{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:35:18Z","timestamp":1774431318374,"version":"3.50.1"},"reference-count":30,"publisher":"Ovid Technologies (Wolters Kluwer Health)","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Whole-body MRI is increasingly used for preventive health screening; however, the prevalence and distribution of incidental oncologically relevant findings in asymptomatic individuals remain incompletely characterized. The primary objective of this multicentre study was to describe the frequency and anatomical distribution of clinically relevant findings detected by whole-body MRI in an asymptomatic adult population. As a secondary objective, we evaluated the feasibility of using a large language model (LLM) for retrospective extraction and structuring of radiology report data for research purposes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Radiology reports from 327 asymptomatic adults who underwent MRI as part of a preventive screening program were retrospectively collected from four diagnostic centers. All MRI examinations were interpreted by subspecialist radiologists (neuroradiology, body imaging, and musculoskeletal imaging), and clinical findings were classified using the Oncologically Relevant Findings Reporting and Data System (ONCO-RADS). A senior radiologist analyzed the reports to extract only findings with ONCO-RADS values \u22653, creating a reference standard. In addition, an LLM (DeepSeek-R1-Llama3.3, Hangzhou DeepSeek Artificial Intelligence Basic Technology Research Co., Ltd., Hangzhou, Zhejiang, China) was subsequently applied to automatically extract all findings from free-text reports with associated ONCO-RADS categories (including also ONCO-RADS 1 and 2) and anatomical locations. LLM outputs were compared with the radiologist-defined ONCO-RADS to assess the performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the 327 individuals (213 males, 114 females; median age 52 years), a total of 237 findings (5%) classified as ONCO-RADS\u2005\u2265\u20053 were extracted by the radiologist, affecting 138 individuals (42.2%). The majority of ONCO-RADS\u2005\u2265\u20053 findings were ONCO-RADS 3 (232, 97.9%). Three findings (1.3%) were ONCO-RADS 4, and two (0.8%) were ONCO-RADS 5. Three malignant lesions were confirmed (prostate cancer, renal cell carcinoma, and appendiceal carcinoma), corresponding to a cancer prevalence of 0.9% in the screened population. Regarding the performance of the LLM in extracting and structuring radiologist-reported findings, 207 (87.3%) ONCO-RADS were correctly extracted, 17 (7.2%) were missed, and 13 (5.5%) were incorrectly localized.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Whole-body MRI detected a small number of confirmed occult malignancies and a higher prevalence of oncologically relevant findings (ONCO-RADS\u2005\u2265\u20053). Regarding the LLM, results showed that it can support efficient and standardized retrospective extraction of structured information from heterogeneous radiology reports.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/cej.0000000000001015","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T07:00:36Z","timestamp":1774422036000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Whole-body magnetic resonance imaging for cancer screening in asymptomatic adults: a multicenter study"],"prefix":"10.1097","author":[{"given":"Marco","family":"Ali","sequence":"first","affiliation":[{"name":"Department of Research, Innovation and Development, CDI Centro Diagnostico Italiano S.p.A."},{"name":"Bracco Research Centre, Bracco Imaging S.p.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Di Palma","sequence":"additional","affiliation":[{"name":"Department of Research, Innovation and Development, CDI Centro Diagnostico Italiano S.p.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gennaro","family":"D\u2019Anna","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging and Stereotactic Radiosurgery, CDI Centro Diagnostico Italiano S.p.A., Milan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatemeh","family":"Darvizeh","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging and Stereotactic Radiosurgery, CDI Centro Diagnostico Italiano S.p.A., Milan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfredo","family":"Goddi","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, SME Centro Medico, Varese, VA, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saman","family":"Fouladi","sequence":"additional","affiliation":[{"name":"Department of Research, Innovation and Development, CDI Centro Diagnostico Italiano S.p.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deborah","family":"Fazzini","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging and Stereotactic Radiosurgery, CDI Centro Diagnostico Italiano S.p.A., Milan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"276","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"R1-20260325","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1016\/j.jacr.2010.06.013","article-title":"Managing incidental findings on abdominal CT: white paper of the ACR incidental findings committee.","volume":"7","author":"Berland","year":"2010","journal-title":"J Am Coll Radiol"},{"key":"R2-20260325","doi-asserted-by":"crossref","first-page":"2589","DOI":"10.1007\/s00330-024-11107-6","article-title":"Large language models for structured reporting in radiology: past, present, and future.","volume":"35","author":"Busch","year":"2025","journal-title":"Eur Radiol"},{"key":"R3-20260325","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1186\/s12911-021-01533-7","article-title":"A systematic review of natural language processing applied to radiology reports.","volume":"21","author":"Casey","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"R4-20260325","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1056\/NEJMp1702071","article-title":"Machine learning and prediction in medicine \u2013 beyond the peak of inflated expectations.","volume":"376","author":"Chen","year":"2017","journal-title":"N Engl J Med"},{"key":"R5-20260325","doi-asserted-by":"crossref","first-page":"4611","DOI":"10.1038\/s41596-021-00588-0","article-title":"Generic acquisition protocol for quantitative MRI of the spinal cord.","volume":"16","author":"Cohen-Adad","year":"2021","journal-title":"Nat Protocols"},{"key":"R6-20260325","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1007\/s00330-024-10983-2","article-title":"Baseline surveillance in Li Fraumeni syndrome using whole-body MRI: a systematic review and updated meta-analysis.","volume":"35","author":"Dacoregio","year":"2025","journal-title":"Eur Radiol"},{"key":"R7-20260325","doi-asserted-by":"crossref","first-page":"1770","DOI":"10.3390\/diagnostics11101770","article-title":"Whole-body MRI in rheumatology: major advances and future perspectives.","volume":"11","author":"Deplano","year":"2021","journal-title":"Diagnostics (Basel)"},{"key":"R8-20260325","doi-asserted-by":"crossref","first-page":"69","DOI":"10.3390\/tomography11060069","article-title":"Structured transformation of unstructured prostate MRI reports using large language models.","volume":"11","author":"Di Palma","year":"2025","journal-title":"Tomography"},{"key":"R9-20260325","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/S1064-9689(21)00019-2","article-title":"WHOLE-BODY MR IMAGING: practical issues, clinical applications, and future directions.","volume":"7","author":"Eustace","year":"1999","journal-title":"Magn Reson Imaging Clin N Am"},{"key":"R10-20260325","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1111\/jon.12673","article-title":"Standardized brain MRI acquisition protocols improve statistical power in multicenter quantitative morphometry studies.","volume":"30","author":"George","year":"2020","journal-title":"J Neuroimaging"},{"key":"R11-20260325","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning.","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"R12-20260325","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1007\/s00330-012-2636-6","article-title":"Potentially relevant incidental findings on research whole-body MRI in the general adult population: frequencies and management.","volume":"23","author":"Hegenscheid","year":"2013","journal-title":"Eur Radiol"},{"key":"R13-20260325","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s40644-024-00665-z","article-title":"Applying ONCO-RADS to whole-body MRI cancer screening in a retrospective cohort of asymptomatic individuals.","volume":"24","author":"Hu","year":"2024","journal-title":"Cancer Imaging"},{"key":"R14-20260325","doi-asserted-by":"crossref","DOI":"10.1007\/s00330-025-11880-y","article-title":"Optimizing whole-body MRI for early cancer detection in Li-Fraumeni syndrome: a prospective bicentric study.","author":"Keymling","year":"2025","journal-title":"Eur Radiol"},{"key":"R15-20260325","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1002\/jmri.26736","article-title":"Whole-body MRI for preventive health screening: a systematic review of the literature.","volume":"50","author":"Kwee","year":"2019","journal-title":"J Magn Reson Imaging"},{"key":"R16-20260325","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.1016\/j.jacr.2022.06.016","article-title":"Natural language processing in radiology: update on clinical applications.","volume":"19","author":"L\u00f3pez-\u00dabeda","year":"2022","journal-title":"J Am Coll Radiol"},{"key":"R17-20260325","doi-asserted-by":"crossref","first-page":"e2500264","DOI":"10.1200\/PO-25-00264","article-title":"Prospective study of annual whole-body magnetic resonance imaging as part of a multimodality screening program for individuals with li-fraumeni syndrome.","volume":"9","author":"Maoz","year":"2025","journal-title":"JCO Precision Oncology"},{"key":"R18-20260325","doi-asserted-by":"crossref","first-page":"1813","DOI":"10.1007\/s00330-025-11976-5","article-title":"Whole-body MRI for opportunistic cancer detection in asymptomatic individuals: a systematic review and meta-analysis.","volume":"36","author":"Martins da Fonseca","year":"2025","journal-title":"Eur Radiol"},{"key":"R19-20260325","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1093\/bib\/bbx044","article-title":"Deep learning for healthcare: review, opportunities and challenges.","volume":"19","author":"Miotto","year":"2018","journal-title":"Brief Bioinform"},{"key":"R20-20260325","doi-asserted-by":"crossref","first-page":"110239","DOI":"10.1016\/j.ejrad.2022.110239","article-title":"Whole-body MRI for preventive health screening in a general population: Prevalence of incidental findings around the hip.","volume":"150","author":"Na Kim","year":"2022","journal-title":"Eur J Radiol"},{"key":"R21-20260325","doi-asserted-by":"crossref","first-page":"2837","DOI":"10.1007\/s00330-021-08327-5","article-title":"Structured reporting in radiology: a systematic review to explore its potential.","volume":"32","author":"Nobel","year":"2022","journal-title":"Eur Radiol"},{"key":"R22-20260325","doi-asserted-by":"crossref","first-page":"4228","DOI":"10.1007\/s00330-023-09526-y","article-title":"Transformer-based structuring of free-text radiology report databases.","volume":"33","author":"Nowak","year":"2023","journal-title":"Eur Radiol"},{"key":"R23-20260325","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1148\/radiol.2021201740","article-title":"Oncologically Relevant Findings Reporting and Data System (ONCO-RADS): guidelines for the acquisition, interpretation, and reporting of whole-body mri for cancer screening.","volume":"299","author":"Petralia","year":"2021","journal-title":"Radiology"},{"key":"R24-20260325","doi-asserted-by":"crossref","first-page":"1434","DOI":"10.1007\/s11547-021-01392-2","article-title":"Whole-body magnetic resonance imaging (WB-MRI) for cancer screening: recommendations for use.","volume":"126","author":"Petralia","year":"2021","journal-title":"La Radiologia Medica"},{"key":"R25-20260325","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1148\/radiol.16142770","article-title":"Natural language processing in radiology: a systematic review.","volume":"279","author":"Pons","year":"2016","journal-title":"Radiology"},{"key":"R26-20260325","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1038\/s41746-024-01219-0","article-title":"A scoping review of large language model based approaches for information extraction from radiology reports.","volume":"7","author":"Reichenpfader","year":"2024","journal-title":"npj Digital Med"},{"key":"R27-20260325","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1007\/s10654-020-00679-4","article-title":"The effects of incidental findings from whole-body MRI on the frequency of biopsies and detected malignancies or benign conditions in a general population cohort study.","volume":"35","author":"Richter","year":"2020","journal-title":"Eur J Epidemiol"},{"key":"R28-20260325","first-page":"205","article-title":"Opportunities and challenges of large language models in medical imaging.","volume":"12","author":"Tarighatnia","year":"2025","journal-title":"Front Biomed Technol"},{"key":"R29-20260325","doi-asserted-by":"crossref","first-page":"407","DOI":"10.12659\/PJR.897570","article-title":"Whole-body MRI screening in asymptomatic subjects; preliminary experience and long-term follow-up findings.","volume":"81","author":"Ulus","year":"2016","journal-title":"Pol J Radiol"},{"key":"R30-20260325","doi-asserted-by":"crossref","first-page":"e24381","DOI":"10.2196\/24381","article-title":"Automating stroke data extraction from free-text radiology reports using natural language processing: instrument validation study.","volume":"9","author":"Yu","year":"2021","journal-title":"JMIR Med Inform"}],"container-title":["European Journal of Cancer Prevention"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/CEJ.0000000000001015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T07:00:43Z","timestamp":1774422043000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/CEJ.0000000000001015"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1097\/cej.0000000000001015","relation":{},"ISSN":["0959-8278","1473-5709"],"issn-type":[{"value":"0959-8278","type":"print"},{"value":"1473-5709","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]},"assertion":[{"value":"2025-11-19","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-25","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}