Title :
Border detection on digitized skin tumor images
Author :
Zhang, Zhao ; Stoecker, William V. ; Moss, Randy H.
Author_Institution :
Dept. of Eng., Missouri Western State Coll., St. Joseph, MO, USA
Abstract :
A radial search technique is presented for detecting skin tumor borders in clinical dermatology images. First, it includes two rounds of radial search based on the same tumor center. The first-round search is independent, and the second-round search is knowledge-based tracking. Then a rescan with a new center is used to solve the blind-spot problem. The algorithm is tested on model images with excellent performance, and on 300 real clinical images with a satisfactory result.
Keywords :
edge detection; medical image processing; skin; tumours; algorithm; blind-spot problem; border detection; clinical dermatology images; digitized skin tumor images; knowledge-based tracking; medical diagnostic imaging; radial search technique; real clinical images; rescan; second-round search; Application software; Biomedical imaging; Image edge detection; Image processing; Image segmentation; Medical diagnostic imaging; Medical simulation; Morphological operations; Skin neoplasms; Testing; Humans; Signal Processing, Computer-Assisted; Skin Neoplasms;
Journal_Title :
Medical Imaging, IEEE Transactions on
