{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:10:55Z","timestamp":1788725455981,"version":"build-2803163510"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686837","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,28]]},"abstract":"<jats:p>This paper presents a dual-stream Transformer-based Visual Question Answering (VQA) framework for brain tumor MRI interpretation, paired with a custom 4,000-pair clinical question-answer dataset generated with LLM assistance and manually verified for medical plausibility. Two configurations, BERT+ViT-B\/16 and RoBERTa+BEiT, were trained under identical conditions on 1,000 MRI images (250 per class) spanning glioma, meningioma, pituitary tumor, and no-tumor categories. On an 800-pair held-out test set, BERT+ViT achieved 82.75% accuracy (WUPS 0.8281, F1 0.1007) and RoBERTa+BEiT achieved 82.38% (WUPS 0.826, F1 0.1047), both reaching 100% on binary questions and approximately 66% on open-ended questions. Error and prediction-distribution analyses show both the flawless binary scores and the persistent open-ended errors are largely artifacts of the dataset\u2019s templated answer structure, meaning much of the headline accuracy reflects dataset regularities rather than genuine visual-linguistic reasoning. We discuss this bias and propose radiologist involvement in future QA-pair design as the primary route to a less biased, more clinically meaningful benchmark.<\/jats:p>","DOI":"10.3233\/faia260764","type":"book-chapter","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:04:16Z","timestamp":1788725056000},"source":"Crossref","is-referenced-by-count":0,"title":["Templated Answers, Inflated Accuracy: Auditing Dataset Bias in Dual-Stream Transformer-Based VQA for Brain Tumor MRI"],"prefix":"10.3233","author":[{"given":"Rifah","family":"Nanziba","sequence":"first","affiliation":[{"name":"Malaysia-Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia, 54100, Kuala Lumpur, Malaysia, rnanziba28@gmail.com, hfujita@i-somet.org"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamido","family":"Fujita","sequence":"additional","affiliation":[{"name":"Malaysia-Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia, 54100, Kuala Lumpur, Malaysia, rnanziba28@gmail.com, hfujita@i-somet.org"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","New Trends in Intelligent Software Methodologies, Tools and Techniques"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA260764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T20:04:17Z","timestamp":1788725057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA260764"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"ISBN":["9781643686837"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia260764","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]}}}