Computer-aided detection (CAD) of lung nodules in CT scans: radiologist performance and reading time with incremental CAD assistance.
Computer-aided detection (CAD) of lung nodules in CT scans: radiologist performance and reading time with incremental CAD assistance.
复制标题
DOI：
10.1007/s00330-009-1596-y
复制
发表时间：
2010-03
影响因子：
5.9
通讯作者：
Rubin GD
中科院分区：
文献类型：
--
作者：
Roos JE;Paik D;Olsen D;Liu EG;Chow LC;Leung AN;Mindelzun R;Choudhury KR;Naidich DP;Napel S;Rubin GD
评估了放射科医生使用增量 CAD 辅助进行 CT 肺结节检测的诊断性能，以及他们在 CAD 评估期间性能的时间变化。 CAD 应用到 20 次胸部多排计算机断层扫描 (MDCT) 扫描，其中包含 190 个非钙化 ≥3 毫米结节。经过免费搜索后，三名放射科医生独立评估了每位患者最多 50 次 CAD 检测。通过将 CAD 检测逐渐添加到放射科医生的表现中，可以生成多条自由响应 ROC 曲线，用于自由搜索和连续 CAD 评估。在每名患者出现 1.15 个假阳性 (FP) 时，免费搜索的灵敏度为 53%（范围为 44%–59%），随着 CAD 的增加，灵敏度在每名患者出现 1.45 个 FP 时增加到 69%（范围为 59–82%）。 CAD 评估最初导致灵敏度急剧上升 14%，而 FP 在 100 秒的时间内增幅最小，随后灵敏度增幅趋平至仅 2%。这种转变是由于早期 CAD 评估中真阳性 (TP) 检测相对于 FP 检测更为普遍，而不是读者表现的暂时变化所致。 TP（9.5 s±4.5 s）和假阴性（FN）（8.4 s±6.7 s）检测所花费的时间相似； FP 决策所需时间 (14.4 s±8.7 s) 比真阴性 (TN) 决策 (4.7 s±1.3 s) 长两到三倍。当 CAD 输出按 CAD 分数排序时，由于 TP CAD 输出分布的不均匀性以及读取器性能随时间的变化，最初的快速性能改进会随着时间的推移而显着减慢。
The diagnostic performance of radiologists using incremental CAD assistance for lung nodule detection on CT and their temporal variation in performance during CAD evaluation was assessed. CAD was applied to 20 chest multidetector-row computed tomography (MDCT) scans containing 190 non-calcified ≥3-mm nodules. After free search, three radiologists independently evaluated a maximum of up to 50 CAD detections/patient. Multiple free-response ROC curves were generated for free search and successive CAD evaluation, by incrementally adding CAD detections one at a time to the radiologists’ performance. The sensitivity for free search was 53% (range, 44%–59%) at 1.15 false positives (FP)/patient and increased with CAD to 69% (range, 59–82%) at 1.45 FP/patient. CAD evaluation initially resulted in a sharp rise in sensitivity of 14%with a minimal increase in FP over a time period of 100 s, followed by flattening of the sensitivity increase to only 2%. This transition resulted from a greater prevalence of true positive (TP) versus FP detections at early CAD evaluation and not by a temporal change in readers’ performance. The time spent for TP (9.5 s±4.5 s) and false negative (FN) (8.4 s±6.7 s) detections was similar; FP decisions took two- to three-times longer (14.4 s±8.7 s) than true negative (TN) decisions (4.7 s±1.3 s). When CAD output is ordered by CAD score, an initial period of rapid performance improvement slows significantly over time because of non-uniformity in the distribution of TP CAD output and not to a changing reader performance over time.