{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:42:47Z","timestamp":1775011367354,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819688883","type":"print"},{"value":"9789819688890","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":[[2026]]},"DOI":"10.1007\/978-981-96-8889-0_44","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T08:56:38Z","timestamp":1751273798000},"page":"519-530","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Brain Tumor MRI Interpretation: Towards a\u00a0Benchmark for\u00a0Medical Visual Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7204-183X","authenticated-orcid":false,"given":"Faheem","family":"Shehzad","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4744-3506","authenticated-orcid":false,"given":"Aniello","family":"Minutolo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7196-7994","authenticated-orcid":false,"given":"Massimo","family":"Esposito","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5256-210X","authenticated-orcid":false,"given":"Hamido","family":"Fujita","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6042-0283","authenticated-orcid":false,"given":"Hanan","family":"Aljuaid","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"44_CR1","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: VQA-Med: overview of the medical visual question answering task at ImageCLEF 2019. In: Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes (2019)"},{"key":"44_CR2","unstructured":"Ben\u00a0Abacha, A., Sarrouti, M., Demner-Fushman, D., Hasan, S.A., M\u00fcller, H.: Overview of the VQA-MED task at ImageCLEF 2021: Visual question answering and generation in the medical domain. In: Proceedings of the CLEF 2021 Conference and Labs of the Evaluation Forum-Working Notes 2021 (2021)"},{"key":"44_CR3","unstructured":"Chen, Z., Gundavarapu, DI, W.: Vision-KAN: exploring the possibility of KAN replacing MLP in vision transformer (2024)"},{"key":"44_CR4","doi-asserted-by":"publisher","first-page":"120597","DOI":"10.1016\/j.eswa.2023.120597","volume":"231","author":"M De Luca","year":"2023","unstructured":"De Luca, M., Fasolino, A.R., Ferraro, A., Moscato, V., Sperl\u00ed, G., Tramontana, P.: A community detection approach based on network representation learning for repository mining. Expert Syst. Appl. 231, 120597 (2023)","journal-title":"Expert Syst. Appl."},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association For Computational Linguistics: Human Language Technologies, Volume 1 (long and short papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"44_CR6","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint: arXiv:2010.11929 (2020)"},{"issue":"7639","key":"44_CR7","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115\u2013118 (2017)","journal-title":"Nature"},{"key":"44_CR8","doi-asserted-by":"publisher","first-page":"1210559","DOI":"10.3389\/fdata.2023.1210559","volume":"6","author":"A Ferraro","year":"2023","unstructured":"Ferraro, A., Galli, A., La Gatta, V., Postiglione, M.: Benchmarking open source and paid services for speech to text: an analysis of quality and input variety. Front. Big Data 6, 1210559 (2023)","journal-title":"Front. Big Data"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint: arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"44_CR10","doi-asserted-by":"publisher","first-page":"115643","DOI":"10.1109\/ACCESS.2021.3105278","volume":"9","author":"R Guarasci","year":"2021","unstructured":"Guarasci, R., Minutolo, A., Damiano, E., De Pietro, G., Fujita, H., Esposito, M.: Electra for neural coreference resolution in Italian. IEEE Access 9, 115643\u2013115654 (2021)","journal-title":"IEEE Access"},{"key":"44_CR11","unstructured":"Hasan, S.A., Ling, Y., Farri, O., Liu, J., M\u00fcller, H., Lungren, M.: Overview of ImageCLEF 2018 medical domain visual question answering task. In: Proceedings of CLEF 2018 Working Notes (2018)"},{"issue":"1","key":"44_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40860-024-00242-y","volume":"11","author":"A Ismail","year":"2025","unstructured":"Ismail, A., Naeem, M., Khalid, U.B., Abbas, M.: Improving adherence to medication in an intelligent environment using reinforcement learning. J. Reliable Intell. Environ. 11(1), 1\u201310 (2025)","journal-title":"J. Reliable Intell. Environ."},{"issue":"1","key":"44_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. data 5(1), 1\u201310 (2018)","journal-title":"Sci. data"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: SLAKE: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"issue":"5","key":"44_CR15","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TMI.2022.3232411","volume":"42","author":"B Liu","year":"2022","unstructured":"Liu, B., Zhan, L.M., Xu, L., Wu, X.M.: Medical visual question answering via conditional reasoning and contrastive learning. IEEE Trans. Med. Imaging 42(5), 1532\u20131545 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"44_CR16","doi-asserted-by":"publisher","first-page":"104561","DOI":"10.1016\/j.robot.2023.104561","volume":"171","author":"U Maniscalco","year":"2024","unstructured":"Maniscalco, U., Minutolo, A., Storniolo, P., Esposito, M.: Towards a more anthropomorphic interaction with robots in museum settings: an experimental study. Robot. Auton. Syst. 171, 104561 (2024)","journal-title":"Robot. Auton. Syst."},{"key":"44_CR17","doi-asserted-by":"publisher","first-page":"105004","DOI":"10.1016\/j.compbiomed.2021.105004","volume":"141","author":"A Minutolo","year":"2022","unstructured":"Minutolo, A., Damiano, E., De Pietro, G., Fujita, H., Esposito, M.: A conversational agent for querying Italian patient information leaflets and improving health literacy. Comput. Biol. Med. 141, 105004 (2022)","journal-title":"Comput. Biol. Med."},{"key":"44_CR18","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.engappai.2016.12.007","volume":"59","author":"A Minutolo","year":"2017","unstructured":"Minutolo, A., Esposito, M., De Pietro, G.: Optimization of rule-based systems in mHealth applications. Eng. Appl. Artif. Intell. 59, 103\u2013121 (2017)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"9","key":"44_CR19","doi-asserted-by":"publisher","first-page":"142","DOI":"10.3390\/technologies12090142","volume":"12","author":"H Qayyum","year":"2024","unstructured":"Qayyum, H., Rizvi, S., Naeem, M., Khalid, U.B., Abbas, M., Coronato, A.: Enhancing diagnostic accuracy for skin cancer and COVID-19 detection: a comparative study using a stacked ensemble method. Technologies 12(9), 142 (2024)","journal-title":"Technologies"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"Rahman, T., Chou, S.H., Sigal, L., Carenini, G.: An improved attention for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131662 (2021)","DOI":"10.1109\/CVPRW53098.2021.00181"},{"issue":"1","key":"44_CR21","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","volume":"1","author":"A Rajkomar","year":"2018","unstructured":"Rajkomar, A., et al.: Scalable and accurate deep learning with electronic health records. NPJ Digit. Med. 1(1), 18 (2018)","journal-title":"NPJ Digit. Med."},{"key":"44_CR22","doi-asserted-by":"publisher","first-page":"104327","DOI":"10.1016\/j.imavis.2021.104327","volume":"116","author":"H Sharma","year":"2021","unstructured":"Sharma, H., Jalal, A.S.: A survey of methods, datasets and evaluation metrics for visual question answering. Image Vis. Comput. 116, 104327 (2021)","journal-title":"Image Vis. Comput."},{"key":"44_CR23","doi-asserted-by":"crossref","unstructured":"Shehzad, F., Minutolo, A., Esposito, M.: Designing and evaluating a dual-stream transformer-based architecture for visual question answering. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3521032"},{"key":"44_CR24","unstructured":"Wu, Z., Palmer, M.: Verb semantics and lexical selection. arXiv preprint: https:\/\/arxiv.org\/abs\/cmp-lg\/9406033 (1994)"},{"key":"44_CR25","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","DOI":"10.1109\/CVPR.2016.10"}],"container-title":["Lecture Notes in Computer Science","Advances and Trends in Artificial Intelligence. Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8889-0_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T01:34:05Z","timestamp":1775007245000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8889-0_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"ISBN":["9789819688883","9789819688890"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8889-0_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"1 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"IEA\/AIE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kytakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"1 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ieaaie2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.i-somet.org\/iea-aie2025\/committees.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}