{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:49:04Z","timestamp":1784137744788,"version":"3.55.0"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3448302","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T18:47:25Z","timestamp":1724352445000},"page":"117627-117649","source":"Crossref","is-referenced-by-count":26,"title":["CViTS-Net: A CNN-ViT Network With Skip Connections for Histopathology Image Classification"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0954-8424","authenticated-orcid":false,"given":"Anusree","family":"Kanadath","sequence":"first","affiliation":[{"name":"Department of Computer Science, Birla Institute of Technology and Science, Pilani, Dubai Campus, Dubai, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1773-8779","authenticated-orcid":false,"given":"J. Angel Arul","family":"Jothi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Birla Institute of Technology and Science, Pilani, Dubai Campus, Dubai, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6897-6243","authenticated-orcid":false,"given":"Siddhaling","family":"Urolagin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Birla Institute of Technology and Science, Pilani, Dubai Campus, Dubai, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1474"},{"issue":"5","key":"ref2","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1038\/s41591-021-01343-4","article-title":"Deep learning in histopathology: The path to the clinic","volume":"27","author":"van der Laak","year":"2021","journal-title":"Nature Med."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-60761-849-2_4"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/B978-0-12-821259-2.00011-9","article-title":"Artificial intelligence for pathology","volume-title":"Artificial Intelligence in Medicine","author":"Xing","year":"2021"},{"key":"ref5","article-title":"A comprehensive review of deep neural networks for medical image processing: Recent developments and future opportunities","volume":"4","author":"Mall","year":"2023","journal-title":"Healthcare Anal."},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1155\/2023\/7091301","article-title":"A review paper about deep learning for medical image analysis","volume":"2023","author":"Sistaninejhad","year":"2023","journal-title":"Comput. Math. Methods Med."},{"issue":"18","key":"ref7","doi-asserted-by":"crossref","first-page":"10521","DOI":"10.3390\/app131810521","article-title":"Applying deep learning to medical imaging: A review","volume":"13","author":"Zhang","year":"2023","journal-title":"Appl. Sci."},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.105032","article-title":"Deep learning based pipelines for Alzheimer\u2019s disease diagnosis: A comparative study and a novel deep-ensemble method","volume":"141","author":"Loddo","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/AIIoT54504.2022.9817327"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/rbme.2024.3357877"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03951-2"},{"issue":"7","key":"ref12","doi-asserted-by":"crossref","first-page":"5930","DOI":"10.3390\/su15075930","article-title":"A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope","volume":"15","author":"Salehi","year":"2023","journal-title":"Sustainability"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/fbinf.2023.1007986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1053\/j.semdp.2023.02.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpi.2022.100184"},{"issue":"12","key":"ref16","doi-asserted-by":"crossref","first-page":"4426","DOI":"10.3390\/s22124426","article-title":"Performance analysis of State-of-the-Art CNN architectures for LUNA16","volume":"22","author":"Naseer","year":"2022","journal-title":"Sensors"},{"key":"ref17","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref18","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-023-01157-0"},{"key":"ref20","first-page":"15","article-title":"Vision transformers for histopathology image analsysis survey","volume-title":"Proc. Image Anal. Process. (ICIAP) Workshops","author":"Baroni"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.csbj.2018.01.001","article-title":"Machine learning methods for histopathological image analysis","volume":"16","author":"Komura","year":"2018","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref23","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref24","article-title":"Vision transformers in medical imaging: A review","author":"Henry","year":"2022","journal-title":"arXiv:2211.10043"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.105253","article-title":"A review on multimodal medical image fusion: Compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics","volume":"144","author":"Azam","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref26","article-title":"Explainable AI in medical imaging: An overview for clinical practitioners\u2014Beyond saliency-based XAI approaches","volume":"162","author":"Borys","year":"2023","journal-title":"Eur. J. Radiol."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-020-00540-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230477"},{"issue":"3","key":"ref29","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.3390\/s23031356","article-title":"CNN\u2013RNN network integration for the diagnosis of COVID-19 using chest X-ray and CT images","volume":"23","author":"Kanjanasurat","year":"2023","journal-title":"Sensors"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12019"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1007\/s10278-023-00811-2","article-title":"CCS-GAN: COVID-19 CT scan generation and classification with very few positive training images","volume":"36","author":"Menon","year":"2023","journal-title":"J. Digit. Imag."},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.105063","article-title":"Generative adversarial networks in medical image segmentation: A review","volume":"140","author":"Xun","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13235"},{"key":"ref34","first-page":"9215","article-title":"What makes transfer learning work for medical images: Feature reuse & other factors","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Matsoukas"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.neucom.2021.08.159","article-title":"Transfer learning for medical images analyses: A survey","volume":"489","author":"Yu","year":"2022","journal-title":"Neurocomputing"},{"key":"ref36","article-title":"Is it time to replace CNNs with transformers for medical images?","author":"Matsoukas","year":"2021","journal-title":"arXiv:2108.09038"},{"key":"ref37","doi-asserted-by":"crossref","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_36"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-022-10032-4"},{"issue":"22","key":"ref40","doi-asserted-by":"crossref","first-page":"10982","DOI":"10.3390\/app112210982","article-title":"Deep learning approaches to colorectal cancer diagnosis: A review","volume":"11","author":"Tamang","year":"2021","journal-title":"Appl. Sci."},{"issue":"4","key":"ref41","doi-asserted-by":"crossref","first-page":"837","DOI":"10.3390\/diagnostics12040837","article-title":"Deep learning on histopathological images for colorectal cancer diagnosis: A systematic review","volume":"12","author":"Davri","year":"2022","journal-title":"Diagnostics"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIS52592.2021.9694125"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48175\/ijarsct-15029"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2022.104172","article-title":"CRCCN-net: Automated framework for classification of colorectal tissue using histopathological images","volume":"79","author":"Kumar","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-35431-x"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3321686"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.105265","article-title":"IL-MCAM: An interactive learning and multi-channel attention mechanism-based weakly supervised colorectal histopathology image classification approach","volume":"143","author":"Chen","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3150924"},{"issue":"3","key":"ref49","doi-asserted-by":"crossref","first-page":"748","DOI":"10.3390\/s21030748","article-title":"A machine learning approach to diagnosing lung and colon cancer using a deep learning-based classification framework","volume":"21","author":"Masud","year":"2021","journal-title":"Sensors"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03575-6"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3226268"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123265"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107086"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103742"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-54846-8"},{"issue":"1","key":"ref56","doi-asserted-by":"crossref","first-page":"72","DOI":"10.3390\/diagnostics13010072","article-title":"A deep CNN transformer hybrid model for skin lesion classification of dermoscopic images using focal loss","volume":"13","author":"Nie","year":"2022","journal-title":"Diagnostics"},{"issue":"7","key":"ref57","doi-asserted-by":"crossref","first-page":"140","DOI":"10.3390\/jimaging9070140","article-title":"Conv-ViT: A convolution and vision transformer-based hybrid feature extraction method for retinal disease detection","volume":"9","author":"Dutta","year":"2023","journal-title":"J. Imag."},{"key":"ref58","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2022.106924","article-title":"StoHisNet: A hybrid multi-classification model with CNN and transformer for gastric pathology images","volume":"221","author":"Fu","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108827"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/NTIC55069.2022.10100518"},{"key":"ref61","article-title":"Exploring the synergies of hybrid CNNs and ViTs architectures for computer vision: A survey","author":"Yunusa","year":"2024","journal-title":"arXiv:2402.02941"},{"key":"ref62","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref64","first-page":"1800","article-title":"Xception: Deep learning with depthwise separable convolutions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Chollet"},{"issue":"6","key":"ref65","doi-asserted-by":"crossref","first-page":"2888","DOI":"10.1109\/TVCG.2023.3261935","article-title":"How does attention work in vision transformers? A visual analytics attempt","volume":"29","author":"Li","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"ref66","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"ref68","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref69","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.104730","article-title":"Deep learning for colon cancer histopathological images analysis","volume":"136","author":"Ben Hamida","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref70","article-title":"Vision transformer for contrastive clustering","author":"Ling","year":"2022","journal-title":"arXiv:2206.12925"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22875"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCCC58608.2023.10176535"},{"key":"ref73","article-title":"ViT-DAE: Transformer-driven diffusion autoencoder for histopathology image analysis","author":"Xu","year":"2023","journal-title":"arXiv:2304.01053"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIPTEKNO56568.2022.9960184"},{"key":"ref75","first-page":"6864","article-title":"Limited data, unlimited potential: A study on ViTs augmented by masked autoencoders","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)","author":"Das"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_11"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103070"},{"key":"ref78","first-page":"110","article-title":"Locality guidance for improving vision transformers on tiny datasets","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Li"},{"key":"ref79","article-title":"TVT: Training-free vision transformer search on tiny datasets","author":"Wei","year":"2023","journal-title":"arXiv:2311.14337"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref81","first-page":"1","article-title":"Going deeper with convolutions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Szegedy"},{"key":"ref82","first-page":"11916","article-title":"Rethinking spatial dimensions of vision transformers","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Heo"},{"key":"ref83","first-page":"22","article-title":"CvT: Introducing convolutions to vision transformers","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Wu"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-39618-0"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref86","first-page":"1","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mehta"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.4103\/2153-3539.186902"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71051-4_1"},{"key":"ref89","volume-title":"Classifying lymphoma subtypes using CNN and CNN LSTM mixed model","author":"Savas","year":"2021"},{"issue":"11","key":"ref90","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.3390\/bioengineering10111279","article-title":"RCKD: Response-based cross-task knowledge distillation for pathological image analysis","volume":"10","author":"Kim","year":"2023","journal-title":"Bioengineering"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10555-1"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.aci.2018.06.002"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.3233\/THC-218031"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00138"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/SETIT54465.2022.9875482"},{"key":"ref96","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117238","article-title":"Classification of non-hodgkin lymphomas based on sample entropy signatures","volume":"202","author":"Rozendo","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1117\/12.2043872"},{"issue":"5","key":"ref98","doi-asserted-by":"crossref","first-page":"4244","DOI":"10.3390\/ijerph20054244","article-title":"Enhancing the breast histopathology image analysis for cancer detection using variational autoencoder","volume":"20","author":"Guleria","year":"2023","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53728-8_13"},{"key":"ref100","article-title":"Supervised contrastive vision transformer for breast histopathological image classification","author":"Shiri","year":"2024","journal-title":"arXiv:2404.11052"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3390\/computation11030059"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2023457"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106258"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105118"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10643450.pdf?arnumber=10643450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:43:06Z","timestamp":1725252186000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10643450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":104,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3448302","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}