{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:41:29Z","timestamp":1792593689000,"version":"4.5.0"},"reference-count":0,"publisher":"Radiological Society of North America (RSNA)","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Radiology: Artificial Intelligence"],"abstract":"<jats:p>The Brain Tumor Reporting and Data System (BT-RADS) standardizes posttreatment MRI response assessment in patients with diffuse gliomas but requires complex integration of imaging trends, medication effects, and radiation timing. An end-to-end multiagent large language model and convolutional neural network system for automated BTRADS classification was developed and evaluated. Five hundred nine consecutive posttreatment glioma MRI examinations (March 2017-July 2021) from a single center were retrospectively evaluated. An extractor agent identified clinical variables from notes using gpt-oss (OpenAI, 20-billion parameters). A scorer agent applied BTRADS decision logic integrating these with quantitative volumetrics. System accuracy was compared against initial assessments, using expert annotation as the reference standard. Four hundred ninety-two examinations were evaluable. Overall system accuracy was 76.0% (374\/492) versus 57.5% (283\/492) for initial assessments, an absolute difference of +18.5 percentage points ( P &lt; .001). Cohen kappa between the system and the reference standard was 0.71. The system achieved high sensitivity in context-dependent categories (BT-1b; 100%; BT-1a, 92.7%; BT-3a, 87.5%) and moderate sensitivity for threshold-dependent categories (BT-3c, 74.8%; BT-2, 69.2%; BT-4, 69.3%; BT-3b, 57.1%). The BT-4 positive predictive value was 92.9%. These results support further evaluation of this system as a clinical decision-support tool, with local open-weight inference preserving data privacy.<\/jats:p>\n                  <jats:p>\u00a9RSNA, 2026<\/jats:p>","DOI":"10.1148\/ryai.260234","type":"journal-article","created":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:04:41Z","timestamp":1792591481000},"source":"Crossref","is-referenced-by-count":0,"title":["Agentic Automation of BT-RADS Scoring Using an End-to-End System for                     Standardized Glioma Follow-up Assessment"],"prefix":"10.1148","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2891-8633","authenticated-orcid":false,"given":"Mohamed Sobhi","family":"Jabal","sequence":"first","affiliation":[{"name":"Department of Radiology, Duke University Medical Center,                     2301 Erwin Rd, Box 3808, Durham, NC 27710"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2247-0639","authenticated-orcid":false,"given":"Jikai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke                     University, Durham, NC"},{"name":"Duke Center for Artificial Intelligence in Radiology,                     Duke University Medical Center, Durham, NC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1713-9538","authenticated-orcid":false,"given":"Dominic","family":"LaBella","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Duke University Medical                     Center, Durham, NC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessica L.","family":"Houk","sequence":"additional","affiliation":[{"name":"Department of Radiology, Duke University Medical Center,                     2301 Erwin Rd, Box 3808, Durham, NC 27710"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-2329","authenticated-orcid":false,"given":"Dylan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Duke University Medical Center,                     2301 Erwin Rd, Box 3808, Durham, NC 27710"},{"name":"Department of Radiology, Santa Clara Valley Medical                     Center, San Jose, Calif"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8609-8421","authenticated-orcid":false,"given":"Jeffrey D.","family":"Rudie","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of California San                     Diego, San Diego, Calif"},{"name":"Department of Radiology, Scripps Clinic Medical Group,                     San Diego, Calif"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4202-8602","authenticated-orcid":false,"given":"Maciej A.","family":"Mazurowski","sequence":"additional","affiliation":[{"name":"Department of Radiology, Duke University Medical Center,                     2301 Erwin Rd, Box 3808, Durham, NC 27710"},{"name":"Department of Electrical and Computer Engineering, Duke                     University, Durham, NC"},{"name":"Department of Biostatistics and Bioinformatics, Duke                     University School of Medicine, Durham, NC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7037-433X","authenticated-orcid":false,"given":"Kirti","family":"Magudia","sequence":"additional","affiliation":[{"name":"Department of Radiology, Duke University Medical Center,                     2301 Erwin Rd, Box 3808, Durham, NC 27710"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1464-0354","authenticated-orcid":false,"given":"Evan","family":"Calabrese","sequence":"additional","affiliation":[{"name":"Department of Radiology, Duke University Medical Center,                     2301 Erwin Rd, Box 3808, Durham, NC 27710"},{"name":"Duke Center for Artificial Intelligence in Radiology,                     Duke University Medical Center, Durham, NC"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1577","published-online":{"date-parts":[[2026,10,21]]},"container-title":["Radiology: Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/pubs.rsna.org\/doi\/pdf\/10.1148\/ryai.260234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:04:42Z","timestamp":1792591482000},"score":1,"resource":{"primary":{"URL":"http:\/\/pubs.rsna.org\/doi\/10.1148\/ryai.260234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,21]]},"references-count":0,"alternative-id":["10.1148\/ryai.260234"],"URL":"https:\/\/doi.org\/10.1148\/ryai.260234","relation":{},"ISSN":["2638-6100"],"issn-type":[{"value":"2638-6100","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,21]]},"article-number":"e260234"}}