{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:12:55Z","timestamp":1784736775429,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500192","type":"print"},{"value":"9789819500208","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-95-0020-8_37","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T09:18:00Z","timestamp":1753262280000},"page":"435-445","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MedLite: A Lightweight Medical Multimodal Model Based on Knowledge Distillation and Inference Optimization"],"prefix":"10.1007","author":[{"given":"Jinwei","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaokang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weibin","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gengshen","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"37_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108709","volume":"178","author":"R Guo","year":"2024","unstructured":"Guo, R., et al.: A survey on advancements in image-text multimodal models: from general techniques to biomedical implementations. Comput. Biol. Med. 178, 108709 (2024). https:\/\/doi.org\/10.1016\/j.compbiomed.2024.108709","journal-title":"Comput. Biol. Med."},{"key":"37_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102861","volume":"151","author":"P Esmaeilzadeh","year":"2024","unstructured":"Esmaeilzadeh, P.: Challenges and strategies for wide-scale artificial intelligence (AI) deployment in healthcare practices: a perspective for healthcare organizations. Artif. Intell. Med. 151, 102861 (2024)","journal-title":"Artif. Intell. Med."},{"key":"37_CR3","unstructured":"Bai, F., Du, Y., Huang, T., Meng, M.Q.-H., Zhao, B.: M3d: advancing 3d medical image analysis with multi-modal large language models. ArXiv Prepr. ArXiv240400578. (2024)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: A multimodal biomedical foundation model trained from fifteen million image\u2013text pairs. NEJM AI. 2, AIoa2400640 (2025)","DOI":"10.1056\/AIoa2400640"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: Medclip: contrastive learning from unpaired medical images and text. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing, p. 3876 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"37_CR6","unstructured":"Zhang, S., et al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. ArXiv Prepr. ArXiv230300915. (2023)"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Jensen, M., Yeung-Levy, S., Lungren, M.P., Poon, H., Chaudhari, A.S.: Multimodal Foundation Models for Medical Imaging-A Systematic Review and Implementation Guidelines. medRxiv. 2024\u201310 (2024)","DOI":"10.1101\/2024.10.23.24316003"},{"key":"37_CR8","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. ArXiv Prepr. ArXiv211002178 (2021)"},{"key":"37_CR9","unstructured":"Jeong, J., et al.: Multimodal image-text matching improves retrieval-based chest x-ray report generation. In: Medical Imaging with Deep Learning, pp. 978\u2013990. PMLR (2024)"},{"key":"37_CR10","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. ArXiv Prepr. ArXiv150302531 (2015)"},{"key":"37_CR11","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"37_CR13","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv Prepr. ArXiv191001108 (2019)"},{"key":"37_CR14","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, (2017)"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"R\u00fcckert, J., et al.: Rocov2: radiology objects in context version 2, an updated multimodal image dataset. Sci. Data. 11, 688 (2024)","DOI":"10.1038\/s41597-024-03496-6"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Clip-event: connecting text and images with event structures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16420\u201316429 (2022)","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"37_CR17","unstructured":"Shen, S., et al.: How much can clip benefit vision-and-language tasks? ArXiv Prepr. ArXiv210706383. (2021)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Cao, W., et al.: Bootstrapping chest ct image understanding by distilling knowledge from x-ray expert models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11238\u201311247 (2024)","DOI":"10.1109\/CVPR52733.2024.01068"},{"key":"37_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101817","volume":"97","author":"D Xu","year":"2023","unstructured":"Xu, D., et al.: Vision-knowledge fusion model for multi-domain medical report generation. Inf. Fusion. 97, 101817 (2023)","journal-title":"Inf. Fusion."},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and pattern Recognition, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"37_CR21","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"37_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. ArXiv Prepr. ArXiv171105101 (2017)"},{"key":"37_CR23","unstructured":"Paszke, A.: Pytorch: An imperative style, high-performance deep learning library. ArXiv Prepr. ArXiv191201703 (2019)"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Irvin, J.,et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"37_CR26","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: Hints for thin deep nets. ArXiv Prepr. ArXiv14126550. (2014)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0020-8_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:52:54Z","timestamp":1784044374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0020-8_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500192","9789819500208"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0020-8_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}