文献速递乳腺乳腺X线

人工智能增强乳腺X线摄影联合数字乳腺断层合成用于乳腺癌检测:临床价值及与放射科医生表现的比较

AI-enhanced Mammography With Digital Breast Tomosynthesis for Breast Cancer Detection: Clinical Value and Comparison With Human Performance.
PubMed 文献 · Radiol Imaging Cancer · 2024-01-01

本回顾性研究纳入419例接受乳腺X线摄影联合数字乳腺断层合成的无症状女性,其中58例经组织学证实为乳腺癌,比较两款深度学习人工智能系统(Transpara 1.7.0与ProFound AI 3.0)与放射科医生双读的诊断性能。Transpara、ProFound AI及人工双读的AUC分别为0.86、0.93和0.98,两款AI系统均表现出较高的乳腺癌检测性能,但低于人工双读。

要点

  • 两款AI系统检测乳腺癌的AUC分别为0.86(Transpara)和0.93(ProFound AI),人工双读为0.98。
  • Transpara评分≤7排除恶性标准的敏感度为100.0%、特异度为60.9%。
  • ProFound AI评分<51排除恶性标准的敏感度为100%、特异度为67.0%。

核心结论

  • 两款AI系统在乳腺癌检测中均表现出较高性能,但与人工双读相比性能较低。

研究设计与样本

  • 回顾性研究,纳入2019年至2020年连续接受乳腺X线摄影联合数字乳腺断层合成的无症状女性419例(中位年龄60岁,IQR 52-70岁),其中58例经组织学证实为乳腺癌。
  • 采用两款深度学习人工智能系统Transpara 1.7.0与ProFound AI 3.0评估数字乳腺断层合成检查,以人工双读获得的BI-RADS结果为对照,采用DeLong检验进行比较。

诊断标准与关键数值

  • 检测恶性肿瘤的AUC:Transpara为0.86(95%CI:0.85,0.91),ProFound AI为0.93(95%CI:0.90,0.95),人工双读为0.98(95%CI:0.96,0.99)。
  • Transpara排除恶性标准(评分≤7分):敏感度100%(95%CI:94.2,100.0),特异度60.9%(95%CI:55.7,66.0)。
  • Transpara纳入恶性标准(评分>9分):敏感度96.6%(95%CI:88.1,99.6),特异度78.1%(95%CI:73.8,82.5)。
  • ProFound AI排除恶性标准(评分<51分):敏感度100%(95%CI:93.8,100),特异度67.0%(95%CI:62.2,72.1)。
  • ProFound AI纳入恶性标准(评分>69分):敏感度93.1%(95%CI:83.3,98.1),特异度82.0%(95%CI:77.9,86.1)。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Purpose To compare two deep learning-based commercially available artificial intelligence (AI) systems for mammography with digital breast tomosynthesis (DBT) and benchmark them against the performance of radiologists. Materials and Methods This retrospective study included consecutive asymptomatic patients who underwent mammography with DBT (2019-2020). Two AI systems (Transpara 1.7.0 and ProFound AI 3.0) were used to evaluate the DBT examinations. The systems were compared using receiver operating characteristic (ROC) analysis to calculate the area under the ROC curve (AUC) for detecting malignancy overall and within subgroups based on mammographic breast density. Breast Imaging Reporting and Data System results obtained from standard-of-care human double-reading were compared against AI results with use of the DeLong test. Results Of 419 female patients (median age, 60 years [IQR, 52-70 years]) included, 58 had histologically proven breast cancer. The AUC was 0.86 (95% CI: 0.85, 0.91), 0.93 (95% CI: 0.90, 0.95), and 0.98 (95% CI: 0.96, 0.99) for Transpara, ProFound AI, and human double-reading, respectively. For Transpara, a rule-out criterion of score 7 or lower yielded 100% (95% CI: 94.2, 100.0) sensitivity and 60.9% (95% CI: 55.7, 66.0) specificity. The rule-in criterion of higher than score 9 yielded 96.6% sensitivity (95% CI: 88.1, 99.6) and 78.1% specificity (95% CI: 73.8, 82.5). For ProFound AI, a rule-out criterion of lower than score 51 yielded 100% sensitivity (95% CI: 93.8, 100) and 67.0% specificity (95% CI: 62.2, 72.1). The rule-in criterion of higher than score 69 yielded 93.1% (95% CI: 83.3, 98.1) sensitivity and 82.0% (95% CI: 77.9, 86.1) specificity. Conclusion Both AI systems showed high performance in breast cancer detection but lower performance compared with human double-reading. Keywords: Mammography, Breast, Oncology, Artificial Intelligence, Deep Learning, Digital Breast Tomosynthesis © RSNA, 2024.

来源:Radiol Imaging Cancer,查看原文。版权归原作者所有。

引用

  1. Resch D, Lo Gullo R, Teuwen J, et al. AI-enhanced Mammography With Digital Breast Tomosynthesis for Breast Cancer Detection: Clinical Value and Comparison With Human Performance. Radiol Imaging Cancer. 2024. PMID: 38995172. doi:10.1148/rycan.230149

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。