{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:38:40Z","timestamp":1782833920783,"version":"3.54.5"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.fr","clinicalkey.jp","clinicalkey.es","clinicalkey.com.au","clinicalkey.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computerized Medical Imaging and Graphics"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1016\/j.compmedimag.2025.102524","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T08:03:28Z","timestamp":1741766608000},"page":"102524","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["NaMA-Mamba: Foundation model for generalizable nasal disease detection using masked autoencoder with Mamba on endoscopic images"],"prefix":"10.1016","volume":"122","author":[{"given":"Wensheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zewen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueli","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-0678","authenticated-orcid":false,"given":"Xinrong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compmedimag.2025.102524_b1","doi-asserted-by":"crossref","unstructured":"Bai, Y., Geng, X., Mangalam, K., Bar, A., Yuille, A.L., Darrell, T., Malik, J., Efros, A.A., 2024. Sequential modeling enables scalable learning for large vision models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 22861\u201322872.","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"10.1016\/j.compmedimag.2025.102524_b2","series-title":"International Conference on Intelligent Systems Design and Applications","article-title":"COVID-vit: COVID-19 detection method based on vision transformers","author":"Balderas","year":"2022"},{"key":"10.1016\/j.compmedimag.2025.102524_b3","series-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021"},{"key":"10.1016\/j.compmedimag.2025.102524_b4","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","article-title":"Optimizing the dice score and jaccard index for medical image segmentation: Theory and practice","author":"Bertels","year":"2019"},{"key":"10.1016\/j.compmedimag.2025.102524_b5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2025.102524_b6","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A., 2021. Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10.1016\/j.compmedimag.2025.102524_b7","series-title":"International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"issue":"3","key":"10.1016\/j.compmedimag.2025.102524_b8","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1111\/j.1467-9868.2012.01046.x","article-title":"SMC2: An efficient algorithm for sequential analysis of state space models","volume":"75","author":"Chopin","year":"2013","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.compmedimag.2025.102524_b9","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J., 2021. Up-detr: Unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1601\u20131610.","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"10.1016\/j.compmedimag.2025.102524_b10","article-title":"Swin MAE: Masked autoencoders for small datasets","volume":"161","author":"Dai","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.compmedimag.2025.102524_b11","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.compmedimag.2025.102524_b12","doi-asserted-by":"crossref","unstructured":"Duan, Z., Lu, M., Ma, Z., Zhu, F., 2023. Lossy image compression with quantized hierarchical vaes. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 198\u2013207.","DOI":"10.1109\/WACV56688.2023.00028"},{"key":"10.1016\/j.compmedimag.2025.102524_b13","doi-asserted-by":"crossref","DOI":"10.1007\/s11042-021-10783-6","article-title":"Automatic prediction of COVID-19 from chest images using modified ResNet50","author":"Elpeltagy","year":"2021","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.compmedimag.2025.102524_b14","first-page":"354","article-title":"Multi-objective evolutionary optimization using the relationship between F1 and accuracy metrics in classification tasks","volume":"79","author":"Fern\u00e1ndez","year":"2019","journal-title":"Appl. Softw. Comput."},{"key":"10.1016\/j.compmedimag.2025.102524_b15","series-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Fu","year":"2022"},{"key":"10.1016\/j.compmedimag.2025.102524_b16","series-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.compmedimag.2025.102524_b17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R., 2022. Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.compmedimag.2025.102524_b18","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R., 2020. Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"10","key":"10.1016\/j.compmedimag.2025.102524_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2023.107463","article-title":"Deep learning for real-time detection of nasopharyngeal carcinoma during nasopharyngeal endoscopy","volume":"26","author":"He","year":"2023","journal-title":"Iscience"},{"issue":"1","key":"10.1016\/j.compmedimag.2025.102524_b20","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1038\/s41746-023-00811-0","article-title":"Self-supervised learning for medical image classification: a systematic review and implementation guidelines","volume":"6","author":"Huang","year":"2023","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.compmedimag.2025.102524_b21","series-title":"Proceedings of the Machine Learning Research","first-page":"1","article-title":"On the computational complexity of self-attention","volume":"vol. 201","author":"Keles","year":"2023"},{"key":"10.1016\/j.compmedimag.2025.102524_b22","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., Timofte, R., 2021. Swinir: Image restoration using swin transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1833\u20131844.","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"10.1016\/j.compmedimag.2025.102524_b23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B., 2021a. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.compmedimag.2025.102524_b24","series-title":"Vmamba: Visual state space model","author":"Liu","year":"2024"},{"issue":"1","key":"10.1016\/j.compmedimag.2025.102524_b25","first-page":"857","article-title":"Self-supervised learning: Generative or contrastive","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.compmedimag.2025.102524_b26","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.patcog.2019.02.023","article-title":"The impact of class imbalance in classification performance metrics based on the binary confusion matrix","volume":"91","author":"Luque","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.compmedimag.2025.102524_b27","series-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024"},{"issue":"11","key":"10.1016\/j.compmedimag.2025.102524_b28","first-page":"9577","article-title":"Accuracy analysis of the zero-order hold model for digital pulse width modulation","volume":"33","author":"Ma","year":"2018","journal-title":"IEEE Trans. Power Electron."},{"key":"10.1016\/j.compmedimag.2025.102524_b29","article-title":"Multi-modal understanding and generation for medical images and text via vision-language pre-training","author":"Moon","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2025.102524_b30","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.compmedimag.2025.102524_b31","series-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"10.1016\/j.compmedimag.2025.102524_b32","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.compmedimag.2025.102524_b33","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.compmedimag.2025.102524_b34","doi-asserted-by":"crossref","first-page":"114331","DOI":"10.1109\/ACCESS.2019.2935761","article-title":"Landslide detection using residual networks and the fusion of spectral and topographic information","volume":"7","author":"Sameen","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.compmedimag.2025.102524_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101693","article-title":"Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation","volume":"63","author":"Tajbakhsh","year":"2020","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2025.102524_b36","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"issue":"1","key":"10.1016\/j.compmedimag.2025.102524_b37","doi-asserted-by":"crossref","first-page":"5915","DOI":"10.1038\/s41467-021-26216-9","article-title":"Annotation-efficient deep learning for automatic medical image segmentation","volume":"12","author":"Wang","year":"2021","journal-title":"Nat. Commun."},{"issue":"1","key":"10.1016\/j.compmedimag.2025.102524_b38","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1002\/lary.30781","article-title":"The detection of nasopharyngeal carcinomas using a neural network based on nasopharyngoscopic images","volume":"134","author":"Wang","year":"2024","journal-title":"Laryngoscope"},{"key":"10.1016\/j.compmedimag.2025.102524_b39","series-title":"International Conference on Medical Imaging with Deep Learning","article-title":"Foundation model for endoscopy video analysis via large-scale self-supervised pre-training","author":"Wang","year":"2023"},{"issue":"5","key":"10.1016\/j.compmedimag.2025.102524_b40","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1002\/lary.29894","article-title":"Deep learning for nasopharyngeal carcinoma identification using both white light and narrow-band imaging endoscopy","volume":"132","author":"Xu","year":"2022","journal-title":"Laryngoscope"},{"key":"10.1016\/j.compmedimag.2025.102524_b41","series-title":"Audio mamba: Selective state spaces for self-supervised audio representations","author":"Yadav","year":"2024"},{"key":"10.1016\/j.compmedimag.2025.102524_b42","series-title":"Medmamba: Vision mamba for medical image classification","author":"Yue","year":"2024"},{"key":"10.1016\/j.compmedimag.2025.102524_b43","first-page":"1","article-title":"Automated endoscopic image classification via deep neural network with class imbalance loss","volume":"72","author":"Yue","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.compmedimag.2025.102524_b44","series-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"}],"container-title":["Computerized Medical Imaging and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611125000333?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611125000333?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T20:38:27Z","timestamp":1742675907000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0895611125000333"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":44,"alternative-id":["S0895611125000333"],"URL":"https:\/\/doi.org\/10.1016\/j.compmedimag.2025.102524","relation":{},"ISSN":["0895-6111"],"issn-type":[{"value":"0895-6111","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"NaMA-Mamba: Foundation model for generalizable nasal disease detection using masked autoencoder with Mamba on endoscopic images","name":"articletitle","label":"Article Title"},{"value":"Computerized Medical Imaging and Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compmedimag.2025.102524","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102524"}}