Ultrasonic image analysis and image-guided interventions

Abstract

The fields of medical image analysis and computer-aided interventions deal with reducing the large volume of digital images (X-ray, computed tomography, magnetic resonance imaging (MRI), positron emission tomography and ultrasound (US)) to more meaningful clinical information using software algorithms. US is a core imaging modality employed in these areas, both in its own right and used in conjunction with the other imaging modalities. It is receiving increased interest owing to the recent introduction of three-dimensional US, significant improvements in US image quality, and better understanding of how to design algorithms which exploit the unique strengths and properties of this real-time imaging modality. This article reviews the current state of art in US image analysis and its application in imageguided interventions. The article concludes by giving a perspective from clinical cardiology which is one of the most advanced areas of clinical application of US image analysis and describing some probable future trends in this important area of ultrasonic imaging research.

Ultrasound guided automatic localization of needle insertion site for epidural anesthesia

“…X-ray, CT, MRI, in that it is safe, nonradioactive and cheap, making it an appropriate imaging modality for assisting epidural needle insertion [19]. However, a barrier to reap these benefits lies in the ability to interpret the ultrasound image effectively.…”

“…The resolution of an ultrasound image is low, usually 1-2mm along the axial direction and 1-3mm along the lateral direction, given that the penetration depth of the ultrasound wave is above 10cm, as required by depth of the epidural space. Moreover, the ultrasound images contain severe speckle noises, making the subtle structures indistinguishable from surrounding background [19]. A full interpretation of ultrasound images requires professional training and experiences.…”

Lumbar Ultrasound Image Feature Extraction and Classification with Support Vector Machine

“…However, despite the benefits of ultrasound, the effective interpretation of ultrasound images remains a challenge, especially for anesthetists who received limited training in reading ultrasound images (Ecimovic and Loughrey 2010). The low spatial resolution and inherent speckle noise of ultrasound images cause the subtle anatomical features to be indiscernible from the surrounding background (Noble et al 2011). Full interpretation of ultrasound images requires professional training, and the learning curve is steep (Chin and Perlas 2011).…”

Recent advances in biomedical ultrasonic imaging techniques

“…These are those on medical ultrasound systems [7], ultrasonic colour Doppler imaging [8], three-dimensional ultrasonic scanning [9], vascular ultrasound for atherosclerosis imaging [10] and quantitative contrast-enhanced ultrasonic imaging [11]. The second category consists of papers on technologies that are just now beginning to impact upon clinical practice: real-time quasi-static ultrasound elastography [12], acoustic radiation force-based elasticity imaging [13] and ultrasonic image analysis and image-guided interventions [14]. The third category consists of papers that discuss contemporary research, which is either not directly concerned with clinical studies (micro-ultrasound for preclinical imaging [15]), or which, although promising, is still seen as being some time away from having an impact: biomedical photoacoustic imaging [16], ultrasound-mediated optical tomography [17], continuous wave ultrasonic Doppler tomography [18] and thermal strain imaging [19].…”