Multi-organ Localization Combining Global-to-Local Regression and Confidence Maps
We propose a method for fast, accurate and robust localization of several organs in medical images. We generalize global-to-local cascades of regression forests  to multiple organs. A first regressor encodes global relationships between organs. Subsequent regressors refine the localization of each organ locally and independently for improved accuracy. We introduce confidence maps, which incorporate information about both the regression vote distribution and the organ shape through probabilistic atlases. They are used within the cascade itself, to better select the test voxels for the second set of regressors, and to provide richer information than the classical bounding boxes thanks to the shape prior. We demonstrate the robustness and accuracy of our approach through a quantitative evaluation on a large database of 130 CT volumes.
KeywordsRandom Forest Binary Mask Fast Implementation Local Step Probabilistic Atlas
- 1.Cuingnet, R., Prevost, R., Lesage, D., Cohen, L.D., Mory, B., Ardon, R.: Automatic detection and segmentation of kidneys in 3D CT images using random forests. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 66–74. Springer, Heidelberg (2012)CrossRefGoogle Scholar
- 3.Zhou, S.: Discriminative anatomy detection: Classification vs regression. Pattern Recognition Letters (in press)Google Scholar
- 6.Sun, M., Kohli, P., Shotton, J.: Conditional regression forests for human pose estimation. In: CVPR, pp. 3394–3401 (2012)Google Scholar
- 7.Gall, J., Lempitsky, V.: Class-specific hough forest for object detection. In: CVPR, pp. 1022–1029 (2009)Google Scholar