Gabor filter based localization of needles in ultrasound guided robotic interventions

Abstract

This paper presents an entropy based parameter tuning method for needle segmentation, and a probability map based needle tip estimation method using Gabor-based line filter. The proposed automatic parameter tuning method optimizes the threshold value that is used by the Otsu's thresholding technique to binarize the ultrasound image. A probability map is created to estimate the needle tip location using the Gabor filtered image and the binarized image. The pixel with the maximum probability represents the needle tip location. Finally, an enhancement method to improve needle visibility is proposed. The proposed methods are experimentally tested in four different phantoms and distilled water. The image processing time is reduced by 24% using the proposed tuning method, and the needle tip location can be successfully estimated using the probability map.