OBJECTIVE: An algorithm is presented for the automatic detection of intradural spaces in MR images of the human head. The primary motivation behind the present work has been to serve as a preprocessing step in automatic segmentation of brain tissue and CSF. A second objective was to use the algorithm in a fully automatic PET-MR registration algorithm. MATERIALS AND METHODS: The method is primarily designed for, and requires, dual echo (T1- and T2-weighted) MR images with transaxial orientations. The algorithm consists of three main stages. First, the head contour is detected using a series of low-level image-processing techniques. In the second stage, the pixels inside the head contour are clustered into a number of classes using the K-means algorithm. Finally, the extradural connected components are eliminated based on a number of heuristics. RESULTS: Test results are presented for 10 MR image sets consisting of 197 slices. As a quantitative measure of accuracy, manual segmentations were performed by radiologists on a number of slices and compared with the results obtained automatically. CONCLUSION: Visual inspection and quantitative validation of the results indicate that the algorithm accurately detects the intradural spaces in MR images. This is an important step in fully automatic segmentation and registration of MR images.
OBJECTIVE: An algorithm is presented for the automatic detection of intradural spaces in MR images of the human head. The primary motivation behind the present work has been to serve as a preprocessing step in automatic segmentation of brain tissue and CSF. A second objective was to use the algorithm in a fully automatic PET-MR registration algorithm. MATERIALS AND METHODS: The method is primarily designed for, and requires, dual echo (T1- and T2-weighted) MR images with transaxial orientations. The algorithm consists of three main stages. First, the head contour is detected using a series of low-level image-processing techniques. In the second stage, the pixels inside the head contour are clustered into a number of classes using the K-means algorithm. Finally, the extradural connected components are eliminated based on a number of heuristics. RESULTS: Test results are presented for 10 MR image sets consisting of 197 slices. As a quantitative measure of accuracy, manual segmentations were performed by radiologists on a number of slices and compared with the results obtained automatically. CONCLUSION: Visual inspection and quantitative validation of the results indicate that the algorithm accurately detects the intradural spaces in MR images. This is an important step in fully automatic segmentation and registration of MR images.