Machine Learning
Ensemble Methods in Machine Learning
MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues
IEEE Transactions on Pattern Analysis and Machine Intelligence
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
An empirical comparison of nine pattern classifiers
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
ISBRA'07 Proceedings of the 3rd international conference on Bioinformatics research and applications
The impact of random samples in ensemble classifiers
Proceedings of the 2010 ACM Symposium on Applied Computing
A general system for automatic biomedical image segmentation using intensity neighborhoods
Journal of Biomedical Imaging
Prostate cancer visualization from MR imagery and MR spectroscopy
EuroVis'11 Proceedings of the 13th Eurographics / IEEE - VGTC conference on Visualization
Hi-index | 0.00 |
While learning ensembles have been widely used for various pattern recognition tasks, surprisingly, they have found limited application in problems related to medical image analysis and computer-aided diagnosis (CAD). In this paper we investigate the performance of several state-of-the-art machine-learning methods on a CAD method for detecting prostatic adenocarcinoma from high resolution (4 Tesla) ex vivo MRI studies. A total of 14 different feature ensemble methods from 4 different families of ensemble methods were compared: Bayesian learning, Boosting, Bagging, and the k-Nearest Neighbor (kNN) classifier. Quantitative comparison of the methods was done on a total of 33 2D sections obtained from 5 different 3D MRI prostate studies. The tumor ground truth was determined on histologic sections and the regions manually mapped onto the corresponding individual MRI slices. All methods considered were found to be robust to changes in parameter settings and showed significantly less classification variability compared to inter-observer agreement among 5 experts. The kNN classifier was the best in terms of accuracy and ease of training, thus validating the principle of Occam's Razor. The success of a simple non-parametric classifier requiring minimal training is significant for medical image analysis applications where large amounts of training data are usually unavailable.