Is there a safety-net effect with computer-aided detection (CAD)?

Is there a safety-net effect with computer-aided detection (CAD)?
复制标题

计算机辅助检测 (CAD) 是否具有安全网效应?

DOI:
10.1117/12.2512720
复制
发表时间:
2019
期刊:
--
影响因子:
--
通讯作者:
Hulleman J
Hulleman J
中科院分区:
--
文献类型:
--
作者:
Hulleman J

文献摘要

参考文献

相似文献

计算机辅助检测(CAD)系统用于帮助读者解释筛查乳房X线照片。一个专业的读者搜索图像最初独立,然后再次与CAD的帮助下,提示自动检测到可疑区域。这可能导致“安全网”效应,其中图像的初始无辅助搜索受到以下事实的不利影响,即它是使用CAD的附加搜索的预备,并且因此可能不太彻底。为了研究这种效应的存在,我们为非专家观察者创建了一个视觉搜索实验,以反映乳腺癌筛查与CAD。在提示和非提示(无CAD)条件下,每个观察者在合成图像中搜索100个图像以寻找微钙化簇。该研究招募了52名参与者,其中48人的眼球运动被实时跟踪; 4名参与者无法准确校准,因此只收集了行为数据。在CAD条件下,在显示提示之前,图像覆盖率显著低于非CAD条件下的覆盖率(t(47)=5.48,p<0.001)。观察者对CAD标记的靶点的敏感性显著高于非CAD条件下的相同靶点(t(51)=11.67,p<0.001)。对于未被CAD标记的靶,与无CAD条件下的相同靶相比,CAD条件下的观察者灵敏度没有显著差异(t(51)=0.88,p=0.382)。这些结果表明,最初的搜索可能会受到随后CAD可用性的影响;如果是这样,CAD疗效研究在估计获益时应考虑该影响。
Computer-Aided Detection (CAD) systems are used to aid readers interpreting screening mammograms. An expert reader searches the image initially unaided, and then once again with the aid of CAD which prompts automatically detected suspicious regions. This could lead to a ‘safety-net’ effect, where the initial unaided search of the image is adversely affected by the fact that it is preliminary to an additional search with CAD, and may, therefore, be less thorough. To investigate the existence of such an effect, we created a visual search experiment for non-expert observers mirroring breast screening with CAD. Each observer searched 100 images for microcalcification clusters within synthetic images in both prompted and unprompted (no-CAD) conditions. Fifty-two participants were recruited for the study, 48 of whom had their eye movements tracked in real-time; four participants could not be accurately calibrated so only behavioural data was collected. In the CAD condition, before prompts were displayed, image coverage was significantly lower than coverage in the no-CAD condition (t(47)=5.48, p<0.001). Observer sensitivity was significantly greater for targets marked by CAD than the same targets in the no-CAD condition (t(51)=11.67, p<0.001). For targets not marked by CAD, there was no significant difference in observer sensitivity in the CAD condition compared to the same targets in the no-CAD condition (t(51)=0.88, p=0.382). These results suggest that the initial search may be influenced by the subsequent availability of CAD; if so, CAD efficacy studies should account for the effect when estimating benefit.
DOI: 10.1007/s00330-010-1821-8
发表时间: 2010-10
期刊: European radiology
影响因子: 5.9
作者:
Samulski M;Hupse R;Boetes C;Mus RD;den Heeten GJ;Karssemeijer N
通讯作者: Karssemeijer N
在乳房 X 光检查期间建模视觉搜索
DOI: 10.1117/12.538063
发表时间: 2004
期刊: Radiology
影响因子: 19.7
作者:
H. Kundel;C. Nodine
通讯作者: C. Nodine
低流行度视觉搜索中的颜色和空间提示
DOI: 10.1080/17470218.2012.656662
发表时间: 2012
影响因子: 1.7
作者:
N. Russell;Melina A. Kunar
通讯作者: Melina A. Kunar
DOI: 10.1037/xap0000132
发表时间: 2017-12-01
影响因子: 2.6
作者:
Kunar, Melina A.;Watson, Derrick G.;Wolska, Julia
通讯作者: Wolska, Julia
计算机辅助检测评估方法并不相同。
DOI: 10.1148/radiol.2513081130
发表时间: 2009
期刊: Radiology
影响因子: 19.7
作者:
R. Nishikawa;Lorenzo L. Pesce
通讯作者: Lorenzo L. Pesce