Fast Vessel Segmentation and Tracking in Ultra High-Frequency Ultrasound Images

Computer-Aided Diagnosis Methods for High-Frequency Ultrasound Data Analysis: A Review

“…Some works addressed the problem of subcutaneous blood vessel segmentation [ 79 , 80 ] or HFUS image quality assessment [ 55 , 89 ]. A novel trend in CAD algorithms is sharing the datasets or source code [ 67 , 88 , 91 ].…”

“…In addition to neoplastic lesions, the analysis of which is usually the most widely described in the literature or works addressing the challenges in the diagnosis of inflammatory skin diseases, incidences of which increase every year, the latest CAD systems also include algorithms for the segmentation of blood vessels [ 79 , 80 ] in HFUS images.…”

“…The first work by Mathai et al [ 79 ] targeted the segmentation and tracking of small and medium hand vessels based on UHFUS images (above 50 MHz). The developed GPU-based approach enabled fast submillimeter 2D vessel contour localization.…”

“…The accurate segmentation and visualization of superficial veins are essential in diagnosing skin lesions and the most crucial findings in this field can be summarized as follows: Only two works targeted HFUS image segmentation with the highest accuracy reported by Mathai et al [ 79 ] using the level-set technique. There appeared to be more algorithms concerning vessel segmentation using the classical US (<20 MHz) [ 113 ], which can also be applied to HFUS image data.…”

“…Only two works targeted HFUS image segmentation with the highest accuracy reported by Mathai et al [ 79 ] using the level-set technique.…”