利用人工智能提高癌症检测率：对乳腺 X 光摄影术漏诊癌症的回顾性评估。
Improved Cancer Detection Using Artificial Intelligence: a Retrospective Evaluation of Missed Cancers on Mammography.
机构信息
Keck School of Medicine, University of Southern California, 1975 Zonal Avenue, Los Angeles, CA, 90033, USA.
Keck School of Medicine, University of Southern California, 2711 North Sepulveda Boulevard, Suite 284, Manhattan Beach, CA, 90266-2725, USA.
出版信息
J Digit Imaging. 2019 Aug;32(4):625-637. doi: 10.1007/s10278-019-00192-5.
To determine whether cmAssist™, an artificial intelligence-based computer-aided detection (AI-CAD) algorithm, can be used to improve radiologists' sensitivity in breast cancer screening and detection. A blinded retrospective study was performed with a panel of seven radiologists using a cancer-enriched data set from 122 patients that included 90 false-negative mammograms obtained up to 5.8 years prior to diagnosis and 32 BIRADS 1 and 2 patients with a 2-year follow-up of negative diagnosis. The mammograms were performed between February 7, 2008 (earliest) and January 8, 2016 (latest), and were all originally interpreted as negative in conjunction with R2 ImageChecker CAD, version 10.0. In this study, the readers analyzed the 122 studies before and after review of cmAssist™, an AI-CAD software for mammography. The statistical significance of our findings was evaluated using Student's t test and bootstrap statistical analysis. There was a substantial and significant improvement in radiologist accuracy with use of cmAssist, as demonstrated in the 7.2% increase in the area-under-the-curve (AUC) of the receiver operating characteristic (ROC) curve with two-sided p value < 0.01 for the reader group. All radiologists showed a significant improvement in their cancer detection rate (CDR) with the use of cmAssist (two-sided p value = 0.030, confidence interval = 95%). The readers detected between 25 and 71% (mean 51%) of the early cancers without assistance. With cmAssist, the overall reader CDR was 41 to 76% (mean 62%). The percentage increase in CDR for the reader panel was significant, ranging from 6 to 64% (mean 27%) with the use of cmAssist. There was less than 1% increase in the readers' false-positive recalls with use of cmAssist. With the use of cmAssist TM, there was a substantial and statistically significant improvement in radiologists' accuracy and sensitivity for detection of cancers that were originally missed. The percentage increase in CDR for the radiologists in the reader panel ranged from 6 to 64% (mean 27%) with the use of cmAssist, with negligible increase in false-positive recalls.
为了确定人工智能辅助检测（AI-CAD）算法 cmAssist 是否可以用于提高乳腺癌筛查和检测的放射科医生的敏感性，进行了一项盲法回顾性研究，该研究使用了一个由 7 名放射科医生组成的小组，该小组使用了一组从 122 名患者中获得的富含癌症的数据集，其中包括 90 例在诊断前 5.8 年内获得的假阴性乳房 X 线照片和 32 例 BI-RADS 1 和 2 患者，对这些患者进行了为期 2 年的阴性诊断随访。乳房 X 线照片的拍摄时间为 2008 年 2 月 7 日（最早）至 2016 年 1 月 8 日（最晚），所有这些均与 R2 ImageChecker CAD 版本 10.0 联合最初解释为阴性。在这项研究中，读者分析了在审查 cmAssist（用于乳房 X 线摄影的 AI-CAD 软件）之前和之后的 122 项研究。使用学生 t 检验和引导统计分析评估我们发现的统计显着性。使用 cmAssist 可显着提高放射科医生的准确性，这体现在接收器工作特征（ROC）曲线下面积（AUC）增加了 7.2％，双侧 p 值<0.01 ，适用于读者组。所有放射科医生的癌症检出率（CDR）均有显着提高（双侧 p 值= 0.030，置信区间= 95％）。使用 cmAssist 后，读者检测到 25％至 71％（平均 51％）的早期癌症。在没有 cmAssist 的情况下，总体读者 CDR 为 41％至 76％（平均 62％）。使用 cmAssist 后，读者小组的 CDR 百分比增加显着，范围为 6％至 64％（平均 27％）。使用 cmAssist 后，读者的假阳性召回率仅增加了不到 1％。使用 cmAssist TM，放射科医生对原始漏诊癌症的准确性和敏感性有了实质性和统计学上的提高。使用 cmAssist 后，读者小组中放射科医生的 CDR 百分比增加了 6％至 64％（平均 27％），假阳性召回率几乎没有增加。
Zotero 插件