Different flowmotion patterns in healthy controls and patients with Raynaud's phenomenon
Technology and Health Care
Segmentation and Extraction of Morphologic Features from Capillary Images
MICAI '07 Proceedings of the 2007 Sixth Mexican International Conference on Artificial Intelligence, Special Session
The Groupwise Medial Axis Transform for Fuzzy Skeletonization and Pruning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
In this study, a Pseudo three-dimensional Vision-based Nail-fold Morphological and Hemodynamic Analysis (PTVNMHA) is proposed to automatically extract morphological/hemodynamic features from a microscopic nail-fold image sequence, reconstruct the corresponding pseudo three-dimensional microvascular models, and visualize the dynamic blood flow in the model constructed. The morphological features extracted include the number, width/height, density, arteriolar limb caliber, curved segment caliber, venular limb caliber, blood color, tortuosity, and width of the curved segment of capillaries. The hemodynamic features identified are blood flow velocity and blood flow rate. All are significant pathological indicators with a spatial precision up to 1.6@mm. The diameters of cross-sections along the centerlines of capillaries are identified and employed to reconstruct the pseudo three-dimensional microvascular surface meshes. The microscopic image sequence acquired is mapped to the corresponding microvascular model constructed to perform dynamic blood flow visualization. Compared with laser Doppler velocimetry, PTVNMHA can derive blood flow velocities for each capillary across the microscopic range separately in much higher precision and obtain diversified morphological and hemodynamic features of capillaries with a low-cost equipment setup. In addition to the blood flow velocity, blood flow rate, which keeps almost constant no matter where the measuring position is in a capillary, has also been measured and proposed as a useful feature to discriminate patients with hypertension from the normal with great significance (p