{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:43Z","timestamp":1785545023517,"version":"3.56.0"},"reference-count":39,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Breast cancer remains the most common cancer among women globally. Mammography is a key diagnostic modality; however, interpretation is increasingly challenged by rising imaging volumes, a global shortage of breast radiologists, and variability in reader experience. Artificial intelligence (AI) has been proposed as a potential adjunct to address these issues, particularly in settings with high breast density, such as Asian populations. This study aimed to evaluate the impact of AI assistance on mammographic diagnostic performance among resident and consultant radiologists in Singapore.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To assess whether AI assistance improves diagnostic accuracy in mammographic breast cancer detection across radiologists with varying levels of experience.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A multi-reader, multi-case study was conducted at the National University Hospital, Singapore, from May to August 2023. De-identified digital mammograms from 500 women (250 with cancer and 250 normal or benign) were interpreted by 17 radiologists (4 consultants, 4 senior residents, and 9 junior residents). Each radiologist read all cases over 2 reading sessions: one without AI assistance and another with AI assistance, separated by a 1-month washout period. The AI system (FxMammo) provided heatmaps and malignancy risk scores to support decision-making. Area under the curve of the receiver operating characteristic (AUROC) was used to evaluate diagnostic performance.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Among the 500 cases, 250 were malignant and 250 were non-malignant. Of the malignant cases, 16%(80\/500) were ductal carcinoma in situ and 84%(420\/500) were invasive cancers. Among non-malignant cases, 69.2%(346\/500) were normal, 17.6%(88) benign, and 3.6%(18\/500) possibly benign but stable on follow-up. Masses (54.4%, 272) and calcifications (10.8%, 54\/500) were the most common findings in cancer cases. A majority of both malignant (66.8%, 334\/500) and non-malignant (68%, 340\/500) cases had heterogeneously or extremely dense breasts (BIRADS [Breast Imaging Reporting and Data System] categories C and D). The AI model achieved an AUROC of 0.93 (95% CI 0.91\u20100.95), slightly higher than consultant radiologists (AUROC 0.90, 95% CI 0.89\u20100.92;\n P<\/jats:italic>\n =.21). With AI assistance, AUROC improved among junior residents (from 0.84 to 0.86;\n P<\/jats:italic>\n =.38) and senior residents (from 0.85 to 0.88;\n P<\/jats:italic>\n =.13), with senior residents approaching consultant-level performance (AUROC difference 0.02;\n P<\/jats:italic>\n =.051). Diagnostic gains with AI were greatest in women with dense breasts and among less experienced radiologists. AI also improved inter-reader agreement and time efficiency, particularly in benign or normal cases.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This is the first study in Asia to evaluate AI assistance in mammography interpretation by radiologists of varying experience. AI significantly improved diagnostic performance and efficiency among residents, helping to narrow the experience-performance gap without compromising specificity. These findings suggest a role for AI in enhancing diagnostic consistency, improving workflow, and supporting training. Integration into clinical and educational settings may offer scalable benefits, though careful attention to threshold calibration, feedback loops, and real-world validation remains essential. Further studies in routine screening settings are needed to confirm generalizability and cost-effectiveness.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/66931","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:41:11Z","timestamp":1764020471000},"page":"e66931-e66931","source":"Crossref","is-referenced-by-count":2,"title":["Impact of AI on Breast Cancer Detection Rates in Mammography by Radiologists of Varying Experience Levels in Singapore: Preliminary Comparative Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4916-2142","authenticated-orcid":false,"given":"Serene Si Ning","family":"Goh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5083-8122","authenticated-orcid":false,"given":"Hao","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4857-3310","authenticated-orcid":false,"given":"Loon Ying","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3061-7881","authenticated-orcid":false,"given":"Edward Zhen Yu","family":"Seah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1047-7658","authenticated-orcid":false,"given":"Wai Keat","family":"Lau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1524-8628","authenticated-orcid":false,"given":"Alvin Hong Zhi","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8011-9439","authenticated-orcid":false,"given":"Shi Wei Desmond","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6241-4132","authenticated-orcid":false,"given":"Han Yang","family":"Ong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0656-2659","authenticated-orcid":false,"given":"Samuel","family":"Lau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1544-1250","authenticated-orcid":false,"given":"Yi Liang","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6874-380X","authenticated-orcid":false,"given":"Mun sze","family":"Khaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0935-6612","authenticated-orcid":false,"given":"Chee Woei","family":"Yap","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4325-1311","authenticated-orcid":false,"given":"Kei Yiu Douglas","family":"Hui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4922-1280","authenticated-orcid":false,"given":"Wei Chuan","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2608-0386","authenticated-orcid":false,"given":"Haziz Siti Rozana Binti","family":"Abdul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1667-3619","authenticated-orcid":false,"given":"Vanessa Mei Hui","family":"Khoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4928-1195","authenticated-orcid":false,"given":"Shuliang","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3575-8853","authenticated-orcid":false,"given":"Felicity Jane","family":"Pool","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5846-0497","authenticated-orcid":false,"given":"Yun Song","family":"Choo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1934-9926","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8491-0375","authenticated-orcid":false,"given":"Pooja","family":"Jagmohan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9086-6240","authenticated-orcid":false,"given":"Premilla Pillay","family":"Gopinathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5726-9965","authenticated-orcid":false,"given":"Mikael","family":"Hartman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5338-6248","authenticated-orcid":false,"given":"Mengling","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"issue":"10","key":"R1","doi-asserted-by":"publisher","first-page":"931","DOI":"10.3348\/kjr.2023.0838","article-title":"The growing problem of radiologist shortage: Hong Kong\u2019s perspective","volume":"24","author":"Lai","journal-title":"Korean J Radiol"},{"issue":"5","key":"R2","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1093\/ije\/30.5.959","article-title":"Ethnic differences in mammographic densities","volume":"30","author":"Maskarinec","journal-title":"Int J Epidemiol"},{"issue":"2","key":"R3","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1148\/radiol.2018181371","article-title":"Detection of breast cancer with mammography: effect of an artificial intelligence support system","volume":"290","author":"Rodr\u00edguez-Ruiz","journal-title":"Radiology"},{"issue":"6","key":"R4","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020190208","article-title":"Improving breast cancer detection accuracy of mammography with the concurrent use of an artificial intelligence tool","volume":"2","author":"Pacil\u00e8","journal-title":"Radiol Artif Intell"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1148\/radiol.2021203555","article-title":"AI-based strategies to reduce workload in breast cancer screening with mammography and tomosynthesis: a retrospective evaluation","volume":"300","author":"Raya-Povedano","journal-title":"Radiology"},{"issue":"3","key":"R6","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1007\/s00330-020-07165-1","article-title":"Identifying normal mammograms in a large screening population using artificial intelligence","volume":"31","author":"L\u00e5ng","journal-title":"Eur Radiol"},{"issue":"6","key":"R7","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1016\/j.jacr.2023.02.031","article-title":"Systematic review of radiology residency artificial intelligence curricula: preparing future radiologists for the artificial intelligence era","volume":"20","author":"Garin","journal-title":"J Am Coll Radiol"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000032518","article-title":"Radiological education in the era of artificial intelligence: a review","volume":"102","author":"Wang","journal-title":"Medicine (Baltimore)"},{"issue":"4","key":"R9","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.222176","article-title":"Automation bias in mammography: the impact of artificial intelligence BI-RADS suggestions on reader performance","volume":"307","author":"Dratsch","journal-title":"Radiology"},{"issue":"5","key":"R10","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1067\/j.cpradiol.2020.09.005","article-title":"Preventing physician burnout in breast imaging: scope of the problem and keys to success","volume":"50","author":"Kalantarova","journal-title":"Curr Probl Diagn Radiol"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1117\/12.2083150","article-title":"Demonstration of multi- and single-reader sample size program for diagnostic studies software","volume":"9416","author":"Hillis","journal-title":"Proc SPIE Int Soc Opt Eng"},{"key":"R12","unstructured":"The Royal College of Radiologists. Joint Final Clinical Radiology exams Joint Final Clinical Radiology Exams. The Royal College of Radiologists; 2023. URL: https:\/\/www.rcr.ac.uk\/clinical-radiology\/exams\/joint-final-clinical-radiology-exams [Accessed 10-10-2023]"},{"key":"R13","unstructured":"Accreditation Council for Graduate Medical Education (ACGME). ACGME program requirements for graduate medical education in diagnostic radiology. 2023. URL: https:\/\/www.acgme.org\/globalassets\/pfassets\/programrequirements\/2025-reformatted-requirements\/420_diagnosticradiology_2025_reformatted.pdf [Accessed 10-10-2023]"},{"key":"R14","unstructured":"Specialists Accreditation Board (SAB). Diagnostic Radiology Residency. Sep 1, 2022. URL: https:\/\/sab.healthprofessionals.gov.sg\/specialist-training\/list-of-recognised-specialties\/diagnostic-radiology\/ [Accessed 10-10-2023]"},{"key":"R15","unstructured":"FathomX. Home. 2023. URL: https:\/\/www.fathomx.co\/ [Accessed 10-10-2023]"},{"issue":"3","key":"R16","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1002\/bimj.200710415","article-title":"Youden Index and optimal cut-point estimated from observations affected by a lower limit of detection","volume":"50","author":"Ruopp","journal-title":"Biom J"},{"key":"R17","unstructured":"OsiriX. OsiriX DICOM viewer. The world famous medical imaging viewer. 2023. URL: https:\/\/www.osirix-viewer.com\/ [Accessed 10-10-2023]"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","DOI":"10.1093\/radadv\/umae011","article-title":"Artificial intelligence as a second reader for screening mammography","volume":"1","author":"Nakai","journal-title":"Radiol Adv"},{"issue":"7788","key":"R19","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","journal-title":"Nature New Biol"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1080\/03610919508813243","article-title":"Hypothesis testing of diagnostic accuracy for multiple readers and multiple tests an anova approach with dependent observations","volume":"24","author":"Obuchowski","journal-title":"Commun Statist Simul Comput"},{"issue":"3","key":"R21","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1002\/sim.2532","article-title":"A comparison of denominator degrees of freedom methods for multiple observer ROC analysis","volume":"26","author":"Hillis","journal-title":"Stat Med"},{"issue":"3","key":"R22","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"DeLong","journal-title":"Biometrics"},{"key":"R23","unstructured":"Rupert Jr G . Simultaneous Statistical Inference. 2012."},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00438-z","article-title":"Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis","volume":"4","author":"Aggarwal","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1148\/radiol.2021210391","article-title":"Machine learning for workflow applications in screening mammography: systematic review and meta-analysis","volume":"302","author":"Hickman","journal-title":"Radiology"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2214\/AJR.23.29655","article-title":"Screening in patients with dense breasts: comparison of mammography, artificial intelligence, and supplementary ultrasound","volume":"222","author":"Lee","journal-title":"AJR Am J Roentgenol"},{"key":"R27","author":"Goh","journal-title":"Intell Oncol"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.acra.2018.06.023","article-title":"Resident case volume correlates with clinical performance: finding the sweet spot","volume":"26","author":"Agarwal","journal-title":"Acad Radiol"},{"issue":"3","key":"R29","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1038\/s41591-024-02850-w","article-title":"Heterogeneity and predictors of the effects of AI assistance on radiologists","volume":"30","author":"Yu","journal-title":"Nat Med"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Chen Y Wu Z Wang P Xie L Yan M Jiang M et al. Ready to embrace artificial intelligence? results of a nationwide survey on radiology residents in China: a cross-sectional study. J Med Internet Res. Preprint posted online on Oct 19, 2023. [doi: 10.2196\/48249]","DOI":"10.2196\/48249"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-023-01595-3","article-title":"A framework to integrate artificial intelligence training into radiology residency programs: preparing the future radiologist","volume":"15","author":"van Kooten","journal-title":"Insights Imaging"},{"issue":"7","key":"R32","doi-asserted-by":"publisher","first-page":"e507","DOI":"10.1016\/S2589-7500(22)00070-X","article-title":"Combining the strengths of radiologists and AI for breast cancer screening: a retrospective analysis","volume":"4","author":"Leibig","journal-title":"Lancet Digit Health"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10549-024-07353-3","article-title":"Frequency and characteristics of errors by artificial intelligence (AI) in reading screening mammography: a systematic review","volume":"207","author":"Zeng","journal-title":"Breast Cancer Res Treat"},{"issue":"6","key":"R34","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1016\/j.acra.2018.03.007","article-title":"Toward augmented radiologists: changes in radiology education in the era of machine learning and artificial intelligence","volume":"25","author":"Tajmir","journal-title":"Acad Radiol"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41754-0","article-title":"Cost-effectiveness requirements for implementing artificial intelligence technology in the Women\u2019s UK Breast Cancer Screening service","volume":"14","author":"Vargas-Palacios","journal-title":"Nat Commun"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36435-3","article-title":"The impact of AI suggestions on radiologists\u2019 decisions: a pilot study of explainability and attitudinal priming interventions in mammography examination","volume":"13","author":"Rezazade Mehrizi","journal-title":"Sci Rep"},{"issue":"4","key":"R37","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jbi\/wbaa033","article-title":"Artificial intelligence: a primer for breast imaging radiologists","volume":"2","author":"Bahl","journal-title":"J Breast Imaging"},{"issue":"3","key":"R38","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.1007\/s00330-023-10181-6","article-title":"Barriers and facilitators of artificial intelligence conception and implementation for breast imaging diagnosis in clinical practice: a scoping review","volume":"34","author":"Lokaj","journal-title":"Eur Radiol"},{"issue":"1","key":"R39","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","journal-title":"BMC Med"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e66931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:28:19Z","timestamp":1785536899000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e66931"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":39,"URL":"https:\/\/doi.org\/10.2196\/66931","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"article-number":"v9i10e66931"}}