{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T02:19:58Z","timestamp":1785291598549,"version":"3.55.0"},"reference-count":33,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Artificial intelligence (AI)-based systems are increasingly being used to assist radiologists in detecting breast cancer on mammograms. However, applying fixed AI score thresholds across diverse lesion types may compromise diagnostic performance, especially in women with dense breasts. This study aimed to determine optimal category-specific AI thresholds and to analyze discrepancies between AI predictions and radiologist assessments, particularly for BI-RADS 4A versus 4B\/4C lesions. Methods: We retrospectively analyzed 194 mammograms (76 BI-RADS 4A and 118 BI-RADS 4B\/4C) using FDA-approved AI software. Lesion characteristics, breast density, AI scores, and pathology results were collected. A receiver operating characteristic (ROC) analysis was conducted to determine the optimal thresholds via Youden\u2019s index. Discrepancy analysis focused on BI-RADS 4A lesions with AI scores of \u226535 and BI-RADS 4B\/4C lesions with AI scores of &lt;35. Results: AI scores were significantly higher in malignant versus benign cases (72.1 vs. 20.9; p &lt; 0.001). The optimal AI threshold was 19 for BI-RADS 4A (AUC = 0.685) and 63 for BI-RADS 4B\/4C (AUC = 0.908). In discordant cases, BI-RADS 4A lesions with scores of \u226535 had a malignancy rate of 43.8%, while BI-RADS 4B\/4C lesions with scores of &lt;35 had a malignancy rate of 19.5%. Conclusions: Using category-specific AI thresholds improves diagnostic accuracy and supports radiologist decision-making. However, limitations persist in BI-RADS 4A cases with overlapping scores, reinforcing the need for radiologist oversight and tailored AI integration strategies in clinical practice.<\/jats:p>","DOI":"10.3390\/diagnostics15111368","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:46:38Z","timestamp":1748493998000},"page":"1368","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Artificial Intelligence Thresholds for Mammographic Lesion Detection: A Retrospective Study on Diagnostic Performance and Radiologist\u2013Artificial Intelligence Discordance"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1404-1578","authenticated-orcid":false,"given":"Taesun","family":"Han","sequence":"first","affiliation":[{"name":"Department of Radiology, Park Heeboong Surgical Clinic, 203, Geowerk, 7, Hyowon-ro, 256beon-gil, Gwonseon-gu, Suwon-si 16571, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyesun","family":"Yun","sequence":"additional","affiliation":[{"name":"Department of Family Medicine, Park Heeboong Surgical Clinic, 203, Geowerk, 7, Hyowon-ro, 256beon-gil, Gwonseon-gu, Suwon-si 16571, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Keun","family":"Sur","sequence":"additional","affiliation":[{"name":"Department of Radiology, Dongsuwon General Hospital, 165, Jungbu-daero, Paldal-gu, Suwon-si 16494, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heeboong","family":"Park","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Park Heeboong Surgical Clinic, 203, Geowerk, 7, Hyowon-ro, 256beon-gil, Gwonseon-gu, Suwon-si 16571, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1038\/s41591-025-03502-3","article-title":"Global Patterns and Trends in Breast Cancer Incidence and Mortality across 185 Countries","volume":"31","author":"Kim","year":"2025","journal-title":"Nat. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"S51","DOI":"10.1046\/j.1524-4741.9.s2.4.x","article-title":"Global Summit Early Detection Panel Early Detection of Breast Cancer in Countries with Limited Resources","volume":"9","author":"Anderson","year":"2003","journal-title":"Breast J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1038\/bjc.2013.177","article-title":"The Benefits and Harms of Breast Cancer Screening: An Independent Review","volume":"108","author":"Marmot","year":"2013","journal-title":"Br. J. Cancer"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1001\/jamainternmed.2015.5231","article-title":"Breast Cancer Surveillance Consortium Diagnostic Accuracy of Digital Screening Mammography with and Without Computer-Aided Detection","volume":"175","author":"Lehman","year":"2015","journal-title":"JAMA Intern. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e200265","DOI":"10.1001\/jamanetworkopen.2020.0265","article-title":"Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms","volume":"3","author":"Schaffter","year":"2020","journal-title":"JAMA Netw. Open"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1148\/radiol.2019191542","article-title":"Can AI Help Make Screening Mammography \u201cLean\u201d?","volume":"293","author":"Kontos","year":"2019","journal-title":"Radiology"},{"key":"ref_7","doi-asserted-by":"crossref","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":"Krupinski","year":"2019","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e138","DOI":"10.1016\/S2589-7500(20)30003-0","article-title":"Changes in Cancer Detection and False-Positive Recall in Mammography Using Artificial Intelligence: A Retrospective, Multireader Study","volume":"2","author":"Kim","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"505","DOI":"10.3348\/kjr.2021.0476","article-title":"Improving the Performance of Radiologists Using Artificial Intelligence-Based Detection Support Software for Mammography: A Multi-Reader Study","volume":"23","author":"Lee","year":"2022","journal-title":"Korean J. Radiol."},{"key":"ref_10","doi-asserted-by":"crossref","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":"ref_11","doi-asserted-by":"crossref","first-page":"e180096","DOI":"10.1148\/ryai.2019180096","article-title":"Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis","volume":"1","author":"Conant","year":"2019","journal-title":"Radiol. Artif. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1148\/radiol.212381","article-title":"Artificial Intelligence Evaluation of 122\u2009969 Mammography Examinations from a Population-Based Screening Program","volume":"303","author":"Larsen","year":"2022","journal-title":"Radiology"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"343","DOI":"10.3348\/kjr.2023.0907","article-title":"Positive Predictive Values of Abnormality Scores From a Commercial Artificial Intelligence-Based Computer-Aided Diagnosis for Mammography","volume":"25","author":"Lee","year":"2024","journal-title":"Korean J. Radiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e468","DOI":"10.1016\/S2589-7500(20)30185-0","article-title":"Effect of Artificial Intelligence-Based Triaging of Breast Cancer Screening Mammograms on Cancer Detection and Radiologist Workload: A Retrospective Simulation Study","volume":"2","author":"Dembrower","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"ref_15","unstructured":"American College of Radiology (2025, April 15). Breast Imaging Reporting and Data System (BI-RADS). ACR.org. Available online: https:\/\/www.acr.org\/Clinical-Resources\/Clinical-Tools-and-Reference\/Reporting-and-Data-Systems\/BI-RADS."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3735","DOI":"10.1007\/s00330-023-09461-y","article-title":"Artificial Intelligence in BreastScreen Norway: A Retrospective Analysis of a Cancer-Enriched Sample Including 1254 Breast Cancer Cases","volume":"33","author":"Koch","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1186\/s13058-024-01821-w","article-title":"Screening Mammography Performance According to Breast Density: A Comparison between Radiologists versus Standalone Intelligence Detection","volume":"26","author":"Kwon","year":"2024","journal-title":"Breast Cancer Res. BCR"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e200299","DOI":"10.1148\/ryai.2021200299","article-title":"Artificial Intelligence Detection of Missed Cancers at Digital Mammography That Were Detected at Digital Breast Tomosynthesis","volume":"3","author":"Dahlblom","year":"2021","journal-title":"Radiol. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"15330338221075172","DOI":"10.1177\/15330338221075172","article-title":"Diagnostic Performance of AI for Cancers Registered in A Mammography Screening Program: A Retrospective Analysis. Technol","volume":"21","author":"Koyluoglu","year":"2022","journal-title":"Cancer Res. Treat."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6145","DOI":"10.1007\/s00330-024-10661-3","article-title":"Diagnostic Capabilities of Artificial Intelligence as an Additional Reader in a Breast Cancer Screening Program","volume":"34","author":"Seker","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"57","DOI":"10.4048\/jbc.2022.25.e4","article-title":"Artificial Intelligence for Breast Cancer Screening in Mammography (AI-STREAM): A Prospective Multicenter Study Design in Korea Using AI-Based CADe\/x","volume":"25","author":"Chang","year":"2022","journal-title":"J. Breast Cancer"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for Rating Diagnostic Tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhao, T., Fu, C., Song, W., and Sham, C.-W. (2024). RGGC-UNet: Accurate Deep Learning Framework for Signet Ring Cell Semantic Segmentation in Pathological Images. Bioengineering, 11.","DOI":"10.3390\/bioengineering11010016"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhao, T., Fu, C., Tian, Y., Song, W., and Sham, C.-W. (2023). GSN-HVNET: A Lightweight, Multi-Task Deep Learning Framework for Nuclei Segmentation and Classification. Bioengineering, 10.","DOI":"10.3390\/bioengineering10030393"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"129489","DOI":"10.1016\/j.neucom.2025.129489","article-title":"RTLinearFormer: Semantic Segmentation with Lightweight Linear Attentions","volume":"625","author":"Gu","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1278","DOI":"10.1111\/imj.15017","article-title":"Addressing the Challenges of Artificial Intelligence in Medicine","volume":"50","author":"Smith","year":"2020","journal-title":"Intern. Med. J."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e703","DOI":"10.1016\/S2589-7500(23)00153-X","article-title":"ScreenTrustCAD Trial Consortium Artificial Intelligence for Breast Cancer Detection in Screening Mammography in Sweden: A Prospective, Population-Based, Paired-Reader, Non-Inferiority Study","volume":"5","author":"Dembrower","year":"2023","journal-title":"Lancet Digit. Health"},{"key":"ref_29","doi-asserted-by":"crossref","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","year":"2024","journal-title":"Breast Cancer Res. Treat."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.jacr.2023.10.018","article-title":"Artificial Intelligence-Driven Mammography-Based Future Breast Cancer Risk Prediction: A Systematic Review","volume":"21","author":"Schopf","year":"2024","journal-title":"J. Am. Coll. Radiol. JACR"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Pertuz, S., Ortega, D., Suarez, \u00c9., Cancino, W., Africano, G., Rinta-Kiikka, I., Arponen, O., Paris, S., and Lozano, A. (2023). Saliency of Breast Lesions in Breast Cancer Detection Using Artificial Intelligence. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-46921-3"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3528","DOI":"10.1111\/cas.15511","article-title":"Establishment of a Deep-Learning System to Diagnose BI-RADS4a or Higher Using Breast Ultrasound for Clinical Application","volume":"113","author":"Hayashida","year":"2022","journal-title":"Cancer Sci."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Evans, K.K., Birdwell, R.L., and Wolfe, J.M. (2013). If You Don\u2019t Find It Often, You Often Don\u2019t Find It: Why Some Cancers Are Missed in Breast Cancer Screening. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0064366"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/11\/1368\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:42:46Z","timestamp":1760031766000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/11\/1368"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,29]]},"references-count":33,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["diagnostics15111368"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15111368","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,29]]}}}