Department of Radiology, State University of New York, Stony Brook, NY 11794, USA.
Acad Radiol. 2011 Aug;18(8):1024-34. doi: 10.1016/j.acra.2011.03.012. Epub 2011 Jun 11.
Current schemes for computer-aided detection (CAD) of colon polyps usually use kernel methods to perform curvature-based shape analysis. However, kernel methods may deliver spurious curvature estimations if the kernel contains two surfaces, because of the vanished gradient magnitudes. The aim of this study was to use the Knutsson mapping method to deal with the difficulty of providing better curvature estimations and to assess the impact of improved curvature estimation on the performance of CAD schemes.
The new method was compared to two widely used kernel methods in terms of the performance of two stages of CAD: initial detection and true-positive and false-positive classification. The evaluation was conducted on a database of 130 computed tomographic scans from 67 patients. In these patient scans, there were 104 clinically significant polyps and masses >5 mm.
In the initial detection stage, the detection sensitivity of the three methods was comparable. In the classification stage, at a 90% sensitivity level on the basis of the input of this step, the new technique yielded 3.15 false-positive results per scan, demonstrating reductions in false-positive findings of 30.2% (P < .01) and 27.9% (P < .01) compared to the two kernel methods.
The new method can benefit CAD schemes with reduced false-positive rates, without sacrificing detection sensitivity.
目前用于结肠息肉计算机辅助检测 (CAD) 的方案通常使用核方法来进行基于曲率的形状分析。然而，如果核中包含两个曲面，由于梯度幅度的消失，核方法可能会给出虚假的曲率估计。本研究的目的是使用 Knutsson 映射方法来解决提供更好的曲率估计的困难，并评估改进的曲率估计对 CAD 方案性能的影响。
新方法在 CAD 的两个阶段（初始检测和真阳性与假阳性分类）的性能方面与两种广泛使用的核方法进行了比较。评估是在来自 67 名患者的 130 个计算机断层扫描的数据库上进行的。在这些患者扫描中，有 104 个临床上有意义的息肉和>5 毫米的肿块。
在初始检测阶段，三种方法的检测灵敏度相当。在分类阶段，在基于此步骤输入的 90%灵敏度水平下，新技术每扫描产生 3.15 个假阳性结果，与两种核方法相比，假阳性发现减少了 30.2%（P <.01）和 27.9%（P <.01）。
新方法可以在不牺牲检测灵敏度的情况下，使 CAD 方案的假阳性率降低。
