Comparative performance of state-of-the-art classifiers in computer-aided detection for CT colonography

Authors:
Sang Ho Lee;Janne J. Näppi;Hiroyuki Yoshida
Affiliations:
3D Imaging Research, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts;3D Imaging Research, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts;3D Imaging Research, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
Venue:
MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications
Year:
2012

Citing 5
Cited 0

Advances in kernel methods: support vector learning

Advances in kernel methods: support vector learning
PCA versus LDA

IEEE Transactions on Pattern Analysis and Machine Intelligence
Random Forests

Machine Learning
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Ensemble detection of colorectal lesions for CT colonography

MICCAI'11 Proceedings of the Third international conference on Abdominal Imaging: computational and Clinical Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Several effective machine learning and pattern recognition schemes have been developed for medical imaging. Although many classifiers have been used with computer-aided detection (CAD) for computed tomographic colonography (CTC), little is known about their relative performance. This pilot study compares the performance of several state-of-the-art classifiers and feature selection methods in the classification of lesion candidates detected by CAD in CTC. There were four classifiers: linear discriminant analysis (LDA), radial basis function support vector machine (RBF-SVM), random forests (RF), and gradient boosting machine (GBM). There were five feature selection methods: sequential forward inclusion (SFI) of principal components (PCs), univariate filtering (UF), UF of PCs, recursive feature elimination (RFE), and RFE of PCs. A strategy of using all available features was tested also. For evaluation, 232,211 detections by a CAD system on 1,211 patients were subsampled randomly to create 10 different populations of 500 true-positive (TP) and 500 false-positive (FP) detections. The classifier performance was evaluated by use of the area under the receiver operating characteristic curve of 3 repeated 10-fold cross-validations. According to the result, the discrimination performance of the RBF-SVM classifier with feature selection by the RFE of PCs compared favorably with other methods, although no single classifier outperformed other classifiers under all conditions and feature selection schemes.