{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:07:20Z","timestamp":1779347240935,"version":"3.51.4"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,8]]},"DOI":"10.1109\/isbi61048.2026.11515681","type":"proceedings-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:48:46Z","timestamp":1779306526000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["X-Plain: Vision-Language Knowledge Distillation for Interpretable Chest X-Ray Diagnosis"],"prefix":"10.1109","author":[{"given":"Supriyo","family":"Sadhya","sequence":"first","affiliation":[{"name":"School of Computing, Utah State University,Logan,Utah,84322-4205"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computing, Utah State University,Logan,Utah,84322-4205"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Blip-2: Bootstrapped language-image pretraining with frozen image encoders and large language models","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref2","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI Technical Report"},{"key":"ref3","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. International Conference on Machine Learning (ICML)","author":"Tan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fimag.2024.1373420"},{"key":"ref5","article-title":"Cxr-agent: Vision-language models for chest x-ray interpretation with uncertainty-aware radiology reporting","author":"Sharma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103224"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref10","article-title":"Radialog: A large vision-language model for radiology report generation and conversational assistance","author":"Pellegrini","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-11339-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3322425"},{"key":"ref14","article-title":"Radvlm: A multitask conversational vision-language model for radiology","author":"Deperrois","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"ref17","first-page":"209","volume-title":"Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model","volume":"158","author":"Endo","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref20","first-page":"4171","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref21","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Hu"}],"event":{"name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","location":"London, United Kingdom","start":{"date-parts":[[2026,4,8]]},"end":{"date-parts":[[2026,4,11]]}},"container-title":["2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11515282\/11515297\/11515681.pdf?arnumber=11515681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:16:25Z","timestamp":1779344185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11515681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/isbi61048.2026.11515681","relation":{},"subject":[],"published":{"date-parts":[[2026,4,8]]}}}