Abstract:
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.
摘要:
目的将两种基于深度学习的商用人工智能(AI)系统与数字乳腺断层摄影(DBT)进行比较,并根据放射科医生的表现对其进行基准测试。材料与方法这项回顾性研究包括连续无症状的患者,这些患者接受了DBT的乳腺X线摄影(2019-2020)。使用两个AI系统(Transpara1.7.0和ProFoundAI3.0)来评估DBT检查。使用受试者工作特征(ROC)分析比较了这些系统,以计算ROC曲线下面积(AUC),以根据乳房X线摄影乳腺密度检测整体和亚组内的恶性肿瘤。使用DeLong测试将从护理标准人类双重阅读获得的乳腺成像报告和数据系统结果与AI结果进行了比较。结果419例女性患者(中位年龄,60年[IQR,52-70年])包括在内,58例经组织学证实患有乳腺癌。AUC为0.86(95%CI:0.85,0.91),0.93(95%CI:0.90,0.95),Transpara为0.98(95%CI:0.96,0.99),ProFoundAI,和人类双重阅读,分别。对于Transpara,评分7或更低的排除标准产生100%(95%CI:94.2,100.0)的敏感性和60.9%(95%CI:55.7,66.0)的特异性.高于9分的规则标准产生96.6%的灵敏度(95%CI:88.1,99.6)和78.1%的特异性(95%CI:73.8,82.5)。对于ProFoundAI,低于51分的排除标准产生100%的敏感性(95%CI:93.8,100)和67.0%的特异性(95%CI:62.2,72.1).高于69分的规则标准产生了93.1%(95%CI:83.3,98.1)的敏感性和82.0%(95%CI:77.9,86.1)的特异性。结论两种AI系统在乳腺癌检测中都表现出较高的性能,但与人类双读数相比性能较低。关键词:乳房X线照相术,乳房,肿瘤学,人工智能,深度学习,数字乳房断层合成©RSNA,2024.