Diego Dall'Alba1, Paolo Fiorini. 1. Department of Computer Science, University of Verona, Strada le Grazie, 15, 37134, Verona, Italy, diego.dallalba@univr.it.
Abstract
PURPOSE: Detection of feature points in medical ultrasound (US) images is the starting point of many clinical tasks, such as segmentation of lesions in pathological areas, estimation of organ deformation, and multimodality image fusion. However, obtaining a reliable feature point localization is a complex task even for an expert radiologist due to the US image characteristics: strong presence of noise, insidious artifacts, and low contrast. In this work, we describe a feature detector based on phase congruency (PhC) combined with a binary pattern descriptor. METHODS: We introduce a feature detector specifically designed for US images and based on PhC analysis. We also introduce a descriptor based on local binary pattern (LBP) operator to improve and simplify the matching between feature points extracted from different images. LBP is not applied directly to the intensity values; instead, it is applied to the PhC output obtained during the detection step to improve robustness to intensity transformation, and the rejection of noise. RESULTS: We tested the proposed approach compared to state-of- the-art methods applied to real US images subject to realistic synthetic transformations. The results of the proposed method, in terms of accuracy and precision, outperform the state-of-the-art approaches that are not designed for US data. CONCLUSIONS: The methods described in this work will enable the development of US-based navigation system, which supports automatic feature point detection and matching from US images acquired at different times during the procedure.
PURPOSE: Detection of feature points in medical ultrasound (US) images is the starting point of many clinical tasks, such as segmentation of lesions in pathological areas, estimation of organ deformation, and multimodality image fusion. However, obtaining a reliable feature point localization is a complex task even for an expert radiologist due to the US image characteristics: strong presence of noise, insidious artifacts, and low contrast. In this work, we describe a feature detector based on phase congruency (PhC) combined with a binary pattern descriptor. METHODS: We introduce a feature detector specifically designed for US images and based on PhC analysis. We also introduce a descriptor based on local binary pattern (LBP) operator to improve and simplify the matching between feature points extracted from different images. LBP is not applied directly to the intensity values; instead, it is applied to the PhC output obtained during the detection step to improve robustness to intensity transformation, and the rejection of noise. RESULTS: We tested the proposed approach compared to state-of- the-art methods applied to real US images subject to realistic synthetic transformations. The results of the proposed method, in terms of accuracy and precision, outperform the state-of-the-art approaches that are not designed for US data. CONCLUSIONS: The methods described in this work will enable the development of US-based navigation system, which supports automatic feature point detection and matching from US images acquired at different times during the procedure.
Authors: Michael Calonder; Vincent Lepetit; Mustafa Özuysal; Tomasz Trzcinski; Christoph Strecha; Pascal Fua Journal: IEEE Trans Pattern Anal Mach Intell Date: 2011-11-15 Impact factor: 6.226