MICCAI 2003: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2003 pp 581-591 | Cite as
A Novel Stochastic Combination of 3D Texture Features for Automated Segmentation of Prostatic Adenocarcinoma from High Resolution MRI
Abstract
In this work, we present a new methodology for fully automated segmentation of prostatic adenocarcinoma from high resolution MR by using a novel feature ensemble of 3D texture features. This work represents the first attempt to solve this difficult problem using high resolution MR. The difficulty of the problem stems from lack of shape and structure in the adenocarcinoma. Hence, in our methodology we compute statistical, gradient and Gabor filter features at multiple scales and orientations in 3D to capture the entire range of shape, size and orientation of the tumor. For an input scene, a classifier module generates Likelihood Scenes for each of the 3D texture features independently. These are then combined using a weighted feature combination scheme. The ground truth for quantitative evaluation was generated by an expert pathologist who manually segmented the tumor on the MR using registered histologic data. Our system was quantitatively compared against the performance of the individual texture features and against an expert’s manual segmentation based solely on visual inspection of the 4T MR data. The automated system was found to be superior in terms of Sensitivity and Positive Predictive Value.
Keywords
Ground Truth Positive Predictive Value Prostatic Adenocarcinoma Texture Operator Expert ObserverReferences
- 1.Kovalev, V., Petrou, M., Bondar, Y.: Texture Anisotropy in 3-D Images. IEEE Trans. on Image Proc. 8(3), 34–43 (1999)CrossRefGoogle Scholar
- 2.Schiebler, M., Schnall, M., et al.: Current Role of MR Imaging in staging of adenocarcinoma of the prostate. Radiology 189(2), 339–352 (1993)Google Scholar
- 3.Gnadt, W., Manolakis, D., et al.: Classification of prostate tissue using neural networks. Int. Joint Conf. on Neural Net. 5, 3569–3572 (1999)Google Scholar
- 4.Haralick, R., Shanmugan, K., Dinstein, I.: Textural Features for Image Classification. IEEE Trans. Syst. Man. Cybern. SMC-3, 610–621 (1973)CrossRefGoogle Scholar
- 5.Madabhushi, A., Udupa, J.: Interplay of Intensity Standardization and Inhomogeneity Correction in MR Image Analysis, vol. 5032, pp. 768–779. SPIE, San Jose (2003)Google Scholar
- 6.Houston, A., Premkumar, S., Pitts, D.: Prostate Ultrasound Image Analysis. In: IEEE Symp. on Computer-Based Med. Syst., pp. 94–101 (1995)Google Scholar
- 7.Basset, D., Sun, Z., et al.: Texture Analysis of Ultrasonic Images of the Prostate by Means of Co-Occurrence Matrices. Ultrasonic Imaging 15, 218–237 (1993)CrossRefGoogle Scholar
- 8.Jain, A., Farrokhnia, F.: Unsupervised Texture Segmentation Using Gabor Filters. Pattern Recog 24(12), 1167–1186 (1991)CrossRefGoogle Scholar
- 9.Duda, R., Hart, P.: Pattern Classification and Scene Analysis. Wiley, Chichester (1973)MATHGoogle Scholar
- 10.Freund, Y., Schapire, R.: Experiments with a new Boosting Algorithm. In: National Conference on Machine Learning, pp. 148–156 (1996)Google Scholar
- 11.Dietterich, T.: Ensemble Methods in Machine Learning. In: Workshop on Multiple Classifier Systems, pp. 1–15 (2000)Google Scholar
- 12.Perrone, M.: Improving regression estimation, Ph.D. Thesis, Dept. of Physics, Brown University (1993)Google Scholar
- 13.Montillo, A., Udupa, J., Axel, L., Metaxas, D.: Interaction between noise suppression & inhomogeneity correction, vol. 5032, pp. 1025–1036. SPIE, San Jose (2003)Google Scholar