Premium
Lung nodule detection on thoracic computed tomography images: Preliminary evaluation of a computer‐aided diagnosis system
Author(s) -
Gurcan Metin N.,
Sahiner Berkman,
Petrick Nicholas,
Chan HeangPing,
Kazerooni Ella A.,
Cascade Philip N.,
Hadjiiski Lubomir
Publication year - 2002
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.1515762
Subject(s) - receiver operating characteristic , computer aided diagnosis , cad , lung , nodule (geology) , linear discriminant analysis , tomography , artificial intelligence , pattern recognition (psychology) , computer science , cluster analysis , radiology , computed tomography , nuclear medicine , medicine , machine learning , paleontology , engineering drawing , engineering , biology
We are developing a computer‐aided diagnosis (CAD) system for lung nodule detection on thoracic helical computed tomography (CT) images. In the first stage of this CAD system, lung regions are identified by a k ‐means clustering technique. Each lung slice is classified as belonging to the upper, middle, or the lower part of the lung volume. Within each lung region, structures are segmented again using weighted k ‐means clustering. These structures may include true lung nodules and normal structures consisting mainly of blood vessels. Rule‐based classifiers are designed to distinguish nodules and normal structures using 2D and 3D features. After rule‐based classification, linear discriminant analysis (LDA) is used to further reduce the number of false positive (FP) objects. We performed a preliminary study using 1454 CT slices from 34 patients with 63 lung nodules. When only LDA classification was applied to the segmented objects, the sensitivity was 84% (53/63) with 5.48 (7961/1454) FP objects per slice. When rule‐based classification was used before LDA, the free response receiver operating characteristic (FROC) curve improved over the entire sensitivity and specificity ranges of interest. In particular, the FP rate decreased to 1.74 (2530/1454) objects per slice at the same sensitivity. Thus, compared to FP reduction with LDA alone, the inclusion of rule‐based classification lead to an improvement in detection accuracy for the CAD system. These preliminary results demonstrate the feasibility of our approach to lung nodule detection and FP reduction on CT images.