Jian-Wu Xu

Massive-Training Artificial Neural Network Coupled With Laplacian-Eigenfunction-Based Dimensionality Reduction for Computer-Aided Detection of Polyps in CT Colonography

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).

Computer-aided detection of hepatocellular carcinoma in hepatic CT: False positive reduction with feature selection

This study presents a computer-aided detection (CADe) system of hepatocellular carcinoma (HCC) using sequential forward floating selection (SFFS) method with linear discriminant analysis (LDA). We extracted morphologic and texture features from the segmented HCC candidate regions from the arterial phase (AP) images of the contrast-enhanced hepatic CT images. To select the most discriminatory features for classification, we developed an SFFS method directly coupled with LDA that maximizes the area under the receiver-operating-characteristic curve (AUC) value. The maximal AUC value criterion directly reflects the CADe system performance used in clinical practice. The initial CADe before the classification achieved a 100% (23/23) sensitivity with 33.7 (775/23) false positives (FPs) per patient. The maximal AUC SFFS method for LDA with eleven selected features eliminated 48.0% (372/775) of the FPs without any removal of the HCCs in a leave-one-lesion-out cross-validation test; thus, a 95.6% sensitivity with 7.9 FPs per patient was achieved.

Computer-aided detection of hepatocellular carcinoma in multiphase contrast-enhanced hepatic CT: a preliminary study

Malignant liver tumors such as hepatocellular carcinoma (HCC) account for 1.25 million deaths each year worldwide. Early detection of HCC is sometimes difficult on CT images because the attenuation of HCC is often similar to that of normal liver parenchyma. Our purpose was to develop computer-aided detection (CADe) of HCC using both arterial phase (AP) and portal-venous phase (PVP) of contrast-enhanced CT images. Our scheme consisted of liver segmentation, tumor candidate detection, feature extraction and selection, and classification of the candidates as HCC or non-lesions. We used a 3D geodesic-active-contour model coupled with a level-set algorithm to segment the liver. Both hyper- and hypo-dense tumors were enhanced by a sigmoid filter. A gradient-magnitude filter followed by a watershed algorithm was applied to the tumor-enhanced images for segmenting closed-contour regions as HCC candidates. Seventy-five morphologic and texture features were extracted from the segmented candidate regions in both AP and PVP images. To select most discriminant features for classification, we developed a sequential forward floating feature selection method directly coupled with a support vector machine (SVM) classifier. The initial CADe before the classification achieved a 100% (23/23) sensitivity with 33.7 (775/23) false positives (FPs) per patient. The SVM with four selected features removed 96.5% (748/775) of the FPs without any removal of the HCCs in a leave-one-lesion-out cross-validation test; thus, a 100% sensitivity with 1.2 FPs per patient was achieved, whereas CADe using AP alone produced 6.4 (147/23) FPs per patient at the same sensitivity level.

Computer-aided detection of polyps in CT colonography by means of AdaBoost

Computer-aided detection (CADe) has been investigated for assisting radiologists in detecting polyps in CT colonography (CTC). One of the major challenges in current CADe of polyps in CTC is to improve the specificity without sacrificing the sensitivity. We have developed several CADe schemes based on a massive-training framework with different nonlinear regression models such as neural network regression, support vector regression, and Gaussian process regression. Individual CADe schemes based on different nonlinear regression models, however, achieved comparable results. In this paper, we propose to use the AdaBoost algorithm to combine different regression models in CADe schemes for improving the specificity without sacrificing the sensitivity. To test the performance of the proposed approach, we compared it with individual regression models in the distinction between polyps and various types of false positives (FPs). Our CTC database consisted of 246 CTC datasets obtained from 123 patients in the supine and prone positions. The testing set contained 93 patients including 19 polyps in seven patients and 86 negative patients with 474 FPs produced by an original CADe scheme. The AdaBoost algorithm combining multiple massive-training regression models achieved a performance that was higher than each individual regression model, yielding a 94.7% (18/19) bypolyp sensitivity at an FP rate of 2.0 (188/93) per patient in a leave-one-lesion-out cross validation test.

Computer-aided detection of polyps in CT colonography with pixel-based machine learning techniques

Pixel/voxel-based machine-learning techniques have been developed for classification between polyp regions of interest (ROIs) and non-polyp ROIs in computer-aided detection (CADe) of polyps in CT colonography (CTC). Although 2D/3D ROIs can be high-dimensional, they may reside in a lower dimensional manifold. We investigated the manifold structure of 2D CTC ROIs by use of the Laplacian eigenmaps technique. We compared a support vector machine (SVM) classifier with the Laplacian eigenmaps-based dimensionality-reduced ROIs with massive-training support vector regression (MTSVR) in reduction of false positive (FP) detections. The Laplacian eigenmaps-based SVM classifier removed 16.0% (78/489) of FPs without any loss of polyps in a leave-one-lesion-out cross-validation test, whereas the MTSVR removed 49.9% (244/489); thus, yielded a 96.6% by-polyp sensitivity at an FP rate of 2.4 (254/106) per patient.