人工智能乳腺 X 光摄影在致密型乳腺中的筛查效果：与补充性筛查超声的对比研究。

Screening Outcomes of Mammography with AI in Dense Breasts: A Comparative Study with Supplemental Screening US.

机构信息

From the Department of Radiology (S.M.H., H.Y., H.J., S.H.L., J.M.C.) and Medical Research Collaborating Center (M.J.J.), Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Republic of Korea; Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea (S.M.H., S.H.L., J.M.C.); Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea (S.M.H.); Department of Radiology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea (I.Y.); and Department of Radiology, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Republic of Korea (A.Y.).

出版信息

Radiology. 2024 Jul;312(1):e233391. doi: 10.1148/radiol.233391.

DOI:10.1148/radiol.233391

PMID:39041940

Abstract

Background Comparative performance between artificial intelligence (AI) and breast US for women with dense breasts undergoing screening mammography remains unclear. Purpose To compare the performance of mammography alone, mammography with AI, and mammography plus supplemental US for screening women with dense breasts, and to investigate the characteristics of the detected cancers. Materials and Methods A retrospective database search identified consecutive asymptomatic women (≥40 years of age) with dense breasts who underwent mammography plus supplemental whole-breast handheld US from January 2017 to December 2018 at a primary health care center. Sequential reading for mammography alone and mammography with the aid of an AI system was conducted by five breast radiologists, and their recall decisions were recorded. Results of the combined mammography and US examinations were collected from the database. A dedicated breast radiologist reviewed marks for mammography alone or with AI to confirm lesion identification. The reference standard was histologic examination and 1-year follow-up data. The cancer detection rate (CDR) per 1000 screening examinations, sensitivity, specificity, and abnormal interpretation rate (AIR) of mammography alone, mammography with AI, and mammography plus US were compared. Results Among 5707 asymptomatic women (mean age, 52.4 years ± 7.9 [SD]), 33 (0.6%) had cancer (median lesion size, 0.7 cm). Mammography with AI had a higher specificity (95.3% [95% CI: 94.7, 95.8], = .003) and lower AIR (5.0% [95% CI: 4.5, 5.6], = .004) than mammography alone (94.3% [95% CI: 93.6, 94.8] and 6.0% [95% CI: 5.4, 6.7], respectively). Mammography plus US had a higher CDR (5.6 vs 3.5 per 1000 examinations, = .002) and sensitivity (97.0% vs 60.6%, = .002) but lower specificity (77.6% vs 95.3%, < .001) and higher AIR (22.9% vs 5.0%, < .001) than mammography with AI. Supplemental US alone helped detect 12 cancers, mostly stage 0 and I (92%, 11 of 12). Conclusion Although AI improved the specificity of mammography interpretation, mammography plus supplemental US helped detect more node-negative early breast cancers that were undetected using mammography with AI. © RSNA, 2024 See also the editorial by Whitman and Destounis in this issue.

摘要

背景人工智能（AI）与乳房超声在致密型乳腺筛查中的对比表现尚不清楚。目的比较单独行乳腺 X 线摄影、乳腺 X 线摄影联合 AI 以及乳腺 X 线摄影联合补充性全乳手持超声在筛查致密型乳腺女性中的表现，并探讨所检出癌症的特征。材料与方法回顾性数据库检索了 2017 年 1 月至 2018 年 12 月在一家初级保健中心接受乳腺 X 线摄影加补充性全乳手持超声检查的连续无症状（≥40 岁）致密型乳腺女性。5 名乳腺放射科医师分别对单独行乳腺 X 线摄影和乳腺 X 线摄影联合 AI 系统进行了连续读片，并记录了其召回决策。从数据库中收集了联合乳腺 X 线摄影和超声检查的结果。一名专门的乳腺放射科医师审查了单独行乳腺 X 线摄影或 AI 联合乳腺 X 线摄影的标记，以确认病变识别。参考标准为组织学检查和 1 年随访数据。比较了单独行乳腺 X 线摄影、乳腺 X 线摄影联合 AI 以及乳腺 X 线摄影联合超声的每 1000 例筛查检查的癌症检出率（CDR）、敏感度、特异度和异常解读率（AIR）。结果在 5707 名无症状女性（平均年龄 52.4 岁±7.9[标准差]）中，有 33 名（0.6%）患有癌症（中位病变大小 0.7 cm）。乳腺 X 线摄影联合 AI 的特异度（95.3%[95%CI：94.7，95.8]）高于单独行乳腺 X 线摄影（94.3%[95%CI：93.6，94.8]），AIR（5.0%[95%CI：4.5，5.6]）低于单独行乳腺 X 线摄影（6.0%[95%CI：5.4，6.7]），差异均有统计学意义（均＜.001）。乳腺 X 线摄影联合超声的 CDR（5.6 比 3.5/1000 次检查， =.002）和敏感度（97.0%比 60.6%， =.002）高于乳腺 X 线摄影联合 AI，但特异度（77.6%比 95.3%，＜.001）和 AIR（22.9%比 5.0%，＜.001）高于乳腺 X 线摄影联合 AI。单独进行超声检查有助于检出 12 例癌症，这些癌症大多为 0 期和 I 期（92%，11/12）。结论尽管 AI 提高了乳腺 X 线摄影解读的特异度，但乳腺 X 线摄影联合补充性全乳手持超声有助于检出更多使用乳腺 X 线摄影联合 AI 无法检出的无淋巴结转移的早期乳腺癌。©RSNA，2024 参见本期 Whitman 和 Destounis 的述评。