Department of Radiology, The University of Chicago, Chicago, IL 60637, USA.
IEEE Trans Med Imaging. 2010 Nov;29(11):1907-17. doi: 10.1109/TMI.2010.2053213. Epub 2010 Jun 21.
A major challenge in the current computer-aided detection (CAD) of polyps in CT colonography (CTC) is to reduce the number of false-positive (FP) detections while maintaining a high sensitivity level. A pattern-recognition technique based on the use of an artificial neural network (ANN) as a filter, which is called a massive-training ANN (MTANN), has been developed recently for this purpose. The MTANN is trained with a massive number of subvolumes extracted from input volumes together with the teaching volumes containing the distribution for the "likelihood of being a polyp;" hence the term "massive training." Because of the large number of subvolumes and the high dimensionality of voxels in each input subvolume, the training of an MTANN is time-consuming. In order to solve this time issue and make an MTANN work more efficiently, we propose here a dimension reduction method for an MTANN by using Laplacian eigenfunctions (LAPs), denoted as LAP-MTANN. Instead of input voxels, the LAP-MTANN uses the dependence structures of input voxels to compute the selected LAPs of the input voxels from each input subvolume and thus reduces the dimensions of the input vector to the MTANN. Our database consisted of 246 CTC datasets obtained from 123 patients, each of whom was scanned in both supine and prone positions. Seventeen patients had 29 polyps, 15 of which were 5-9 mm and 14 were 10-25 mm in size. We divided our database into a training set and a test set. The training set included 10 polyps in 10 patients and 20 negative patients. The test set had 93 patients including 19 polyps in seven patients and 86 negative patients. To investigate the basic properties of a LAP-MTANN, we trained the LAP-MTANN with actual polyps and a single source of FPs, which were rectal tubes. We applied the trained LAP-MTANN to simulated polyps and rectal tubes. The results showed that the performance of LAP-MTANNs with 20 LAPs was advantageous over that of the original MTANN with 171 inputs. To test the feasibility of the LAP-MTANN, we compared the LAP-MTANN with the original MTANN in the distinction between actual polyps and various types of FPs. The original MTANN yielded a 95% (18/19) by-polyp sensitivity at an FP rate of 3.6 (338/93) per patient, whereas the LAP-MTANN achieved a comparable performance, i.e., an FP rate of 3.9 (367/93) per patient at the same sensitivity level. With the use of the dimension reduction architecture, the time required for training was reduced from 38 h to 4 h. The classification performance in terms of the area under the receiver-operating-characteristic curve of the LAP-MTANN (0.84) was slightly higher than that of the original MTANN (0.82) with no statistically significant difference (p-value =0.48).
在 CT 结肠成像（CTC）中，当前计算机辅助检测（CAD）的一个主要挑战是在保持高灵敏度水平的同时减少假阳性（FP）检测的数量。最近，为了解决这个问题，已经开发出一种基于使用人工神经网络（ANN）作为滤波器的模式识别技术，称为大规模训练 ANN（MTANN）。MTANN 是通过与包含“可能是息肉的可能性”分布的教学卷一起从输入卷中提取大量子体积进行训练的；因此称为“大规模训练”。由于子体积的数量很大，并且每个输入子体积中的体素的维度很高，因此 MTANN 的训练非常耗时。为了解决这个时间问题并使 MTANN 更有效地工作，我们在这里提出了一种使用拉普拉斯特征函数（LAPs）对 MTANN 进行降维的方法，称为 LAP-MTANN。LAP-MTANN 不是使用输入体素，而是使用输入体素的依赖结构，从每个输入子体积中计算输入体素的选定 LAP，从而将输入向量的维度降低到 MTANN。我们的数据库由 123 名患者的 246 个 CTC 数据集组成，每位患者均进行仰卧位和俯卧位扫描。17 名患者有 29 个息肉，其中 15 个大小为 5-9 毫米，14 个大小为 10-25 毫米。我们将数据库分为训练集和测试集。训练集包括 10 名患者中的 10 个息肉和 20 个阴性患者。测试集包括 93 名患者，其中 7 名患者中有 19 个息肉和 86 个阴性患者。为了研究 LAP-MTANN 的基本特性，我们使用实际息肉和单一来源的 FP（直肠管）对 LAP-MTANN 进行了训练。我们将经过训练的 LAP-MTANN 应用于模拟息肉和直肠管。结果表明，使用 20 个 LAP 的 LAP-MTANN 的性能优于具有 171 个输入的原始 MTANN。为了测试 LAP-MTANN 的可行性，我们比较了 LAP-MTANN 和原始 MTANN 在实际息肉与各种类型 FP 之间的区别。原始的 MTANN 在每位患者的 FP 率为 3.6（338/93）时达到 95%（18/19）的息肉灵敏度，而 LAP-MTANN 则在相同的灵敏度水平下达到了可比的性能，即每位患者的 FP 率为 3.9（367/93）。通过使用降维架构，训练所需的时间从 38 小时减少到 4 小时。LAP-MTANN 的接收器工作特性曲线下面积的分类性能（0.84）略高于原始 MTANN（0.82），但无统计学差异（p 值=0.48）。
