Ok Hee Woo, Sung Eun Song, Su Jin Choe, Minhye Kim, Kyu Ran Cho, Bo Kyoung Seo
{"title":"人工智能筛查乳房x光检查遗漏的浸润性乳腺癌","authors":"Ok Hee Woo, Sung Eun Song, Su Jin Choe, Minhye Kim, Kyu Ran Cho, Bo Kyoung Seo","doi":"10.1148/radiol.242408","DOIUrl":null,"url":null,"abstract":"<p><p>Background Little is known about the features of invasive breast cancers missed by artificial intelligence (AI) on mammograms. Purpose To assess the false-negative rate (FNR) of AI mammogram evaluation according to molecular subtype and to investigate the features of and reasons for AI-missed cancers. Materials and Methods This retrospective study identified consecutive patients diagnosed with breast cancer between January 2014 and December 2020. Commercial AI software was used to read the mammograms, and abnormality score (AS) was acquired. AI-missed cancers were defined as those for which AI did not identify a precise location matching the reference standard. The FNR was calculated by counting AI-missed cancers according to molecular subtype (hormone receptor-positive [luminal] vs human epidermal growth factor receptor 2 [HER2]-enriched vs triple-negative). Three blinded radiologists classified AI-missed cancers as either actionable or under threshold, and reasons for misses were determined through nonblinded reviews. Features were compared according to AI detection with the χ<sup>2</sup> test. Results A total of 1082 consecutive women diagnosed with 1097 cancers (mean age, 54.3 years ± 11 [SD]) were included. AI missed 14% (154 of 1097) of cancers. The FNR was lowest in the HER2-enriched subtype (9% [36 of 398] in the HER2-enriched subtype, 17.2% [106 of 616] in the luminal subtype, and 14.5% [12 of 83] in the triple-negative subtype; <i>P</i> = .001). Compared with AI-detected cancers, AI-missed cancers were associated with younger age, a tumor size less than or equal to 2 cm, a lower histologic grade, fewer lymph node metastases, more Breast Imaging Reporting and Data System category 4 findings, lower Ki-67 expression, and nonmammary zone locations (all, <i>P</i> < .05). In blinded reviews, 61.7% (95 of 154) of AI-missed cancers were actionable; the reasons for misses were dense breasts (<i>n</i> = 56), nonmammary zone locations (<i>n</i> = 22), architectural distortions (<i>n</i> = 12), and amorphous microcalcifications (<i>n</i> = 5). Conclusion To reduce AI-missed cancers on mammograms, attention should be given to luminal cancer, dense breasts, nonmammary zone locations, architectural distortions, and amorphous calcifications. Published under a CC BY 4.0 license. <i>Supplemental material is available for this article.</i> See also the editorial by Mullen in this issue.</p>","PeriodicalId":20896,"journal":{"name":"Radiology","volume":"315 3","pages":"e242408"},"PeriodicalIF":12.1000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Invasive Breast Cancers Missed by AI Screening of Mammograms.\",\"authors\":\"Ok Hee Woo, Sung Eun Song, Su Jin Choe, Minhye Kim, Kyu Ran Cho, Bo Kyoung Seo\",\"doi\":\"10.1148/radiol.242408\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Background Little is known about the features of invasive breast cancers missed by artificial intelligence (AI) on mammograms. Purpose To assess the false-negative rate (FNR) of AI mammogram evaluation according to molecular subtype and to investigate the features of and reasons for AI-missed cancers. Materials and Methods This retrospective study identified consecutive patients diagnosed with breast cancer between January 2014 and December 2020. Commercial AI software was used to read the mammograms, and abnormality score (AS) was acquired. AI-missed cancers were defined as those for which AI did not identify a precise location matching the reference standard. The FNR was calculated by counting AI-missed cancers according to molecular subtype (hormone receptor-positive [luminal] vs human epidermal growth factor receptor 2 [HER2]-enriched vs triple-negative). Three blinded radiologists classified AI-missed cancers as either actionable or under threshold, and reasons for misses were determined through nonblinded reviews. Features were compared according to AI detection with the χ<sup>2</sup> test. Results A total of 1082 consecutive women diagnosed with 1097 cancers (mean age, 54.3 years ± 11 [SD]) were included. AI missed 14% (154 of 1097) of cancers. The FNR was lowest in the HER2-enriched subtype (9% [36 of 398] in the HER2-enriched subtype, 17.2% [106 of 616] in the luminal subtype, and 14.5% [12 of 83] in the triple-negative subtype; <i>P</i> = .001). Compared with AI-detected cancers, AI-missed cancers were associated with younger age, a tumor size less than or equal to 2 cm, a lower histologic grade, fewer lymph node metastases, more Breast Imaging Reporting and Data System category 4 findings, lower Ki-67 expression, and nonmammary zone locations (all, <i>P</i> < .05). In blinded reviews, 61.7% (95 of 154) of AI-missed cancers were actionable; the reasons for misses were dense breasts (<i>n</i> = 56), nonmammary zone locations (<i>n</i> = 22), architectural distortions (<i>n</i> = 12), and amorphous microcalcifications (<i>n</i> = 5). Conclusion To reduce AI-missed cancers on mammograms, attention should be given to luminal cancer, dense breasts, nonmammary zone locations, architectural distortions, and amorphous calcifications. Published under a CC BY 4.0 license. <i>Supplemental material is available for this article.</i> See also the editorial by Mullen in this issue.</p>\",\"PeriodicalId\":20896,\"journal\":{\"name\":\"Radiology\",\"volume\":\"315 3\",\"pages\":\"e242408\"},\"PeriodicalIF\":12.1000,\"publicationDate\":\"2025-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1148/radiol.242408\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1148/radiol.242408","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Invasive Breast Cancers Missed by AI Screening of Mammograms.
Background Little is known about the features of invasive breast cancers missed by artificial intelligence (AI) on mammograms. Purpose To assess the false-negative rate (FNR) of AI mammogram evaluation according to molecular subtype and to investigate the features of and reasons for AI-missed cancers. Materials and Methods This retrospective study identified consecutive patients diagnosed with breast cancer between January 2014 and December 2020. Commercial AI software was used to read the mammograms, and abnormality score (AS) was acquired. AI-missed cancers were defined as those for which AI did not identify a precise location matching the reference standard. The FNR was calculated by counting AI-missed cancers according to molecular subtype (hormone receptor-positive [luminal] vs human epidermal growth factor receptor 2 [HER2]-enriched vs triple-negative). Three blinded radiologists classified AI-missed cancers as either actionable or under threshold, and reasons for misses were determined through nonblinded reviews. Features were compared according to AI detection with the χ2 test. Results A total of 1082 consecutive women diagnosed with 1097 cancers (mean age, 54.3 years ± 11 [SD]) were included. AI missed 14% (154 of 1097) of cancers. The FNR was lowest in the HER2-enriched subtype (9% [36 of 398] in the HER2-enriched subtype, 17.2% [106 of 616] in the luminal subtype, and 14.5% [12 of 83] in the triple-negative subtype; P = .001). Compared with AI-detected cancers, AI-missed cancers were associated with younger age, a tumor size less than or equal to 2 cm, a lower histologic grade, fewer lymph node metastases, more Breast Imaging Reporting and Data System category 4 findings, lower Ki-67 expression, and nonmammary zone locations (all, P < .05). In blinded reviews, 61.7% (95 of 154) of AI-missed cancers were actionable; the reasons for misses were dense breasts (n = 56), nonmammary zone locations (n = 22), architectural distortions (n = 12), and amorphous microcalcifications (n = 5). Conclusion To reduce AI-missed cancers on mammograms, attention should be given to luminal cancer, dense breasts, nonmammary zone locations, architectural distortions, and amorphous calcifications. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Mullen in this issue.
期刊介绍:
Published regularly since 1923 by the Radiological Society of North America (RSNA), Radiology has long been recognized as the authoritative reference for the most current, clinically relevant and highest quality research in the field of radiology. Each month the journal publishes approximately 240 pages of peer-reviewed original research, authoritative reviews, well-balanced commentary on significant articles, and expert opinion on new techniques and technologies.
Radiology publishes cutting edge and impactful imaging research articles in radiology and medical imaging in order to help improve human health.