Surface Normal Overlap: A Computer-Aided Detection Algorithm With Application to Colonic Polyps and Lung Nodules in Helical CT

Abstract

We developed a novel computer-aided detection (CAD) algorithm called the surface normal overlap method that we applied to colonic polyp detection and lung nodule detection in helical computed tomography (CT) images. We demonstrate some of the theoretical aspects of this algorithm using a statistical shape model. The algorithm was then optimized on simulated CT data and evaluated using a per-lesion cross-validation on 8 CT colonography datasets and on 8 chest CT datasets. It is able to achieve 100% sensitivity for colonic polyps 10 mm and larger at 7.0 false positives (FPs)/dataset and 90% sensitivity for solid lung nodules 6 mm and larger at 5.6 FP/dataset.

Computerized Detection of Lung Nodules in Thin-Section CT Images by Use of Selective Enhancement Filters and an Automated Rule-Based Classifier

“…CAD schemes for lung nodule detection in thin-section CT images have been developed by some investigators [14][15][16][17][18][19][20][21][22]. A major disadvantage of some current CAD schemes is the use of a relatively small database.…”

“…We believe that comparison of our CAD scheme with these CAD schemes is inappropriate. In the remaining two studies, Paik et al [20] used a leave-one-out method to evaluate the performance levels of their CAD scheme based on a database of 8 CT scans with an unknown number of solid nodules, and they achieved a sensitivity of 80% with 1.3 false positives per scan or a sensitivity of 90% with 5.6 false positives per scan; McCulloch et al [19] used a cross-validation method to evaluate the performance levels of their CAD scheme based on a database of 50 CT scans with 43 nodules (35 solid and 8 GGO nodules), and they achieved a sensitivity of 70% with 8.3 false positives per scan. In this study, we employed a cross-validation method to evaluate the performance levels of our CAD scheme based on a database of 117 CT scans with 153 nodules (101 solid and 52 GGO nodules), and we achieved a sensitivity of 81% with 3.3 false positive per scan, or a sensitivity of 86% with 6.6 false positive per scan.…”

“…Since 2001, some investigators have reported their efforts in the development of CAD schemes for lung nodule detection in thin-section CT images [14][15][16][17][18][19][20][21][22]. Because the section thickness in thin-section CT is small, three-dimensional (3D) image processing and analysis techniques become applicable.…”

Automatic 3D pulmonary nodule detection in CT images: A survey

“…The radiologist may also suffer interference factors such as fatigue, Authors Computational technique(s) Choi and Choi [24], Santos et al [4], Chen et al [27] and Li and Doi [80] Hessian matrix based method El-Baz et al [22] and Le et al [81] Genetic algorithm template matching Cascio et al [26] Stable 3D mass-spring models Soltaninejad, Keshani and Tajeripour [28] k-Nearest Neighbors (k-NN) classifier and active contour Suiyuan and Junfeng [29] Thresholding Awai et al [82] Sieve filter Tanino et al [83] Variable n-quoit filter Riccardi et al [30] 3D fast radial transform Namin et al [32] and Murphy et al [84] Shape index Ozekes, Osman and Ucan [38] 3D template matching Ge et al [45] Adaptive weighted k-means clustering Yamada et al [85] and Kanazawa et al [86] Fuzzy clustering Mekada et al [51] Maximum distance inside a connected component Mao et al [87] Fragmentary window filtering Mendonça et al [88] Curvature tensor Paik et al [89] Statistical shape model Agam and Armato [90] Correlation-based enhancement filters Wang et al [25] and Armato III et al [91] Multiple gray-level thresholding Saita et al [92] 3D labeling method subjectivity of the analysis, images acquired with improper configuration of the equipment and noise. A detailed analysis of the LIDC-IDRI database can help us understand the difficulties encountered during this task.…”

Development of a synthetic phantom for the selection of optimal scanning parameters in CAD–CT colonography

“…Since its introduction by Vining et al. [11] in 1994, CTC has received extensive attention from research community and many publications have emerged in areas of 3D surface rendering and visualization [15][16][17], centerline calculation [18], colon unfolding [19] and automated polyp detection [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34]. Recent publications [22,23,35] indicate that the results returned by the automatic CAD-CTC polyp detection systems in the vast majority of cases closely match or even outperform the human reader performance.…”