{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T13:45:33Z","timestamp":1792158333348,"version":"4.4.0"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers in Biology and Medicine"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.compbiomed.2026.111980","type":"journal-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T07:21:38Z","timestamp":1791789698000},"page":"111980","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multimodal visual question answering in neuro-oncology and gastroenterology: A domain-specific feasibility study"],"prefix":"10.1016","volume":"216","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7204-183X","authenticated-orcid":false,"given":"Faheem","family":"Shehzad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0419-7181","authenticated-orcid":false,"given":"Ciro","family":"Mennella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5256-210X","authenticated-orcid":false,"given":"Hamido","family":"Fujita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7196-7994","authenticated-orcid":false,"given":"Massimo","family":"Esposito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4744-3506","authenticated-orcid":false,"given":"Aniello","family":"Minutolo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compbiomed.2026.111980_bib0005","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40860-024-00242-y","article-title":"Improving adherence to medication in an intelligent environment using reinforcement learning","volume":"11","author":"Ismail","year":"2025","journal-title":"J. Reliab. Intell. Environ."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0015","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0020","doi-asserted-by":"crossref","first-page":"142","DOI":"10.3390\/technologies12090142","article-title":"Enhancing diagnostic accuracy for skin cancer and COVID-19 detection: a comparative study using a stacked ensemble method","volume":"12","author":"Qayyum","year":"2024","journal-title":"Technologies"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0025","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.engappai.2016.12.007","article-title":"Optimization of rule-based systems in mHealth applications","volume":"59","author":"Minutolo","year":"2017","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120597","article-title":"A community detection approach based on network representation learning for repository mining","volume":"231","author":"De Luca","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0035","doi-asserted-by":"crossref","DOI":"10.3389\/fdata.2023.1210559","article-title":"Benchmarking open source and paid services for speech to text: an analysis of quality and input variety","volume":"6","author":"Ferraro","year":"2023","journal-title":"Front. Big Data"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0040","author":"de Faria"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0045","series-title":"European Conference on Computer Vision","first-page":"104","article-title":"Uniter: universal image-text representation learning","author":"Chen","year":"2020"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0050","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"Vilt: vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102611","article-title":"Medical visual question answering: a survey","volume":"143","author":"Lin","year":"2023","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0060","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.patrec.2021.07.002","article-title":"Visual question answering in the medical domain based on deep learning approaches: a comprehensive study","volume":"150","author":"Al-Sadi","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0065","doi-asserted-by":"crossref","first-page":"2983","DOI":"10.3390\/app15062983","article-title":"Generative models in medical visual question answering: a survey","volume":"15","author":"Dong","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0070","author":"Gautam"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2025.110195","article-title":"A global visual information intervention model for medical visual question answering","volume":"192","author":"Peng","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0080","series-title":"Proceedings of CLEF 2018 Working Notes","article-title":"Overview of imageclef 2018 medical domain visual question answering task","author":"Hasan","year":"2018"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0085","series-title":"Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes, (9-12 September 2019)","article-title":"VQA-med: overview of the medical visual question answering task at imageclef 2019","author":"Ben Abacha","year":"2019"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0090","series-title":"Proceedings of the CLEF 2021 Conference and Labs of the Evaluation Forum-Working Notes, (21-24 September 2021)","article-title":"Overview of the VQA-med task at imageclef 2021: visual question answering and generation in the medical domain","author":"Ben Abacha","year":"2021"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0095","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.251","article-title":"A dataset of clinically generated visual questions and answers about radiology images","volume":"5","author":"Lau","year":"2018","journal-title":"Sci. Data"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0100","series-title":"021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","first-page":"1650","article-title":"Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering","author":"Liu","year":"2021"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0105","doi-asserted-by":"crossref","first-page":"195561","DOI":"10.1109\/ACCESS.2024.3521032","article-title":"Designing and evaluating a dual-stream transformer-based architecture for visual question answering","volume":"12","author":"Shehzad","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0110","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/s44163-026-01011-x","article-title":"Efficient multimodal learning using BERT and vision transformers for visual question answering on peripheral blood cells","volume":"6","author":"Shehzad","year":"2026","journal-title":"Discov. Artif. Intell."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0115","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0120","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0125","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-33128-3_1","article-title":"Deep learning in medical image analysis","author":"Chan","year":"2020","journal-title":"Deep learn. med. image anal. chall. appl."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0130","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"522","article-title":"Overcoming data limitation in medical visual question answering","author":"Nguyen","year":"2019"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0135","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"386","article-title":"Consistency-preserving visual question answering in medical imaging","author":"Tascon-Morales","year":"2022"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0140","author":"Johnson"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101857","article-title":"Machine-learning-based multiple abnormality prediction with large-scale chest computed tomography volumes","volume":"67","author":"Draelos","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0150","author":"Alsentzer"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0155","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Making the most of text semantics to improve biomedical vision\u2013language processing","author":"Boecking","year":"2022"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0160","doi-asserted-by":"crossref","first-page":"e588","DOI":"10.1002\/itl2.588","article-title":"Optimizing medical visual question answering: evaluating the impact of enhanced images, augmented training data, and model selection","volume":"8","author":"Almalki","year":"2025","journal-title":"Internet Technol. Lett."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0165","author":"Guo"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0170","doi-asserted-by":"crossref","first-page":"4605","DOI":"10.1109\/TMI.2025.3580561","article-title":"Bridging the semantic gap in medical visual question answering with prompt learning","volume":"44","author":"Lu","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0175","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41019-024-00255-w","article-title":"Effective medical visual question answering using dynamic prompting and decoding knowledge editing: Z. zhou et al","author":"Zhou","year":"2025","journal-title":"Data Sci. Eng."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0180","series-title":"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)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0185","author":"Dosovitskiy"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0190","article-title":"Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0195","first-page":"9694","article-title":"Align before fuse: vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0200","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9268","article-title":"Class-balanced loss based on effective number of samples","author":"Cui","year":"2019"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0205","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2021.104327","article-title":"A survey of methods, datasets and evaluation metrics for visual question answering","volume":"116","author":"Sharma","year":"2021","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0210","author":"Wu"},{"key":"10.1016\/j.compbiomed.2026.111980_bib0215","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume":"27","author":"Malinowski","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0220","doi-asserted-by":"crossref","first-page":"16","DOI":"10.3390\/mti10020016","article-title":"Systematic analysis of vision\u2013language models for medical visual question answering","volume":"10","author":"Shah","year":"2026","journal-title":"Multimodal Technol. Interact."},{"key":"10.1016\/j.compbiomed.2026.111980_bib0225","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.105004","article-title":"A conversational agent for querying Italian patient information leaflets and improving health literacy","volume":"141","author":"Minutolo","year":"2022","journal-title":"Comput. Biol. Med."}],"container-title":["Computers in Biology and Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482526005469?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482526005469?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T12:50:44Z","timestamp":1792155044000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0010482526005469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":45,"alternative-id":["S0010482526005469"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiomed.2026.111980","relation":{},"ISSN":["0010-4825"],"issn-type":[{"value":"0010-4825","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal visual question answering in neuro-oncology and gastroenterology: A domain-specific feasibility study","name":"articletitle","label":"Article Title"},{"value":"Computers in Biology and Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiomed.2026.111980","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"111980"}}