Department of Radiology and Nuclear Medicine, Radboud University Medical Center, PO Box 9101, 6500 HB, Nijmegen, The Netherlands.
ScreenPoint Medical BV, Stationplein 26, 6512 AB, Nijmegen, The Netherlands.
Eur Radiol. 2019 Sep;29(9):4825-4832. doi: 10.1007/s00330-019-06186-9. Epub 2019 Apr 16.
To study the feasibility of automatically identifying normal digital mammography (DM) exams with artificial intelligence (AI) to reduce the breast cancer screening reading workload.
A total of 2652 DM exams (653 cancer) and interpretations by 101 radiologists were gathered from nine previously performed multi-reader multi-case receiver operating characteristic (MRMC ROC) studies. An AI system was used to obtain a score between 1 and 10 for each exam, representing the likelihood of cancer present. Using all AI scores between 1 and 9 as possible thresholds, the exams were divided into groups of low- and high likelihood of cancer present. It was assumed that, under the pre-selection scenario, only the high-likelihood group would be read by radiologists, while all low-likelihood exams would be reported as normal. The area under the reader-averaged ROC curve (AUC) was calculated for the original evaluations and for the pre-selection scenarios and compared using a non-inferiority hypothesis.
Setting the low/high-likelihood threshold at an AI score of 5 (high likelihood > 5) results in a trade-off of approximately halving (- 47%) the workload to be read by radiologists while excluding 7% of true-positive exams. Using an AI score of 2 as threshold yields a workload reduction of 17% while only excluding 1% of true-positive exams. Pre-selection did not change the average AUC of radiologists (inferior 95% CI > - 0.05) for any threshold except at the extreme AI score of 9.
It is possible to automatically pre-select exams using AI to significantly reduce the breast cancer screening reading workload.
• There is potential to use artificial intelligence to automatically reduce the breast cancer screening reading workload by excluding exams with a low likelihood of cancer. • The exclusion of exams with the lowest likelihood of cancer in screening might not change radiologists' breast cancer detection performance. • When excluding exams with the lowest likelihood of cancer, the decrease in true-positive recalls would be balanced by a simultaneous reduction in false-positive recalls.
研究使用人工智能（AI）自动识别正常数字乳腺 X 线摄影（DM）检查的可行性，以减少乳腺癌筛查的阅读工作量。
从之前进行的九项多读者多病例受试者工作特征（MRMC ROC）研究中收集了 2652 例 DM 检查（653 例癌症）和 101 名放射科医生的解释。使用 AI 系统为每例检查获得 1 到 10 之间的分数，代表存在癌症的可能性。使用 1 到 9 之间的所有 AI 分数作为可能的阈值，将检查分为癌症存在低概率和高概率组。假设在预选方案下，只有高概率组的检查将由放射科医生阅读，而所有低概率的检查将报告为正常。计算读者平均 ROC 曲线下面积（AUC）的原始评估和预选方案，并使用非劣效性假设进行比较。
将低/高概率阈值设置为 AI 评分 5（高概率>5），则放射科医生的阅读工作量减少约一半（-47%），同时排除了 7%的真阳性检查。使用 AI 评分 2 作为阈值，工作量减少 17%，同时仅排除 1%的真阳性检查。除了 AI 评分极端为 9 之外，预选方案没有改变任何阈值下放射科医生的平均 AUC（低于 95%置信区间的下限> -0.05）。
使用 AI 自动预选检查可以显著减少乳腺癌筛查的阅读工作量。
• 使用人工智能自动减少乳腺癌筛查阅读工作量是可能的，通过排除癌症可能性低的检查。• 在筛查中排除癌症可能性最低的检查可能不会改变放射科医生的乳腺癌检测性能。• 当排除癌症可能性最低的检查时，真阳性召回的减少将与假阳性召回的同时减少相平衡。
Zotero 插件
