Coherence-Enhancing Diffusion Filtering
International Journal of Computer Vision
Automatic Hepatic Vessel Segmentation Using Graphics Hardware
MIAR '08 Proceedings of the 4th international workshop on Medical Imaging and Augmented Reality
Vessel segmentation for ablation treatment planning and simulation
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Hi-index | 0.00 |
We present an evaluation of five diffusion filters for liver vessel enhancement in 3D CTA datasets of the liver. 3D CTA liver images are generally noisy, with limited contrast between vessels and parenchyma, especially for the small vessels. We investigate the performance of five (an)isotropic diffusions filters: Regular Perona-Malik, Coherence-Enhancing Diffusion, Edge-Enhancing Diffusion, Hybrid Diffusion with Continuous Switch and Vessel Enhancing Diffusion on a set of 14 abdominal CTA clinical datasets. The evaluation is based on signal to noise improvement. A parameter optimization is performed on 7 training images, after which the optimal versions of the filters are compared on 7 test images. The results demonstrate that all the diffusion filters improve SNR of the images and Hybrid Diffusion with Continuous Switch and Vessel Enhancing Diffusion gives the largest increase in SNR.