Title :
Snakules: Snakes that seek spicules on mammography
Author :
Muralidhar, Gautam S. ; Bovik, Alan C. ; Markey, Mia K.
Author_Institution :
Dept. of Biomed. Eng., Univ. of Texas, Austin, TX, USA
Abstract :
We present a new method called “snakules” for the annotation of spicules on mammography. Snakules employs parametric open-ended snakes that are deployed in a region around a suspect spiculated mass location that has been identified by a radiologist or a computer-aided detection (CADe) algorithm. The set of convergent snakules deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Our results from an initial observer study involving an experienced radiologist demonstrate the strong potential of the method as an image analysis technique to improve the specificity of CADe algorithms.
Keywords :
mammography; radiology; CADe algorithms; computer-aided detection algorithm; image analysis; mammography; parametric open-ended snakes; radiologist; snakules; spiculated mass location; spicules; Active contours; Force; Image edge detection; Mammography; Manuals; Observers; Pixel; Snakules; active contours; computer-aided detection; mammography; snakes;
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2010.5652334