Department of Radiology, The University of Chicago, 5841 South Maryland Avenue, Chicago, Illinois 60637, USA.
Med Phys. 2010 Jan;37(1):12-21. doi: 10.1118/1.3263615.
The purpose of this study was to develop an advanced computer-aided detection (CAD) scheme utilizing massive-training artificial neural networks (MTANNs) to allow detection of "difficult" polyps in CT colonography (CTC) and to evaluate its performance on false-negative (FN) CTC cases that radiologists "missed" in a multicenter clinical trial.
The authors developed an advanced CAD scheme consisting of an initial polyp-detection scheme for identification of polyp candidates and a mixture of expert MTANNs for substantial reduction in false positives (FPs) while maintaining sensitivity. The initial polyp-detection scheme consisted of (1) colon segmentation based on anatomy-based extraction and colon-based analysis and (2) detection of polyp candidates based on a morphologic analysis on the segmented colon. The mixture of expert MTANNs consisted of (1) supervised enhancement of polyps and suppression of various types of nonpolyps, (2) a scoring scheme for converting output voxels into a score for each polyp candidate, and (3) combining scores from multiple MTANNs by the use of a mixing artificial neural network. For testing the advanced CAD scheme, they created a database containing 24 FN cases with 23 polyps (range of 6-15 mm; average of 8 mm) and a mass (35 mm), which were "missed" by radiologists in CTC in the original trial in which 15 institutions participated.
The initial polyp-detection scheme detected 63% (15/24) of the missed polyps with 21.0 (505/24) FPs per patient. The MTANNs removed 76% of the FPs with loss of one true positive; thus, the performance of the advanced CAD scheme was improved to a sensitivity of 58% (14/24) with 8.6 (207/24) FPs per patient, whereas a conventional CAD scheme yielded a sensitivity of 25% at the same FP rate (the difference was statistically significant).
With the advanced MTANN CAD scheme, 58% of the polyps missed by radiologists in the original trial were detected and with a reasonable number of FPs. The results suggest that the use of an advanced MTANN CAD scheme may potentially enhance the detection of "difficult" polyps.
本研究旨在开发一种利用大规模训练人工神经网络（MTANN）的先进计算机辅助检测（CAD）方案，以检测 CT 结肠成像（CTC）中的“困难”息肉，并评估其在多中心临床试验中放射科医生“遗漏”的假阴性（FN）CTC 病例中的性能。
作者开发了一种先进的 CAD 方案，该方案由一个初始的息肉检测方案组成，用于识别息肉候选物，以及一个专家 MTANN 的混合物，用于在保持灵敏度的同时大量减少假阳性（FP）。初始的息肉检测方案包括：（1）基于解剖学提取和基于结肠的分析的结肠分割；（2）基于分割结肠的形态分析检测息肉候选物。专家 MTANN 的混合物包括：（1）对息肉进行监督增强，对各种类型的非息肉进行抑制；（2）将输出体素转换为每个息肉候选物得分的评分方案；（3）使用混合人工神经网络组合来自多个 MTANN 的得分。为了测试先进的 CAD 方案，他们创建了一个数据库，其中包含 24 个 FN 病例，有 23 个息肉（范围为 6-15 毫米；平均 8 毫米）和一个肿块（35 毫米），这些息肉在最初的试验中被 15 个机构参与的 CTC 中的放射科医生“遗漏”。
初始的息肉检测方案检测到 63%（24 例中的 15 例）的遗漏息肉，每个患者有 21.0 个（24 例中的 505 个）FP。MTANN 去除了 76%的 FP，同时只丢失了一个真阳性；因此，先进的 CAD 方案的性能提高到了 58%（24 例中的 14 例），每个患者有 8.6 个 FP，而传统的 CAD 方案在相同的 FP 率下的灵敏度为 25%（差异具有统计学意义）。
利用先进的 MTANN CAD 方案，检测到了原始试验中放射科医生遗漏的 58%的息肉，且 FP 数量合理。结果表明，使用先进的 MTANN CAD 方案可能有助于提高“困难”息肉的检测率。
