{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T05:40:26Z","timestamp":1787982026536,"version":"build-2784847793"},"reference-count":65,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate classification of cervical cytology images plays a crucial role in early detection and prevention of cervical cancer, which remains a significant global health challenge. Despite advancements in deep learning for medical image analysis, the unique characteristics of cervical cells, including subtle morphological differences and complex nuclear patterns, pose considerable challenges for automated classification systems. In this paper, we present a novel deep learning architecture specifically designed for cervical cytology image classification. Our approach integrates three key components: (1) a specialized data augmentation pipeline tailored for cytopathology images, (2) a Morphology Attention Module (MAM) that captures multi-scale cellular features with adaptive feature fusion, and (3) a Spatial-Channel Mixer (SCM) that efficiently encodes nuclear neighborhood spatial information. Extensive experiments on both the SIPaKMeD and Mendeley LBC datasets demonstrate the superior performance of our model, achieving state-of-the-art accuracy of 99.06% on the 5-class SIPaKMeD dataset and 98.55% on the Mendeley LBC dataset. Importantly, our approach reduces error rates by up to 82.5% compared to conventional CNN architectures and 61.8% compared to recent Vision Transformer approaches. The proposed architecture demonstrates robust generalization across different cell types and imaging conditions, making it a promising tool for enhancing cervical cancer screening programs. Our work contributes to the advancement of automated cytology analysis and has the potential to improve early detection of cervical abnormalities, particularly in resource-limited settings where expert cytopathologists may be scarce.<\/jats:p>","DOI":"10.1371\/journal.pone.0351063","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T17:44:48Z","timestamp":1781113488000},"page":"e0351063","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-scale feature integration with enhanced cytomorph for high-accuracy cervical cytology classification"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1468-4944","authenticated-orcid":true,"given":"Elif","family":"\u0130lgazi K\u0131l\u0131\u00e7","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2014-7638","authenticated-orcid":true,"given":"\u015eafak","family":"K\u0131l\u0131\u00e7","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"pone.0351063.ref001","doi-asserted-by":"crossref","first-page":"111482","DOI":"10.1016\/j.knosys.2024.111482","article-title":"MaxCerVixT: A novel lightweight vision transformer-based Approach for precise cervical cancer detection","volume":"289","author":"I Pacal","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"pone.0351063.ref002","doi-asserted-by":"crossref","first-page":"101496","DOI":"10.1016\/j.imu.2024.101496","article-title":"A federated learning aided system for classifying cervical cancer using PAP-SMEAR images","volume":"47","author":"NS Joyinab","year":"2024","journal-title":"Informatics in Medicine Unlocked"},{"key":"pone.0351063.ref003","doi-asserted-by":"crossref","DOI":"10.1177\/20552076241295440","article-title":"CerviXpert: A multi-structural convolutional neural network for predicting cervix type and cervical cell abnormalities","volume":"10","author":"RS Akash","year":"2024","journal-title":"Digital Health"},{"key":"pone.0351063.ref004","article-title":"Improving cervical cancer classification in PAP smear images with enhanced segmentation and deep progressive learning-based techniques","author":"P Mahajan","year":"2024","journal-title":"Diagnost Cytopathol"},{"issue":"1","key":"pone.0351063.ref005","doi-asserted-by":"crossref","DOI":"10.1007\/s44163-024-00185-6","article-title":"Optimizing cervical cancer classification using transfer learning with deep gaussian processes and support vector machines","volume":"4","author":"E Ahishakiye","year":"2024","journal-title":"Discov Artif Intell"},{"issue":"30","key":"pone.0351063.ref006","doi-asserted-by":"crossref","first-page":"75343","DOI":"10.1007\/s11042-024-18608-y","article-title":"Enhancing cervical cancer diagnosis with graph convolution network: AI-powered segmentation, feature analysis, and classification for early detection","volume":"83","author":"NM Fahad","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"pone.0351063.ref007","article-title":"Comparison of deep transfer learning models for classification of cervical cancer from pap smear images","author":"H Kaur","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0351063.ref008","unstructured":"Dasa S, Sethyc M, Giric PP, et al. Comparative analysis of machine learning and deep learning models for classifying squamous epithelial cells of the cervix. AI and HPC Research Center. 2024."},{"issue":"1","key":"pone.0351063.ref009","doi-asserted-by":"crossref","first-page":"28","DOI":"10.69882\/adba.ai.2025075","article-title":"A Comparative Analysis of Convolutional Neural Network Architectures for Breast Cancer Classification from Mammograms","volume":"1","author":"Y \u00c7akmak","year":"2025","journal-title":"AIAPP"},{"issue":"1","key":"pone.0351063.ref010","doi-asserted-by":"crossref","first-page":"20","DOI":"10.69882\/adba.csai.2025074","article-title":"Deep Learning for Early Diagnosis of Lung Cancer","volume":"1","author":"Y \u00c7akmak","year":"2025","journal-title":"CSAI"},{"key":"pone.0351063.ref011","doi-asserted-by":"crossref","first-page":"120624","DOI":"10.1016\/j.eswa.2023.120624","article-title":"CerCan\u00b7Net: Cervical cancer classification model via multi-layer feature ensembles of lightweight CNNs and transfer learning","volume":"229","author":"O Attallah","year":"2023","journal-title":"Exp Syst Appl"},{"key":"pone.0351063.ref012","doi-asserted-by":"crossref","first-page":"103428","DOI":"10.1016\/j.bspc.2021.103428","article-title":"Exemplar pyramid deep feature extraction based cervical cancer image classification model using pap-smear images","volume":"73","author":"O Yaman","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"pone.0351063.ref013","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1016\/j.eswa.2018.08.050","article-title":"Classification and diagnosis of cervical cancer with stacked autoencoder and softmax classification","volume":"115","author":"K Adem","year":"2019","journal-title":"Expert Systems with Applications"},{"key":"pone.0351063.ref014","doi-asserted-by":"crossref","unstructured":"Albayrak A, Unlu A, Calik N, Bilgin G, Turkmen I, Cakir A, et al. Segmentation of precursor lesions in cervical cancer using convolutional neural networks. In: 2017 25th Signal Processing and Communications Applications Conference (SIU), 2017. p. 1\u20134. https:\/\/doi.org\/10.1109\/siu.2017.7960459","DOI":"10.1109\/SIU.2017.7960459"},{"key":"pone.0351063.ref015","doi-asserted-by":"crossref","first-page":"106336","DOI":"10.1016\/j.engappai.2023.106336","article-title":"MSENet: Mean and standard deviation based ensemble network for cervical cancer detection","volume":"123","author":"R Pramanik","year":"2023","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0351063.ref016","first-page":"1","article-title":"A fuzzy rank-based ensemble of CNN models for classification of cervical cytology","volume":"11","author":"A Manna","year":"2021","journal-title":"Scient Rep"},{"issue":"2","key":"pone.0351063.ref017","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/s11390-021-0849-3","article-title":"CytoBrain: Cervical Cancer Screening System Based on Deep Learning Technology","volume":"36","author":"H Chen","year":"2021","journal-title":"J Comput Sci Technol"},{"key":"pone.0351063.ref018","doi-asserted-by":"crossref","unstructured":"Tripathi A, Arora A, Bhan A. Classification of cervical cancer using deep learning algorithm. In: Proceedings - 5th International Conference on Intelligent Computing and Control Systems (ICICCS). 2021. p. 1210\u20138.","DOI":"10.1109\/ICICCS51141.2021.9432382"},{"issue":"9","key":"pone.0351063.ref019","doi-asserted-by":"crossref","first-page":"3272","DOI":"10.3390\/s22093272","article-title":"Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification","volume":"22","author":"W Chen","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0351063.ref020","doi-asserted-by":"crossref","first-page":"104920","DOI":"10.1016\/j.bspc.2023.104920","article-title":"CervixFuzzyFusion for cervical cancer cell image classification","volume":"85","author":"K Hemalatha","year":"2023","journal-title":"Biomed Signal Process Control"},{"issue":"11","key":"pone.0351063.ref021","doi-asserted-by":"crossref","first-page":"3911","DOI":"10.1007\/s13042-023-01872-z","article-title":"Cervical cancerous cell classification: opposition-based harmony search for deep feature selection","volume":"14","author":"N Das","year":"2023","journal-title":"Int J Mach Learn & Cyber"},{"key":"pone.0351063.ref022","doi-asserted-by":"crossref","DOI":"10.1007\/s42979-021-00741-2","article-title":"Cervical cytology classification using PCA and GWO enhanced deep features selection","volume":"2","author":"H Basak","year":"2021","journal-title":"SN Comput Sci"},{"key":"pone.0351063.ref023","doi-asserted-by":"crossref","first-page":"103177","DOI":"10.1016\/j.bspc.2021.103177","article-title":"Lightweight convolutional neural network with knowledge distillation for cervical cells classification","volume":"71","author":"W Chen","year":"2022","journal-title":"Biomed Signal Process Control"},{"issue":"1","key":"pone.0351063.ref024","doi-asserted-by":"crossref","first-page":"3551","DOI":"10.1038\/s41598-022-07186-4","article-title":"Federated learning for multi-center imaging diagnostics: a simulation study in cardiovascular disease","volume":"12","author":"A Linardos","year":"2022","journal-title":"Sci Rep"},{"key":"pone.0351063.ref025","doi-asserted-by":"crossref","unstructured":"Sheller MJ, Reina GA, Edwards B, Martin J, Bakas S. Multi-institutional deep learning modeling without sharing patient data: a feasibility study on brain tumor segmentation. In: BrainLes 2018, MICCAI 2018. 2019. p. 92\u2013104.","DOI":"10.1007\/978-3-030-11723-8_9"},{"key":"pone.0351063.ref026","doi-asserted-by":"crossref","first-page":"860532","DOI":"10.3389\/fonc.2022.860532","article-title":"An assisted diagnosis model for cancer patients based on federated learning","volume":"12","author":"Z Ma","year":"2022","journal-title":"Front Oncol"},{"issue":"5","key":"pone.0351063.ref027","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1007\/s12553-019-00375-8","article-title":"Cervical cancer prognosis using genetic algorithm and adaptive boosting approach","volume":"9","author":"M Sharma","year":"2019","journal-title":"Health Technol"},{"key":"pone.0351063.ref028","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/bioengineering9100578","article-title":"Cervical net: a novel cervical cancer classification using feature fusion","volume":"9","author":"H Alquran","year":"2022","journal-title":"Bioengineering"},{"key":"pone.0351063.ref029","doi-asserted-by":"crossref","first-page":"788376","DOI":"10.3389\/fpubh.2021.788376","article-title":"Machine learning assisted cervical cancer detection","volume":"9","author":"M Mehmood","year":"2021","journal-title":"Front Public Health"},{"issue":"2","key":"pone.0351063.ref030","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1002\/cam4.4460","article-title":"A screening assistance system for cervical cytology of squamous cell atypia based on a two-step combined CNN algorithm with label smoothing","volume":"11","author":"Y Nambu","year":"2022","journal-title":"Cancer Med"},{"key":"pone.0351063.ref031","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/JBHI.2021.3094311","article-title":"Cervical cancer diagnostics healthcare system using hybrid object detection adversarial networks","volume":"26","author":"R Elakkiya","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"issue":"11","key":"pone.0351063.ref032","doi-asserted-by":"crossref","first-page":"8590","DOI":"10.1007\/s11227-020-03159-4","article-title":"Internet of health things-driven deep learning system for detection and classification of cervical cells using transfer learning","volume":"76","author":"A Khamparia","year":"2020","journal-title":"J Supercomput"},{"key":"pone.0351063.ref033","doi-asserted-by":"crossref","first-page":"107070","DOI":"10.1016\/j.compbiomed.2023.107070","article-title":"CAM-VT: A Weakly supervised cervical cancer nest image identification approach using conjugated attention mechanism and visual transformer","volume":"162","author":"Z Fan","year":"2023","journal-title":"Comput Biol Med"},{"key":"pone.0351063.ref034","doi-asserted-by":"crossref","first-page":"104649","DOI":"10.1016\/j.compbiomed.2021.104649","article-title":"DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques","volume":"136","author":"MM Rahaman","year":"2021","journal-title":"Comput Biol Med"},{"issue":"9","key":"pone.0351063.ref035","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0331896","article-title":"FocusGate-Net: A dual-attention guided MLP-convolution hybrid network for accurate and efficient medical image segmentation","volume":"20","author":"\u015e K\u0131l\u0131\u00e7","year":"2025","journal-title":"PLoS One"},{"issue":"3","key":"pone.0351063.ref036","doi-asserted-by":"crossref","first-page":"297","DOI":"10.51537\/chaos.1807694","article-title":"Chaotic Learning Rate Scheduling for Improved CNN-Based Breast Cancer Ultrasound Classification","volume":"7","author":"I Pacal","year":"2025","journal-title":"CHTA"},{"issue":"9","key":"pone.0351063.ref037","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0330914","article-title":"Deep feature engineering for accurate sperm morphology classification using CBAM-enhanced ResNet50","volume":"20","author":"\u015e K\u0131l\u0131\u00e7","year":"2025","journal-title":"PLoS One"},{"key":"pone.0351063.ref038","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.3329","article-title":"Densenet201+ with multi-scale attention and deep feature engineering for automated Kellgren\u2013Lawrence grading of knee osteoarthritis","volume":"11","author":"\u015e K\u0131l\u0131\u00e7","year":"2025","journal-title":"PeerJ Comput Sci"},{"issue":"1","key":"pone.0351063.ref039","article-title":"Investigating deep learning approaches for cervical cancer diagnosis: a focus on modern image-based models","volume":"46","author":"I Pacal","year":"2025","journal-title":"Eur J Gynaecol Oncol"},{"issue":"3","key":"pone.0351063.ref040","doi-asserted-by":"crossref","first-page":"655","DOI":"10.21605\/cukurovaumfd.1653486","article-title":"A Novel Multi-Head Attention Framework for COVID-19 Detection: Hybrid Integration of MobileNet and VGG19 with Enhanced Feature Learning","volume":"40","author":"\u015e K\u0131l\u0131\u00e7","year":"2025","journal-title":"\u00c7ukurova \u00dcniv M\u00fchendislik Fak\u00fcltesi Dergisi"},{"key":"pone.0351063.ref041","doi-asserted-by":"crossref","DOI":"10.37349\/emed.2025.1001377","article-title":"Comparative analysis of transformer architectures for brain tumor classification","volume":"6","author":"Y Cakmak","year":"2025","journal-title":"Explor Med"},{"key":"pone.0351063.ref042","doi-asserted-by":"crossref","first-page":"30399","DOI":"10.1007\/s11042-020-09607-w","article-title":"DCAVN: Cervical cancer prediction and classification using deep convolutional and variational autoencoder network","volume":"80","author":"A Khamparia","year":"2021","journal-title":"Multimed Tools Appl"},{"issue":"32","key":"pone.0351063.ref043","first-page":"50","article-title":"An improved deep learning based cervical cancer detection using a median filter based preprocessing","author":"ZK \u015eent\u00fcrk","year":"2022","journal-title":"Avrupa Bilim ve Teknoloji Dergisi"},{"key":"pone.0351063.ref044","doi-asserted-by":"crossref","first-page":"101677","DOI":"10.1016\/j.tice.2021.101677","article-title":"Cervical cell multi-classification algorithm using global context information and attention mechanism","volume":"74","author":"J Li","year":"2022","journal-title":"Tissue Cell"},{"issue":"1","key":"pone.0351063.ref045","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s11042-021-10627-3","article-title":"Imaging based cervical cancer diagnostics using small object detection - generative adversarial networks","volume":"81","author":"R Elakkiya","year":"2021","journal-title":"Multimed Tools Appl"},{"key":"pone.0351063.ref046","doi-asserted-by":"crossref","first-page":"130968","DOI":"10.1109\/ACCESS.2022.3230280","article-title":"A Deep Neural Network for Cervical Cell Classification Based on Cytology Images","volume":"10","author":"M Fang","year":"2022","journal-title":"IEEE Access"},{"issue":"3","key":"pone.0351063.ref047","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1007\/s11517-022-02745-3","article-title":"Cervical cell classification with deep-learning algorithms","volume":"61","author":"L Xu","year":"2023","journal-title":"Med Biol Eng Comput"},{"issue":"9","key":"pone.0351063.ref048","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e29913","article-title":"CerviLearnNet: Advancing cervical cancer diagnosis with reinforcement learning-enhanced convolutional networks","volume":"10","author":"S Muksimova","year":"2024","journal-title":"Heliyon"},{"key":"pone.0351063.ref049","doi-asserted-by":"crossref","first-page":"108829","DOI":"10.1016\/j.patcog.2022.108829","article-title":"CVM-Cervix: A hybrid cervical Pap-smear image classification framework using CNN, visual transformer and multilayer perceptron","volume":"130","author":"W Liu","year":"2022","journal-title":"Pattern Recognit"},{"issue":"17","key":"pone.0351063.ref050","doi-asserted-by":"crossref","first-page":"24265","DOI":"10.1007\/s11042-022-12670-0","article-title":"Improving cervical cancer classification with imbalanced datasets combining taming transformers with T2T-ViT","volume":"81","author":"C Zhao","year":"2022","journal-title":"Multimed Tools Appl"},{"key":"pone.0351063.ref051","doi-asserted-by":"crossref","first-page":"104156","DOI":"10.1016\/j.bspc.2022.104156","article-title":"VisionCervix: Papanicolaou cervical smears classification using novel CNN-Vision ensemble approach","volume":"79","author":"R Maurya","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"pone.0351063.ref052","doi-asserted-by":"crossref","first-page":"108153","DOI":"10.1016\/j.compbiomed.2024.108153","article-title":"Deep integrated fusion of local and global features for cervical cell classification","volume":"171","author":"M Fang","year":"2024","journal-title":"Comput Biol Med"},{"key":"pone.0351063.ref053","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/OJEMB.2024.3367243","article-title":"MFEM-CIN: A Lightweight Architecture Combining CNN and Transformer for the Classification of Pre-Cancerous Lesions of the Cervix","volume":"5","author":"P Chen","year":"2024","journal-title":"IEEE Open J Eng Med Biol"},{"issue":"5","key":"pone.0351063.ref054","article-title":"Vtcnet: A feature fusion DL model based on CNN and ViT for the classification of cervical cells","volume":"34","author":"M Li","year":"2024","journal-title":"Int J Imag Syst Technol"},{"key":"pone.0351063.ref055","doi-asserted-by":"crossref","unstructured":"8, IEEE.Plissiti ME, Dimitrakopoulos P, Sfikas G, Nikou C, Krikoni O, Charchanti A. SIPaKMeD: A new dataset for feature and image based classification of normal and pathological cervical cells in Pap smear images. In: Proc. 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, IEEE, Oct. 7\u201310, 2018, p. 3144\u20138.","DOI":"10.1109\/ICIP.2018.8451588"},{"key":"pone.0351063.ref056","doi-asserted-by":"crossref","first-page":"105589","DOI":"10.1016\/j.dib.2020.105589","article-title":"Liquid based-cytology Pap smear dataset for automated multi-class diagnosis of pre-cancerous and cervical cancer lesions","volume":"30","author":"E Hussain","year":"2020","journal-title":"Data Brief"},{"key":"pone.0351063.ref057","doi-asserted-by":"crossref","first-page":"16","DOI":"10.25259\/Cytojournal_24_2021","article-title":"Squamous intraepithelial lesions (SIL: LSIL, HSIL, ASCUS, ASC-H, LSIL-H) of uterine cervix and Bethesda system","volume":"18","author":"A Alrajjal","year":"2021","journal-title":"Cytojournal"},{"key":"pone.0351063.ref058","doi-asserted-by":"crossref","first-page":"100340","DOI":"10.1016\/j.health.2024.100340","article-title":"A systematic review of deep learning data augmentation in medical imaging: Recent advances and future research directions","volume":"5","author":"T Islam","year":"2024","journal-title":"Healthc Anal"},{"key":"pone.0351063.ref059","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015. p. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"pone.0351063.ref060","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Dollar P, Tu Z, He K. Aggregated Residual Transformations for Deep Neural Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. p. 5987\u201395.","DOI":"10.1109\/CVPR.2017.634"},{"key":"pone.0351063.ref061","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS. CBAM: Convolutional Block Attention Module. In: Proceedings of the European Conference on Computer Vision (ECCV). 2018. p. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"pone.0351063.ref062","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-Excitation Networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018. p. 7132\u201341.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"pone.0351063.ref063","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0351063.ref064","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. 2017."},{"key":"pone.0351063.ref065","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. arXiv preprint arXiv:2010.11929. 2020."}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0351063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T17:45:05Z","timestamp":1781113505000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0351063"}},"subtitle":[],"editor":[{"given":"Wencheng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":65,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,10]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0351063","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]}}}