. Compared with Transformers, large-kernel Convolutional Neural Networks (CNNs) and Multi-Layer Perceptrons (MLPs) offer more efficient inference while retaining global contextual awareness. Therefore, we rethink the role of large-kernel CNNs and MLPs in medical image analysis and leverage them to replace the heavy self-attention operation, to strike a better balance between performance and efficiency. Specifically, we propose backbone models for medical image classification and segmentation, featured by three lightweight modules: Linear Attention Feed Forward Network (FFN) for enhancing lesion features, Spatial Encoding Module for integrating multi-scale lesion information, and Smooth Depth-Wise Convolution (DwConv) FFN for efficient interaction of channel features. Composed solely of lightweight convolutional and MLP operations, our method achieves a better balance between performance and efficiency, validated by the superior performances on five datasets with varying data scales and diseases, with 98.39% on SARS-COV2-CT-Scan, 98.12% on Monkeypox Skin Lesion Dataset, 98.58% on Large COVID-19-CT scan slice, 79.45% on Synapse and 91.28% on ACDC. The low computational cost, high-performance with limited training data, and generalizability to various of medical tasks make the proposed method a promising and practical solution for medical image classification and segmentation.<\/jats:p>","DOI":"10.1371\/journal.pone.0340108","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:50:07Z","timestamp":1767639007000},"page":"e0340108","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["MedNeXt for accurate medical image classification and segmentation: A lightweight transformer-style convolutional neural network"],"prefix":"10.1371","volume":"21","author":[{"given":"Ziqing","family":"Xue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengpeng","family":"Pi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2407-9599","authenticated-orcid":true,"given":"Ziyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaomu","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"pone.0340108.ref001","doi-asserted-by":"crossref","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: A survey","volume":"88","author":"F Shamshad","year":"2023","journal-title":"Med Image Anal."},{"issue":"7","key":"pone.0340108.ref002","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1109\/TMI.2022.3213244","article-title":"Federated learning with privacy-preserving ensemble attention distillation","volume":"42","author":"X Gong","year":"2023","journal-title":"IEEE Trans Med Imaging."},{"key":"pone.0340108.ref003","doi-asserted-by":"crossref","first-page":"108540","DOI":"10.1016\/j.cmpb.2024.108540","article-title":"A multi-task framework for breast cancer segmentation and classification in ultrasound imaging","volume":"260","author":"C Aumente-Maestro","year":"2025","journal-title":"Comput Methods Programs Biomed."},{"key":"pone.0340108.ref004","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR); 2021. p. 1\u201321."},{"key":"pone.0340108.ref005","doi-asserted-by":"crossref","first-page":"124628","DOI":"10.1016\/j.eswa.2024.124628","article-title":"Efficient and lightweight layer-wise in-situ defect detection in laser powder bed fusion via knowledge distillation and structural re-parameterization","volume":"255","author":"K Tan","year":"2024","journal-title":"Expert Syst Applic."},{"issue":"3","key":"pone.0340108.ref006","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"PVT v2: Improved baselines with pyramid vision transformer","volume":"8","author":"W Wang","year":"2022","journal-title":"Comp Visual Med."},{"key":"pone.0340108.ref007","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli S, Touvron H, Leavitt ML, Morcos AS, Biroli G, Sagun L. Convit: Improving vision transformers with soft convolutional inductive biases. In: International conference on machine learning (ICML); 2021. p. 2286\u201396.","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"pone.0340108.ref008","doi-asserted-by":"crossref","unstructured":"Pan J, Bulat A, Tan F, Zhu X, Dudziak L, Li H, et al. Edgevits: Competing light-weight cnns on mobile devices with vision transformers. In: European conference on computer vision (ECCV); 2022. p. 294\u2013311.","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"pone.0340108.ref009","doi-asserted-by":"crossref","unstructured":"Liu Z, Hu H, Lin Y, Yao Z, Xie Z, Wei Y, et al. Swin transformer v2: Scaling up capacity and resolution. In: IEEE conference on computer vision and pattern recognition (CVPR); 2022. p. 12009\u201319.","DOI":"10.1109\/CVPR52688.2022.01170"},{"issue":"4","key":"pone.0340108.ref010","doi-asserted-by":"crossref","first-page":"5314","DOI":"10.1109\/TPAMI.2022.3206148","article-title":"ResMLP: Feedforward networks for image classification with data-efficient training","volume":"45","author":"H Touvron","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"key":"pone.0340108.ref011","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S. A convnet for the 2020 s. In: IEEE conference on computer vision and pattern recognition (CVPR); 2022. p. 11976\u201386.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"pone.0340108.ref012","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"J Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"pone.0340108.ref013","doi-asserted-by":"crossref","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, et al. Swin-unet: Unet-like pure transformer for medical image segmentation. In: European conference on computer vision (ECCV); 2022. p. 205\u201318.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"pone.0340108.ref014","doi-asserted-by":"crossref","unstructured":"Wang H, Xie S, Lin L, Iwamoto Y, Han X-H, Chen Y-W, et al. Mixed transformer U-net for medical image segmentation. In: ICASSP 2022 - 2022 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2022. 2390\u20134. https:\/\/doi.org\/10.1109\/icassp43922.2022.9746172","DOI":"10.1109\/ICASSP43922.2022.9746172"},{"key":"pone.0340108.ref015","first-page":"1","article-title":"Multiscale attention network for detection and localization of image splicing forgery","volume":"72","author":"Y Xu","year":"2023","journal-title":"IEEE Trans Instrum Meas."},{"key":"pone.0340108.ref016","doi-asserted-by":"crossref","first-page":"106285","DOI":"10.1016\/j.bspc.2024.106285","article-title":"PAMSNet: A medical image segmentation network based on spatial pyramid and attention mechanism","volume":"94","author":"Y Feng","year":"2024","journal-title":"Biomed Signal Process Control."},{"key":"pone.0340108.ref017","doi-asserted-by":"crossref","first-page":"108526","DOI":"10.1016\/j.cmpb.2024.108526","article-title":"Laplacian-guided hierarchical transformer: A network for medical image segmentation","volume":"260","author":"Y Chen","year":"2025","journal-title":"Comput Methods Programs Biomed."},{"issue":"9","key":"pone.0340108.ref018","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep convolutional neural networks for image classification: A comprehensive review","volume":"29","author":"W Rawat","year":"2017","journal-title":"Neural Comput."},{"key":"pone.0340108.ref019","doi-asserted-by":"crossref","unstructured":"Wu M, Zhou J, Peng Y, Wang S, Zhang Y. Deep learning for image classification: A review. In: International conference on medical imaging and computer-aided diagnosis (MICAD); 2023. p. 352\u201362.","DOI":"10.1007\/978-981-97-1335-6_31"},{"key":"pone.0340108.ref020","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NeurIPS). vol. 25; 2012. p. 1106\u201314."},{"key":"pone.0340108.ref021","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR); 2014. p. 1\u201314."},{"key":"pone.0340108.ref022","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR); 2015. p. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"pone.0340108.ref023","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR); 2016. p. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"pone.0340108.ref024","article-title":"Multi-modal medical image classification using deep residual network and genetic algorithm","volume":"18","author":"MH Abid","year":"2023","journal-title":"PLoS One."},{"key":"pone.0340108.ref025","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, J\u00e9gou H. Training data-efficient image transformers & distillation through attention. In: International conference on machine learning (ICML); 2021. p. 10347\u201357."},{"key":"pone.0340108.ref026","doi-asserted-by":"crossref","unstructured":"Touvron H, Cord M, Sablayrolles A, Synnaeve G, J\u00e9gou H. Going deeper with image transformers. In: IEEE international conference on computer vision (ICCV); 2021. p. 32\u201342.","DOI":"10.1109\/ICCV48922.2021.00010"},{"issue":"7","key":"pone.0340108.ref027","first-page":"3523","article-title":"Image segmentation using deep learning: A Survey","volume":"44","author":"S Minaee","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"key":"pone.0340108.ref028","unstructured":"Ciresan D, Giusti A, Gambardella L, Schmidhuber J. Deep neural networks segment neuronal membranes in electron microscopy images. In: Advances in neural information processing systems; 2012."},{"key":"pone.0340108.ref029","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR); 2015. p. 3431\u201340.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"pone.0340108.ref030","doi-asserted-by":"crossref","unstructured":"Strudel R, Garcia R, Laptev I, Schmid C. Segmenter: Transformer for semantic segmentation. In: IEEE international conference on computer vision (ICCV); 2021. p. 7262\u201372.","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"pone.0340108.ref031","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Fan DP, Song K, Liang D. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: IEEE international conference on computer vision (ICCV); 2021. p. 568\u201378.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"pone.0340108.ref032","doi-asserted-by":"crossref","unstructured":"Guo R, Niu D, Qu L, Li Z. Sotr: Segmenting objects with transformers. In: IEEE international conference on computer vision (ICCV); 2021. p. 7157\u201366.","DOI":"10.1109\/ICCV48922.2021.00707"},{"key":"pone.0340108.ref033","unstructured":"Chu X, Tian Z, Wang Y, Zhang B, Ren H, Wei X. In: Advances in neural information processing systems; 2021. p. 9355\u201366."},{"key":"pone.0340108.ref034","doi-asserted-by":"crossref","unstructured":"Jain J, Singh A, Orlov N, Huang Z, Li J, Walton S, et al. SeMask: Semantically masked transformers for semantic segmentation. In: 2023 IEEE\/CVF international conference on computer vision workshops (ICCVW); 2023. p. 752\u201361. https:\/\/doi.org\/10.1109\/iccvw60793.2023.00083","DOI":"10.1109\/ICCVW60793.2023.00083"},{"key":"pone.0340108.ref035","doi-asserted-by":"crossref","first-page":"105581","DOI":"10.1016\/j.cmpb.2020.105581","article-title":"CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images","volume":"196","author":"AI Khan","year":"2020","journal-title":"Comput Methods Programs Biomed."},{"key":"pone.0340108.ref036","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.ymeth.2019.06.014","article-title":"Breast cancer histopathological image classification using a hybrid deep neural network","volume":"173","author":"R Yan","year":"2020","journal-title":"Methods."},{"key":"pone.0340108.ref037","unstructured":"Hsu CC, Chen GL, Wu MH. Visual transformer with statistical test for covid-19 classification. arXiv preprint arXiv:210705334; 2021."},{"key":"pone.0340108.ref038","doi-asserted-by":"crossref","unstructured":"Yang H, Chen J, Xu M. Fundus disease image classification based on improved transformer. In: 2021 international conference on neuromorphic computing (ICNC); 2021. p. 207\u201314. https:\/\/doi.org\/10.1109\/icnc52316.2021.9608181","DOI":"10.1109\/ICNC52316.2021.9608181"},{"issue":"12","key":"pone.0340108.ref039","doi-asserted-by":"crossref","first-page":"10076","DOI":"10.1109\/TPAMI.2024.3435571","article-title":"Medical image segmentation review: The success of U-Net","volume":"46","author":"R Azad","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"key":"pone.0340108.ref040","doi-asserted-by":"crossref","first-page":"107747","DOI":"10.1016\/j.patcog.2020.107747","article-title":"Automatic COVID-19 lung infected region segmentation and measurement using CT-scans images","volume":"114","author":"A Oulefki","year":"2021","journal-title":"Pattern Recognit."},{"key":"pone.0340108.ref041","doi-asserted-by":"crossref","unstructured":"Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. Unet: A nested u-net architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support (DLMIA); 2018. p. 3\u201311.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"pone.0340108.ref042","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","article-title":"Attention gated networks: Learning to leverage salient regions in medical images","volume":"53","author":"J Schlemper","year":"2019","journal-title":"Med Image Anal."},{"key":"pone.0340108.ref043","article-title":"Layer normalization","author":"JL Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"pone.0340108.ref044","unstructured":"Soares E, Angelov P, Biaso S, Froes MH, Abe DK. SARS-CoV-2 CT-scan dataset: A large dataset of real patients CT scans for SARS-CoV-2 identification. MedRxiv. 2020:2020\u20132004."},{"key":"pone.0340108.ref045","unstructured":"Ali SN, Ahmed M, Paul J, Jahan T, Sani S, Noor N, et al. Monkeypox skin lesion detection using deep learning models: A feasibility study. arXiv preprint arXiv:220703342; 2022."},{"key":"pone.0340108.ref046","doi-asserted-by":"crossref","unstructured":"Maftouni M, Law ACC, Shen B, Grado ZJK, Zhou Y, Yazdi NA. A robust ensemble-deep learning model for COVID-19 diagnosis based on an integrated CT scan images database. In: IISE annual conference and expo; 2021.","DOI":"10.36227\/techrxiv.18166667"},{"key":"pone.0340108.ref047","unstructured":"Landman B, Xu Z, Igelsias J, Styner M, Langerak T, Klein A. Miccai multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In: Proc. MICCAI multi-atlas labeling beyond cranial vault\u2014Workshop challenge. vol. 5; 2015. p. 12."},{"issue":"11","key":"pone.0340108.ref048","doi-asserted-by":"crossref","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","article-title":"Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved?","volume":"37","author":"O Bernard","year":"2018","journal-title":"IEEE Trans Med Imaging."},{"key":"pone.0340108.ref049","unstructured":"Loshchilov I, Hutter F. Decoupled weight decay regularization. In: International conference on learning representations (ICLR); 2019. p. 1\u201318."},{"key":"pone.0340108.ref050","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. In: International conference on learning representations (ICLR); 2015. p. 1\u201315."},{"key":"pone.0340108.ref051","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognition (CVPR); 2017. p. 4700\u20138.","DOI":"10.1109\/CVPR.2017.243"},{"key":"pone.0340108.ref052","unstructured":"Tolstikhin IO, Houlsby N, Kolesnikov A, Beyer L, Zhai X, Unterthiner T. Mlp-mixer: An all-mlp architecture for vision. In: Advances in neural information processing systems; 2021. p. 24261\u201372."},{"issue":"2","key":"pone.0340108.ref053","doi-asserted-by":"crossref","first-page":"2344","DOI":"10.1609\/aaai.v36i2.20133","article-title":"Sparse MLP for image recognition: Is self-attention really necessary?","volume":"36","author":"C Tang","year":"2022","journal-title":"AAAI."},{"issue":"8","key":"pone.0340108.ref054","doi-asserted-by":"crossref","first-page":"2688","DOI":"10.1109\/TMI.2020.2993291","article-title":"Deep learning COVID-19 features on CXR using limited training data sets","volume":"39","author":"Y Oh","year":"2020","journal-title":"IEEE Trans Med Imaging."},{"key":"pone.0340108.ref055","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention (MICCAI); 2015. p. 234\u201341.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"pone.0340108.ref056","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi SA.V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: International conference on 3D vision (3DV); 2016. p. 565\u201371.","DOI":"10.1109\/3DV.2016.79"},{"key":"pone.0340108.ref057","doi-asserted-by":"crossref","unstructured":"Fu S, Lu Y, Wang Y, Zhou Y, Shen W, Fishman E, et al. Domain adaptive relational reasoning for 3d multi-organ segmentation. In: International conference on medical image computing and computer-assisted intervention (MICCAI); 2020. p. 656\u201366.","DOI":"10.1007\/978-3-030-59710-8_64"},{"issue":"2","key":"pone.0340108.ref058","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"F Isensee","year":"2021","journal-title":"Nat Methods."}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:50:19Z","timestamp":1767639019000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340108"}},"subtitle":[],"editor":[{"given":"Aamna","family":"AlShehhi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":58,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340108","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]}}}