[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-364561-105":59,"doc-detail-364561-en":135},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":128,"head_meta":130,"extra_data":132,"updated_unix":134},105,"en","performance-of-digital-mammography-based-artificial-intelligence-computer-aided-diagnosis-on-synthetic-mammography-from-digital-breast-tomosynthesis","Performance of Digital Mammography-Based Artificial Intelligence Computer-Aided Diagnosis on Synthetic Mammography From Digital Breast Tomosynthesis","","Objective: Test the performance of an AI-CAD system for full-field digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: Retrospective analysis of 501 women (1002 breasts; 517 with cancer, 485 without) who underwent DBT and FFDM; SM was reconstructed from DBT. Commercial AI-CAD computed abnormality scores for SM and FFDM, which were compared using discrimination (AUC, sensitivity, specificity at a 10% threshold) and calibration assessment. Results: AI-CAD showed lower scores and worse calibration on SM; sensitivity decreased while specificity increased versus FFDM, with differences varying by breast and cancer characteristics. Conclusion: Due to reduced calibration and altered discrimination at the preset threshold, off-label AI-CAD use for SM should be avoided.",{"@graph":69,"@context":127},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/performance-of-digital-mammography-based-artificial-intelligence-computer-aided-diagnosis-on-synthetic-mammography-from-digital-breast-tomosynthesis/364561/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/performance-of-digital-mammography-based-artificial-intelligence-computer-aided-diagnosis-on-synthetic-mammography-from-digital-breast-tomosynthesis/364561.png","ImageObject",300,407,{"name":92,"@type":93},"Oliver","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119,123],{"name":110,"@type":111,"acceptedAnswer":112},"What was the objective of this study?","Question",{"text":113,"@type":114},"To evaluate how an AI-CAD system designed for full-field digital mammography performs when applied to synthetic mammography reconstructed from digital breast tomosynthesis.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How were performance metrics measured for SM and FFDM?",{"text":118,"@type":114},"Abnormality scores were generated for each breast, then discrimination was assessed using AUC, sensitivity, and specificity at a 10% preset threshold, along with calibration curve evaluation. Sensitivity and specificity were further analyzed by imaging and pathological characteristics.",{"name":120,"@type":111,"acceptedAnswer":121},"What were the main findings comparing SM with FFDM?",{"text":122,"@type":114},"Compared with FFDM, SM produced lower median abnormality scores and poorer calibration, with lower sensitivity but higher specificity, while AUC was comparable. Differences were especially evident across subgroups such as dense breasts and certain cancer characteristics.",{"name":124,"@type":111,"acceptedAnswer":125},"What recommendation did the study make regarding AI-CAD use for SM?",{"text":126,"@type":114},"Given reduced calibration performance and different discrimination results at the preset threshold, off-label application of the current AI-CAD to synthetic mammography should be avoided.","https://schema.org",{"og:url":83,"og:type":129,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":131,"canonical":83},"index,follow",{"doc_id":133,"site_id":62},364561,1790537966,{"code":4,"msg":5,"data":136},{"doc_id":133,"user_id":137,"nickname":92,"user_avatar":138,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":139,"file_id":140,"file_url":141,"file_type":142,"file_size":143,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":144,"language":145,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":146,"faqs":147,"seo_title":148,"seo_description":67,"update_tm":149,"read_time":150,"preview_page_count":19,"preview_urls":151},8796095461610,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Original Article | Breast Imaging  \neISSN 2005-8330  \n[https://doi.org/10.3348/kjr.2024.0664](https://doi.org/10.3348/kjr.2024.0664)  \n[Korean J Radiol 2025](Korean J Radiol 2025);[26](26)([3](3))[:217-229](:217-229)  \nPerformance of Digital Mammography-Based Artificial Intelligence Computer-Aided Diagnosis on Synthetic Mammography From Digital Breast Tomosynthesis  \nKyung Eun Lee1, Sung Eun Song2, Kyu Ran Cho2, Min Sun Bae3, Bo Kyoung Seo3, Soo-Yeon Kim1 * , Ok Hee Woo1 *  \n1 Department of Radiology, Korea University Guro Hospital, Korea University College of Medicine, Seoul, Republic of Korea 2 Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul, Republic of Korea 3 Department of Radiology, Korea University Ansan Hospital, Korea University College of Medicine, Ansan, Republic of Korea  \nObjective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM) .  \nMaterials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version [1.1.7.2](1.1.7.2)) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics. The results of SM and FFDM were compared.  \nResults: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P \u003C 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P \u003C 0.001), higher specificity (95.5% vs. 91.8%, P \u003C 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM inasymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts.  \nConclusion: AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM. Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.  \nKeywords: Artificial intelligence-based computer-aided diagnosis; Synthetic mammography; Full-field digital mammography; Sensitivity; Specificity  \nINTRODUCTION  \nDigital breast tomosynthesis (DBT) provides three-  \ndimensional images of the breast by acquiring multiple projections at different angles [1] . DBT helps reduce recall rates by reducing tissue superimposition [1] . Studies have  \nReceived: July 12, 2024 Revised: December 10, 2024 Accepted: December 12, 2024  \n*These authors contributed equally to this work.  \nCorresponding author: Soo-Yeon Kim, MD, PhD, Department of Radiology, Korea University Guro Hospital, Korea University College of Medicine, 148 Gurodong-ro, Guro-gu, Seoul 08308, Republic of Korea  \n• E-mail: [sooyeonkim41@gmail.com](sooyeonkim41@gmail.com)  \nCorresponding author: Ok Hee Woo, MD, PhD, Department of Radiology, Korea University Guro Hospital, Korea University College of Medicine, 148 Gurodong-ro, Guro-gu, Seoul 08308, Republic of Korea  \n• [E-mail: wokhee@korea.ac.kr](E-mail: wokh","cbCaisx5veU3IHQP","https://ap.wps.com/l/cbCaisx5veU3IHQP","pdf",2441054,13,"English","# Introduction\n## Background on DBT vs FFDM\n## Role of synthetic mammography\n## AI-CAD integration with mammography","[{\"question\":\"What was the objective of this study?\",\"answer\":\"To evaluate how an AI-CAD system designed for full-field digital mammography performs when applied to synthetic mammography reconstructed from digital breast tomosynthesis.\"},{\"question\":\"How were performance metrics measured for SM and FFDM?\",\"answer\":\"Abnormality scores were generated for each breast, then discrimination was assessed using AUC, sensitivity, and specificity at a 10% preset threshold, along with calibration curve evaluation. Sensitivity and specificity were further analyzed by imaging and pathological characteristics.\"},{\"question\":\"What were the main findings comparing SM with FFDM?\",\"answer\":\"Compared with FFDM, SM produced lower median abnormality scores and poorer calibration, with lower sensitivity but higher specificity, while AUC was comparable. Differences were especially evident across subgroups such as dense breasts and certain cancer characteristics.\"},{\"question\":\"What recommendation did the study make regarding AI-CAD use for SM?\",\"answer\":\"Given reduced calibration performance and different discrimination results at the preset threshold, off-label application of the current AI-CAD to synthetic mammography should be avoided.\"}]","Performance of Digital Mammography-Based Artificial Intelligence Computer-Aided Diagnosis on Synthetic Mammography From Digital Breast Tomosynthesis | PDF",1790158166,33,[152,156,160,164],{"page_no":8,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/73351d9a510986fa6d705d7659c77566.webp",983,1310,{"page_no":14,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/62b901ad649e22440c1f7d2005ad52d5.webp",982,1309,{"page_no":81,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/79c30df2e639fdefb0c9fe95f123f2ef.webp",981,1308,{"page_no":19,"url":165,"width":166,"height":167},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/48d2478d2645fbea07230fa6910846e9.webp",980,1306]