Abstract: Provided are methods for characterizing a feature of interest in a digital image. In certain aspects, the methods use an adaptive local window and include obtaining an initial contour for a feature of interest, defining a region of interest around the contour, and segmenting the feature of interest by iteratively selecting a size of a local window surrounding each point on the contour. Non-transitory computer readable media and systems that find use in practicing the methods of the present disclosure are also provided.

Abstract: Provided are methods for characterizing a feature of interest in a digital image. In certain aspects, the methods use an adaptive local window and include obtaining an initial contour for a feature of interest, defining a region of interest around the contour, and segmenting the feature of interest by iteratively selecting a size of a local window surrounding each point on the contour. Non-transitory computer readable media and systems that find use in practicing the methods of the present disclosure are also provided.

Abstract: Systems and methods using contrast enhanced ultrasound imaging for quantitative assessment of neovascularization, such as within a tumor or a plaque. The contrast agent moves in small blotches rather than in continuous flow, but image processing methods enable the detection and quantification of the blood flow, even in the tiny blood vessels of the vasculature tree. The image processing includes compensation for motion of the tissue arising from body movement. The position and extent of the discrete positions of contrast material may be accumulating during a complete heart cycle onto a single 2D image, to enable an indication of a vascular tree based on this local accumulated image. Dynamic processing (DP) of the discrete positions of contrast material enables a complete vascular tree to be obtained. The neovascularization is quantified by the ratio of its total area to that of the plaque in which the neovascularization has grown.