{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T12:26:55Z","timestamp":1786969615559,"version":"build-2736575974"},"reference-count":29,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"am","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100022131","name":"NBCF","doi-asserted-by":"publisher","award":["IF-12-20"],"award-info":[{"award-number":["IF-12-20"]}],"id":[{"id":"10.13039\/100022131","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BREAST project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Breast cancer screening with mammography reduces mortality, but interpretation errors persist. While artificial intelligence (AI) shows promise, most studies focus on case-level accuracy and overlook lesion-level performance. This study evaluated the AI (GMIC\u2009+\u2009CLAHE) model against radiologists and radiology trainees, considering breast density and lesion characteristics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Nine BREAST test sets of screening digital mammograms (540 cases: 179 cancer, 361 normal) were analyzed. AI performance was compared with 17 radiologists and 26 trainees. Case- and lesion-level performance were assessed across breast density, lesion type, and size. AI malignancy scores were dichotomized using Youden\u2019s index. Sensitivity, specificity, ROC AUC, lesion localization, and odds ratios (ORs) were calculated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>AI achieved higher case-level AUC (0.974) than radiologists (0.82\u2009\u00b1\u20090.06; P\u2009=\u2009.01) and trainees (0.74\u2009\u00b1\u20090.05; P\u2009&amp;lt;\u2009.0001) across breast densities. At lesion level, AI matched radiologists and outperformed trainees (OR = 1.6; P\u2009=\u2009.03), with lesion sensitivities of 66.3% (AI), 67.0% (radiologists), and 55.0% (trainees). AI also outperformed trainees in detecting mixed-type lesions (75% vs 55%; OR = 2.4) and small lesions \u226415\u2009mm (65.7% vs 55%; OR = 1.6). Architectural distortion had the highest miss rate (43.8%) whereas mixed-type lesions demonstrated the lowest miss rate (25.0%) by AI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>AI demonstrated superior case-level accuracy compared with radiologists and trainees, but limitations in localizing specific lesion types, supporting its role as an adjunct to human readers in screening and training.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Advances in knowledge<\/jats:title>\n                    <jats:p>This study integrates case-and-lesion-level evaluation in different case characteristics, identifying key strengths and limitations for clinical implementation. Despite superior case-level accuracy, variability in lesion localization across cancer types and sizes highlights important considerations for its integration into screening services.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bjr\/tqag177","type":"journal-article","created":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T07:52:11Z","timestamp":1785570731000},"source":"Crossref","is-referenced-by-count":0,"title":["From shadows to signals: exploring the strengths and limitations of artificial intelligence in breast cancer lesion detection on screening mammograms compared to radiologists and radiology trainees"],"prefix":"10.1093","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7021-6331","authenticated-orcid":false,"given":"Phuong Dung (Yun)","family":"Trieu","sequence":"first","affiliation":[{"name":"Discipline of Medical Imaging Sciences, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney , Camperdown, NSW 2006,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5835-1984","authenticated-orcid":false,"given":"Zhengqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Discipline of Medical Imaging Sciences, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney , Camperdown, NSW 2006,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8759-0063","authenticated-orcid":false,"given":"Seyedamir","family":"Tavakoli Taba","sequence":"additional","affiliation":[{"name":"Discipline of Medical Imaging Sciences, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney , Camperdown, NSW 2006,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7294-2599","authenticated-orcid":false,"given":"Minyan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Discipline of Medical Imaging Sciences, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney , Camperdown, NSW 2006,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4327-0724","authenticated-orcid":false,"given":"Dania Abu","family":"Awwad","sequence":"additional","affiliation":[{"name":"Discipline of Medical Imaging Sciences, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney , Camperdown, NSW 2006,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1143-5486","authenticated-orcid":false,"given":"Melissa L","family":"Barron","sequence":"additional","affiliation":[{"name":"Discipline of Medical Imaging Sciences, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney , Camperdown, NSW 2006,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4791-9845","authenticated-orcid":false,"given":"Sarah J","family":"Lewis","sequence":"additional","affiliation":[{"name":"Discipline of Medical Imaging Sciences, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney , Camperdown, NSW 2006,","place":["Australia"]},{"name":"Faculty of Health, Western Sydney University , Campbelltown 2560,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"2026081707514631800_tqag177-B1","doi-asserted-by":"publisher","first-page":"481","DOI":"10.7326\/0003-4819-155-8-201110180-00004","article-title":"Cumulative probability of false-positive recall or biopsy recommendation after 10 years of screening mammography: a cohort study","volume":"155","author":"Hubbard","year":"2011","journal-title":"Ann Intern Med"},{"key":"2026081707514631800_tqag177-B2","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.ejrad.2017.09.013","article-title":"Effectiveness and cost-effectiveness of double reading in digital mammography screening: a systematic review and meta-analysis","volume":"96","author":"Posso","year":"2017","journal-title":"Eur J Radiol"},{"key":"2026081707514631800_tqag177-B3","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/S1470-2045(23)00298-X","article-title":"Artificial intelligence-supported screen reading versus standard double reading in the mammography screening with artificial intelligence trial (MASAI): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study","volume":"24","author":"Lang","year":"2023","journal-title":"Lancet Oncol"},{"key":"2026081707514631800_tqag177-B4","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1007\/s00330-021-07892-z","article-title":"Artificial intelligence in radiology: 100 commercially available products and their scientific evidence","volume":"31","author":"van Leeuwen","year":"2021","journal-title":"Eur Radiol"},{"key":"2026081707514631800_tqag177-B5","doi-asserted-by":"publisher","first-page":"1356014","DOI":"10.3389\/fonc.2024.1356014","article-title":"A contemporary review of breast cancer risk factors and the role of artificial intelligence","volume":"14","author":"Nicolis","year":"2024","journal-title":"Front Oncol"},{"key":"2026081707514631800_tqag177-B6","doi-asserted-by":"publisher","first-page":"1732","DOI":"10.1200\/JCO.21.01337","article-title":"Multi-Institutional validation of a mammography-based breast cancer risk model","volume":"40","author":"Yala","year":"2022","journal-title":"J Clin Oncol"},{"key":"2026081707514631800_tqag177-B7","doi-asserted-by":"publisher","first-page":"11769351251371273","DOI":"10.1177\/11769351251371273","article-title":"The impact of artificial intelligence on cancer diagnosis and treatment: a review","volume":"24","author":"Najar Najafi","year":"2025","journal-title":"Cancer Inform"},{"key":"2026081707514631800_tqag177-B8","doi-asserted-by":"publisher","first-page":"1386","DOI":"10.1016\/j.acra.2014.06.013","article-title":"How mammographic breast density affects radiologists\u2019 visual search patterns","volume":"21","author":"Al Mousa","year":"2014","journal-title":"Acad Radiol"},{"key":"2026081707514631800_tqag177-B9","doi-asserted-by":"publisher","first-page":"20200363","DOI":"10.1259\/bjr.20200363","article-title":"Reader characteristics and mammogram features associated with breast imaging reporting scores","volume":"93","author":"Trieu","year":"2020","journal-title":"Br J Radiol"},{"key":"2026081707514631800_tqag177-B10","doi-asserted-by":"publisher","first-page":"1023714","DOI":"10.3389\/fonc.2022.1023714","article-title":"Look how far we have come: BREAST cancer detection education on the international stage","volume":"12","author":"Trieu","year":"2022","journal-title":"Front Oncol"},{"key":"2026081707514631800_tqag177-B11","doi-asserted-by":"publisher","first-page":"e341","DOI":"10.1016\/j.acra.2018.12.017","article-title":"Improvement of cancer detection on mammograms via BREAST test sets","volume":"26","author":"Trieu","year":"2019","journal-title":"Acad Radiol"},{"key":"2026081707514631800_tqag177-B12","volume-title":"Radiology","author":"Ranzcr","year":"2018"},{"key":"2026081707514631800_tqag177-B13","doi-asserted-by":"publisher","first-page":"322","DOI":"10.3390\/cancers16020322","article-title":"Evaluating recalibrating AI models for breast cancer diagnosis in a new context: insights from transfer learning, image enhancement and high-quality training data integration","volume":"16","author":"Jiang","year":"2024","journal-title":"Cancers (Basel)"},{"key":"2026081707514631800_tqag177-B14","doi-asserted-by":"publisher","first-page":"11893","DOI":"10.1038\/s41598-024-62324-4","article-title":"AI for interpreting screening mammograms: implications for missed cancer in double reading practices and challenging-to-locate lesions","volume":"14","author":"Jiang","year":"2024","journal-title":"Sci Rep"},{"key":"2026081707514631800_tqag177-B15","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF03178082","article-title":"Contrast limited adaptive histogram equalization image processing to improve the detection of simulated spiculations in dense mammograms","volume":"11","author":"Pisano","year":"1998","journal-title":"J Digit Imaging"},{"key":"2026081707514631800_tqag177-B16","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-32692-0_3","article-title":"Globally-aware multiple instance classifier for breast cancer screening","volume":"11861","author":"Shen","year":"2019","journal-title":"Mach Learn Med Imaging"},{"key":"2026081707514631800_tqag177-B17","volume-title":"Essential Medical Statistics","author":"Kirkwood","year":"2003"},{"key":"2026081707514631800_tqag177-B18","doi-asserted-by":"publisher","first-page":"927","DOI":"10.2147\/BCTT.S550307","article-title":"Exploring AI approaches for breast cancer detection and diagnosis: a review article","volume":"17","author":"Ali","year":"2025","journal-title":"Breast Cancer (Dove Med Press)"},{"key":"2026081707514631800_tqag177-B19","doi-asserted-by":"publisher","first-page":"e-rbgo71","DOI":"10.61622\/rbgo\/2024rbgo71","article-title":"Artificial intelligence in mammography: a systematic review of the external validation","volume":"46","author":"Branco","year":"2024","journal-title":"Rev Bras Ginecol Obstet"},{"key":"2026081707514631800_tqag177-B20","doi-asserted-by":"publisher","first-page":"m689","DOI":"10.1136\/bmj.m689","article-title":"Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies","volume":"368","author":"Nagendran","year":"2020","journal-title":"BMJ"},{"key":"2026081707514631800_tqag177-B21","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1093\/jnci\/djy222","article-title":"Stand-Alone artificial intelligence for breast cancer detection in mammography: comparison with 101 radiologists","volume":"111","author":"Rodriguez-Ruiz","year":"2019","journal-title":"J Natl Cancer Inst"},{"key":"2026081707514631800_tqag177-B22","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature"},{"key":"2026081707514631800_tqag177-B23","author":"Kharel","year":"2017"},{"key":"2026081707514631800_tqag177-B24","doi-asserted-by":"publisher","first-page":"20230210","DOI":"10.1259\/bjr.20230210","article-title":"Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography","volume":"96","author":"Salim","year":"2023","journal-title":"Br J Radiol"},{"key":"2026081707514631800_tqag177-B25","doi-asserted-by":"publisher","first-page":"e223299","DOI":"10.1148\/radiol.223299","article-title":"Performance of a breast cancer detection AI algorithm using the personal performance in mammographic screening scheme","volume":"308","author":"Chen","year":"2023","journal-title":"Radiology"},{"key":"2026081707514631800_tqag177-B26","doi-asserted-by":"publisher","first-page":"6298","DOI":"10.1007\/s00330-024-10681-z","article-title":"AI performance by mammographic density in a retrospective cohort study of 99,489 participants in BreastScreen Norway","volume":"34","author":"Bergan","year":"2024","journal-title":"Eur Radiol"},{"key":"2026081707514631800_tqag177-B27","doi-asserted-by":"publisher","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"2026081707514631800_tqag177-B28","first-page":"3462","article-title":"ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017","journal-title":"IEEE CVPR"},{"key":"2026081707514631800_tqag177-B29","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1148\/radiol.212381","article-title":"Artificial intelligence evaluation of 122 969 mammography examinations from a population-based screening program","volume":"303","author":"Larsen","year":"2022","journal-title":"Radiology"}],"container-title":["British Journal of Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bjr\/advance-article-pdf\/doi\/10.1093\/bjr\/tqag177\/70427839\/tqag177.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjr\/advance-article-pdf\/doi\/10.1093\/bjr\/tqag177\/70427839\/tqag177.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:51:52Z","timestamp":1786967512000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bjr\/advance-article\/doi\/10.1093\/bjr\/tqag177\/8748709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1093\/bjr\/tqag177","relation":{},"ISSN":["0007-1285","1748-880X"],"issn-type":[{"value":"0007-1285","type":"print"},{"value":"1748-880X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"article-number":"tqag177"}}