Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition
IEEE Transactions on Information Technology in Biomedicine
Knee MR image segmentation combining contextual constrained neural network and level set evolution
CIBCB'09 Proceedings of the 6th Annual IEEE conference on Computational Intelligence in Bioinformatics and Computational Biology
Hi-index | 0.00 |
Kinematic approaches using MR images have been regarded of more accuracy in knee pain (AKP) detection than stationary approaches. However, the challenge in segmenting femur, patellar and tibia due to the intensity non-uniformity caused by magnetic propagation degradation in MR images, and the strong adhesion of the soft tissue around the knee organs, has restricted the use of kinematic approaches. This paper proposes a combinatorial based kinematic patellar tracking (CKPT) for AKP detection. The CKPT uses a hybrid approach for extracting knee organs, where an edge-constrained wavelet enhancement followed by moment preserving segmentation is employed for conquering the soft tissue adhesion for extracting the femur and tibia from axial MR images, and a sliding window based moment preserving for resolving the segmentation difficulty associated with intensity non-uniformity in saggital MR images. The location constraints are then applied for extracting landmark points from femur and patellar, and three inclination angles reflecting patellar position and orientation, during leg movement, are calculated as the measurement of patellar dislocation. The experiment shows that the hybrid approach can accurately extract femur, patellar and tibia. It also demonstrates the prominent of the calculated inclination angles in detecting AKP.