Comprehensive Breast Health Center, Taipei Veterans General Hospital, No.201, Sec. 2, Shipai Rd., Beitou District, Taipei, 11217, Taiwan, ROC; School of Medicine, National Yang Ming Chiao Tung University, No.155, Sec. 2, Linong St., Beitou District, Taipei, 112304, Taiwan, ROC.
TaiHao Medical Inc., 6F.-1, No.100, Sec. 2, Heping E. Rd., Da'an District, Taipei, 10663, Taiwan, ROC.
Breast. 2022 Oct;65:124-135. doi: 10.1016/j.breast.2022.07.009. Epub 2022 Jul 18.
The purpose of this study was to compare the diagnostic performance and the interpretation time of breast ultrasound examination between reading without and with the artificial intelligence (AI) system as a concurrent reading aid.
A fully crossed multi-reader and multi-case (MRMC) reader study was conducted. Sixteen participating physicians were recruited and retrospectively interpreted 172 breast ultrasound cases in two reading scenarios, once without and once with the AI system (BU-CAD™, TaiHao Medical Inc.) assistance for concurrent reading. Interpretations of any given case set with and without the AI system were separated by at least 5 weeks. These reading results were compared to the reference standard and the area under the LROC curve (AUCLROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for performance evaluations. The interpretation time was also compared between the unaided and aided scenarios.
With the help of the AI system, the readers had higher diagnostic performance with an increase in the average AUCLROC from 0.7582 to 0.8294 with statistically significant. The sensitivity, specificity, PPV, and NPV were also improved from 95.77%, 24.07%, 44.18%, and 93.50%-98.17%, 30.67%, 46.91%, and 96.10%, respectively. Of these, the improvement in specificity reached statistical significance. The average interpretation time was significantly reduced by approximately 40% when the readers were assisted by the AI system.
The concurrent-read AI system improves the diagnostic performance in detecting and diagnosing breast lesions on breast ultrasound images. In addition, the interpretation time is effectively reduced for the interpreting physicians.
本研究旨在比较在人工智能（AI）系统作为辅助同时阅读的情况下，进行乳腺超声检查时的诊断性能和解读时间。
进行了一项完全交叉的多读者和多病例（MRMC）读者研究。招募了 16 名参与的医生，他们在两种阅读场景下回顾性地解读了 172 个乳腺超声病例，一次是没有 AI 系统（BU-CAD™，TaiHao Medical Inc.）辅助的情况下，一次是有 AI 系统辅助的情况下同时阅读。任何给定病例集的解读结果，无论是否使用 AI 系统，至少相隔 5 周。将这些阅读结果与参考标准进行比较，并计算曲线下面积（AUCLROC）、敏感度、特异度、阳性预测值（PPV）和阴性预测值（NPV）以进行性能评估。还比较了无辅助和辅助场景下的解读时间。
在 AI 系统的帮助下，读者的诊断性能提高，平均 AUCLROC 从 0.7582 增加到 0.8294，具有统计学意义。敏感度、特异度、PPV 和 NPV 也分别从 95.77%、24.07%、44.18%和 93.50%-98.17%、30.67%、46.91%和 96.10%提高到 98.17%、30.67%、46.91%和 96.10%。其中，特异度的提高具有统计学意义。当读者在 AI 系统的辅助下进行解读时，平均解读时间减少了约 40%。
同时阅读的 AI 系统提高了在乳腺超声图像上检测和诊断乳腺病变的诊断性能。此外，对解释医生来说，解释时间得到了有效减少。
