Bidirectional blood vessel segmentation
Embodiments relate to segmenting blood vessels in angiogram images. An aspect includes a method that includes receiving and preprocessing at least one angiogram frame and preprocessing. In one embodiment, at least one angiogram frame is received and preprocessed. Bottom-up filtering of the preprocessed angiogram frame and top-down segmentation of the preprocessed angiogram frame are performed based on the results of the bottom-up filtering. The bottom-up filtering and the top-down segmentation are iteratively repeated until the difference between results of the top-down segmentation from consecutive iterations is equal to or below a threshold value. Based on determining that a difference between results of the top-down segmentation from consecutive iterations is below or equal to the threshold value, the results of the top-down segmentation are outputted.
1. A method for segmenting blood vessels comprising:
receiving at least one angiogram frame;
preprocessing, by a processor, the angiogram frame by applying a Butterworth bandpass filter to suppress high and low frequency background noise;
performing bottom-up filtering of the preprocessed angiogram frame;
performing top-down segmentation of the preprocessed angiogram frame based on the results of the bottom-up filtering;
iteratively repeating the bottom-up filtering and the top-down segmentation until the difference between results of the top-down segmentation from consecutive iterations is equal to or below a threshold value;
outputting the results of the top-down segmentation based on a determination that a difference between results of the top-down segmentation from consecutive iterations is below or equal to the threshold value.
2. The method of claim 1 , wherein preprocessing the one or more angiogram frame comprises detecting one or more regions of interest.
3. The method of claim 2 , wherein preprocessing the one or more angiogram frame comprises adaptive enhancement of the one or more regions of interest.
4. The method of claim 2 , wherein preprocessing the one or more angiogram frame comprises removal of non-arterial shapes from the one or more regions of interest.
5. The method of claim 1 , wherein performing bottom-up filtering comprises performing a Frangi-Radon feature filter on the one or more angiogram frame.
6. The method of claim 1 , wherein the top-down segmentation model uses motion through active contours to segment blood vessels.