{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:26:54Z","timestamp":1776184014491,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819626403","type":"print"},{"value":"9789819626410","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\/978-981-96-2641-0_20","type":"book-chapter","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:57:06Z","timestamp":1743382626000},"page":"293-307","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DermAI: A Chatbot Assistant for\u00a0Skin Lesion Diagnosis Using Vision and\u00a0Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8537-1331","authenticated-orcid":false,"given":"Viet-Tham","family":"Huynh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7729-2927","authenticated-orcid":false,"given":"Trong-Thuan","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0109-1114","authenticated-orcid":false,"given":"Thao Thi-Phuong","family":"Dao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0236-7992","authenticated-orcid":false,"given":"Tam V.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Abraham, N., Khan, N.M.: A novel focal Tversky loss function with improved attention U-Net for lesion segmentation. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 683\u2013687. IEEE (2019)","DOI":"10.1109\/ISBI.2019.8759329"},{"key":"20_CR2","unstructured":"Alexey, D.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929 (2020)"},{"key":"20_CR3","unstructured":"Asadi-Aghbolaghi, M., Azad, R., Fathy, M., Escalera, S.: Multi-level context gating of embedded collective knowledge for medical image segmentation. arXiv preprint arXiv:2003.05056 (2020)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Azad, R., Asadi-Aghbolaghi, M., Fathy, M., Escalera, S.: Bi-directional ConvLSTM U-Net with densley connected convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp.\u00a00\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00052"},{"key":"20_CR5","doi-asserted-by":"crossref","first-page":"133365","DOI":"10.1109\/ACCESS.2021.3116265","volume":"9","author":"M Ben\u010devi\u0107","year":"2021","unstructured":"Ben\u010devi\u0107, M., Gali\u0107, I., Habijan, M., Babin, D.: Training on polar image transformations improves biomedical image segmentation. IEEE access 9, 133365\u2013133375 (2021)","journal-title":"IEEE access"},{"key":"20_CR6","doi-asserted-by":"publisher","unstructured":"Bozorgpour, A., Sadegheih, Y., Kazerouni, A., Azad, R., Merhof, D.: DermoSegDiff: a boundary-aware segmentation diffusion model for skin lesion delineation. In: International Workshop on PRedictive Intelligence In MEdicine, pp. 146\u2013158. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-46005-0_13","DOI":"10.1007\/978-3-031-46005-0_13"},{"key":"20_CR7","unstructured":"Chen, J., et al.: TransUet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Codella, N.C., et\u00a0al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 168\u2013172. IEEE (2018)","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"20_CR9","first-page":"18157","volume":"35","author":"R Daneshjou","year":"2022","unstructured":"Daneshjou, R., Yuksekgonul, M., Cai, Z.R., Novoa, R., Zou, J.Y.: SkinCon: a skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis. Adv. Neural. Inf. Process. Syst. 35, 18157\u201318167 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR10","unstructured":"Gutman, D., et al.: Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1605.01397 (2016)"},{"key":"20_CR11","unstructured":"Han, T., et al.: MedAlpaca\u2013An open-source collection of medical conversational AI models and training data. arXiv preprint arXiv:2304.08247 (2023)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Jha, D., Riegler, M.A., Johansen, D., Halvorsen, P., Johansen, H.D.: DoubleU-Net: a deep convolutional neural network for medical image segmentation. In: 2020 IEEE 33rd International Symposium on Computer-based Medical Systems (CBMS), pp. 558\u2013564. IEEE (2020)","DOI":"10.1109\/CBMS49503.2020.00111"},{"issue":"1","key":"20_CR13","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1007\/s12325-019-01130-1","volume":"37","author":"OT Jones","year":"2020","unstructured":"Jones, O.T., Ranmuthu, C.K., Hall, P.N., Funston, G., Walter, F.M.: Recognising skin cancer in primary care. Adv. Ther. 37(1), 603\u2013616 (2020)","journal-title":"Adv. Ther."},{"key":"20_CR14","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Z., Zhang, K., Dan, R., Jiang, S., Zhang, Y.: ChatDoctor: a medical chat model fine-tuned on a large language model meta-AI (LLAMA) using medical domain knowledge. Cureus 15(6), e40895 (2023)","DOI":"10.7759\/cureus.40895"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, T.T., Nguyen, T.V., Tran, M.T.: Collaborative consultation doctors model: unifying CNN and VIT for Covid-19 diagnostic. IEEE Access 11, 95346\u201395357 (2023)","DOI":"10.1109\/ACCESS.2023.3307014"},{"key":"20_CR17","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"20_CR18","unstructured":"Peng, B., Li, C., He, P., Galley, M., Gao, J.: Instruction tuning with GPT-4. arXiv preprint arXiv:2304.03277 (2023)"},{"key":"20_CR19","unstructured":"Perera, S., Erzurumlu, Y., Gulati, D., Yilmaz, A.: MobileUNETR: a lightweight end-to-end hybrid vision transformer for efficient medical image segmentation. arXiv preprint arXiv:2409.03062 (2024)"},{"issue":"12","key":"20_CR20","doi-asserted-by":"crossref","first-page":"323","DOI":"10.3390\/jimaging8120323","volume":"8","author":"KA Phung","year":"2022","unstructured":"Phung, K.A., Nguyen, T.T., Wangad, N., Baraheem, S., Vo, N.D., Nguyen, K.: Disease recognition in x-ray images with doctor consultation-inspired model. J. Imaging 8(12), 323 (2022)","journal-title":"J. Imaging"},{"key":"20_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Soenksen, L.R., et\u00a0al.: Using deep learning for dermatologist-level detection of suspicious pigmented skin lesions from wide-field images. Sci. Transl. Med. 13(581), eabb3652 (2021)","DOI":"10.1126\/scitranslmed.abb3652"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Srivastav, S., et al.: ChatGPT in radiology: the advantages and limitations of artificial intelligence for medical imaging diagnosis. Cureus 15(7), e41435 (2023)","DOI":"10.7759\/cureus.41435"},{"issue":"5","key":"20_CR24","doi-asserted-by":"crossref","first-page":"2252","DOI":"10.1109\/JBHI.2021.3138024","volume":"26","author":"A Srivastava","year":"2021","unstructured":"Srivastava, A., et al.: MSRF-NET: a multi-scale residual fusion network for biomedical image segmentation. IEEE J. Biomed. Health Inform. 26(5), 2252\u20132263 (2021)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"20_CR25","doi-asserted-by":"publisher","unstructured":"Tang, F., et al.: DUAT: dual-aggregation transformer network for medical image segmentation. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 343\u2013356. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-8469-5_27","DOI":"10.1007\/978-981-99-8469-5_27"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Thawkar, O., et al.: XrayGPT: chest radiographs summarization using medical vision-language models. arXiv preprint arXiv:2306.07971 (2023)","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"20_CR27","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"20_CR28","unstructured":"Tu, T., et\u00a0al.: Towards conversational diagnostic AI. arXiv preprint arXiv:2401.05654 (2024)"},{"key":"20_CR29","unstructured":"Vorndran, M.R., Roeck, B.F.: Inconsistency masks: removing the uncertainty from input-pseudo-label pairs. arXiv preprint arXiv:2401.14387 (2024)"},{"key":"20_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-030-87193-2_20","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"J Wang","year":"2021","unstructured":"Wang, J., Wei, L., Wang, L., Zhou, Q., Zhu, L., Qin, J.: Boundary-aware transformers for skin lesion segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 206\u2013216. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_20"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedClip: contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"20_CR32","unstructured":"Wolleb, J., Sandk\u00fchler, R., Bieder, F., Valmaggia, P., Cattin, P.C.: Diffusion models for implicit image segmentation ensembles. In: Konukoglu, E., Menze, B., Venkataraman, A., Baumgartner, C., Dou, Q., Albarqouni, S. (eds.) Proceedings of The 5th International Conference on Medical Imaging with Deep Learning. Proceedings of Machine Learning Research, vol.\u00a0172, pp. 1336\u20131348. PMLR 2022). https:\/\/proceedings.mlr.press\/v172\/wolleb22a.html"},{"key":"20_CR33","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: PMC-LLaMA: further finetuning llama on medical papers. arXiv preprint arXiv:2304.14454 (2023)"},{"key":"20_CR34","unstructured":"Wu, J., et al.: MedSegDiff: Medical image segmentation with diffusion probabilistic model. In: Medical Imaging with Deep Learning, pp. 1623\u20131639. PMLR (2024)"},{"key":"20_CR35","unstructured":"Xiong, H., et al.: DoctorGLM: fine-tuning your chinese doctor is not a herculean task. arXiv preprint arXiv:2304.01097 (2023)"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhang, J., Xu, Y., Tao, D.: Vision transformer with quadrangle attention. IEEE Trans. Pattern Anal. Mach. Intell. 46, 3608\u20133624 (2024)","DOI":"10.1109\/TPAMI.2023.3347693"},{"issue":"1","key":"20_CR37","doi-asserted-by":"crossref","first-page":"5649","DOI":"10.1038\/s41467-024-50043-3","volume":"15","author":"J Zhou","year":"2024","unstructured":"Zhou, J., et al.: Pre-trained multimodal large language model enhances dermatological diagnosis using SkinGPT-4. Nat. Commun. 15(1), 5649 (2024)","journal-title":"Nat. Commun."},{"key":"20_CR38","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=1tZbq88f27"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2641-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:57:43Z","timestamp":1743382663000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2641-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819626403","9789819626410"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2641-0_20","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":"29 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}