Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees.

Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study.

[1]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[2]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[3]  G Reibnegger,et al.  Neural networks as a tool for utilizing laboratory information: comparison with linear discriminant analysis and with classification and regression trees. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Alexis Gourdon,et al.  Computing the Differential Characteristics of Isointensity Surfaces , 1995, Comput. Vis. Image Underst..

[5]  Olivier Monga,et al.  Using Partial Derivatives of 3D Images to Extract Typical Surface Features , 1995, Comput. Vis. Image Underst..

[6]  R. Tibshirani,et al.  Improvements on Cross-Validation: The 632+ Bootstrap Method , 1997 .

[7]  L. Breiman Arcing classifier (with discussion and a rejoinder by the author) , 1998 .

[8]  G Reibnegger,et al.  Artificial Neural Networks in Laboratory Medicine and Medical Outcome Prediction , 1999, Clinical chemistry and laboratory medicine.

[9]  K. Doi,et al.  Computer-aided diagnosis in radiology: potential and pitfalls. , 1999, European journal of radiology.

[10]  R. Jeffrey,et al.  Automated polyp detector for CT colonography: feasibility study. , 2000, Radiology.

[11]  J G Fletcher,et al.  Optimization of CT colonography technique: prospective trial in 180 patients. , 2000, Radiology.

[12]  W Luboldt,et al.  Computed tomographic and magnetic resonance colonography: summary of progress from 1995 to 2000. , 2001, Current problems in diagnostic radiology.

[13]  Carey E. Floyd,et al.  Initial development of a computer-aided diagnosis tool for solitary pulmonary nodules , 2001, SPIE Medical Imaging.

[14]  Hiroyuki Yoshida,et al.  Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps , 2001, IEEE Transactions on Medical Imaging.

[15]  J. Malley,et al.  Colonic polyps: complementary role of computer-aided detection in CT colonography. , 2002, Radiology.