Optimizing computer-aided colonic polyp detection for CT colonography by evolving the Pareto fronta.

A multiobjective genetic algorithm is designed to optimize a computer-aided detection (CAD) system for identifying colonic polyps. Colonic polyps appear as elliptical protrusions on the inner surface of the colon. Curvature-based features for colonic polyp detection have proved to be successful in several CT colonography (CTC) CAD systems. Our CTC CAD program uses a sequential classifier to form initial polyp detections on the colon surface. The classifier utilizes a set of thresholds on curvature-based features to cluster suspicious colon surface regions into polyp candidates. The thresholds were previously chosen experimentally by using feature histograms. The chosen thresholds were effective for detecting polyps sized 10 mm or larger in diameter. However, many medium-sized polyps, 6-9 mm in diameter, were missed in the initial detection procedure. In this paper, the task of finding optimal thresholds as a multiobjective optimization problem was formulated, and a genetic algorithm to solve it was utilized by evolving the Pareto front of the Pareto optimal set. The new CTC CAD system was tested on 792 patients. The sensitivities of the optimized system improved significantly, from 61.68% to 74.71% with an increase of 13.03% (95% CI [6.57%, 19.5%], p = 7.78 x 10(-5)) for the size category of 6-9 mm polyps, from 65.02% to 77.4% with an increase of 12.38% (95% CI [6.23%, 18.53%], p = 7.95 x 10(-5)) for polyps 6 mm or larger, and from 82.2% to 90.58% with an increase of 8.38% (95% CI [0.75%, 16%], p = 0.03) for polyps 8 mm or larger at comparable false positive rates. The sensitivities of the optimized system are nearly equivalent to those of expert radiologists.

[1]  Nicholas Petrick,et al.  Using Pareto fronts to evaluate polyp detection algorithms for CT colonography , 2007, SPIE Medical Imaging.

[2]  Zhengrong Liang,et al.  Reduction of false positives by internal features for polyp detection in CT-based virtual colonoscopy. , 2005, Medical physics.

[3]  Matthew A. Kupinski,et al.  Multiobjective Genetic Optimization of Diagnostic Classifiers with Implications for Generating ROC Curves , 1999, IEEE Trans. Medical Imaging.

[4]  I. Bitter,et al.  Computed tomographic virtual colonoscopy computer-aided polyp detection in a screening population. , 2005, Gastroenterology.

[5]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[6]  Stuart A. Taylor,et al.  CT colonography in the detection of colorectal polyps and cancer: systematic review, meta-analysis, and proposed minimum data set for study level reporting. , 2005, Radiology.

[7]  Ronald M. Summers,et al.  Colonic polyp segmentation in CT colonography-based on fuzzy clustering and deformable models , 2004, IEEE Transactions on Medical Imaging.

[8]  A. Jemal,et al.  Cancer Statistics, 2007 , 2007, CA: a cancer journal for clinicians.

[9]  Marco Laumanns,et al.  SPEA2: Improving the strength pareto evolutionary algorithm , 2001 .

[10]  Ronald M. Summers,et al.  An Efficient Feature Selection Algorithm for Computer-aided Polyp Detection , 2006, Int. J. Artif. Intell. Tools.

[11]  Hussein A. Abbass,et al.  Performance analysis of evolutionary multi-objective optimization methods in noisy environments , 2004 .

[12]  S. Armato,et al.  Mixture of expert 3D massive-training ANNs for reduction of multiple types of false positives in CAD for detection of polyps in CT colonography. , 2008, Medical physics.

[13]  Joyoni Dey,et al.  > Replace This Line with Your Paper Identification Number (double-click Here to Edit) < , 2022 .

[14]  Ronald M. Summers,et al.  Automatic colonic polyp detection using multi-objective evolutionary techniques , 2006, SPIE Medical Imaging.

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

[16]  P. Pickhardt,et al.  Computed tomographic virtual colonoscopy to screen for colorectal neoplasia in asymptomatic adults. , 2003, The New England journal of medicine.

[17]  Ronald M. Summers,et al.  3D colonic polyp segmentation using dynamic deformable surfaces , 2004, SPIE Medical Imaging.

[18]  Y. Masutani,et al.  Computerized detection of colonic polyps at CT colonography on the basis of volumetric features: pilot study. , 2002, Radiology.

[19]  H. Yoshida,et al.  CAD techniques, challenges, andcontroversies in computed tomographic colonography , 2004, Abdominal Imaging.

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

[21]  H. Pohl,et al.  Prevalence of clinically important histology in small adenomas. , 2006, Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association.

[22]  Robert M. Nishikawa,et al.  Optimization and FROC analysis of rule-based detection schemes using a multiobjective approach , 1998, IEEE Transactions on Medical Imaging.

[23]  Hiroyuki Yoshida,et al.  Massive-training artificial neural network (MTANN) for reduction of false positives in computer-aided detection of polyps: Suppression of rectal tubes. , 2006, Medical physics.

[24]  Ronald M. Summers,et al.  Validating Pareto optimal operation parameters of polyp detection algorithms for CT colonography , 2007, SPIE Medical Imaging.

[25]  Jianhua Yao,et al.  Wavelet method for CT colonography computer-aided polyp detectiona). , 2008, Medical physics.

[26]  M. Anastasio,et al.  Multiobjective genetic optimization of diagnostic classifiers with implications for generating receiver operating characteristic curves , 1999, IEEE Transactions on Medical Imaging.

[27]  Gary B. Lamont,et al.  Multiobjective evolutionary algorithm test suites , 1999, SAC '99.

[28]  Marco Laumanns,et al.  Performance assessment of multiobjective optimizers: an analysis and review , 2003, IEEE Trans. Evol. Comput..

[29]  J. Yee,et al.  CT colonography reporting and data system: a consensus proposal. , 2005, Radiology.

[30]  Ronald M. Summers,et al.  Surface curvature estimation for automatic colonic polyp detection , 2005, SPIE Medical Imaging.

[31]  William E. Lorensen,et al.  Marching cubes: a high resolution 3D surface construction algorithm , 1996 .

[32]  Ronald M. Summers,et al.  Automatic detection of endobronchial lesions using virtual bronchoscopy: comparison of two methods , 1998, Medical Imaging.

[33]  J. Malley,et al.  Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees. , 2002, Medical physics.

[34]  Marek Franaszek,et al.  Multiple neural network classification scheme for detection of colonic polyps in CT colonography data sets. , 2003, Academic radiology.

[35]  J. Jackson,et al.  Meta-Analysis: Computed Tomographic Colonography , 2005, Annals of Internal Medicine.

[36]  Ronald M. Summers,et al.  Support vector machines committee classification method for computer-aided polyp detection in CT colonography1 , 2005 .

[37]  Ronald M. Summers,et al.  Wavelet method for CT colonography computer-aided polyp detection , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[38]  Carlos A. Coello Coello,et al.  An updated survey of evolutionary multiobjective optimization techniques: state of the art and future trends , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[39]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..