Parametrical modelling for texture characterization-A novel approach applied to ultrasound thyroid segmentation.

Texture analysis is an important topic in Ultrasound (US) image analysis for structure segmentation and tissue classification. In this work a novel approach for US image texture feature extraction is presented. It is mainly based on parametrical modelling of a signal version of the US image in order to process it as data resulting from a dynamical process. Because of the predictive characteristics of such a model representation, good estimations of texture features can be obtained with less data than generally used methods require, allowing higher robustness to low Signal-to-Noise ratio and a more localized US image analysis. The usability of the proposed approach was demonstrated by extracting texture features for segmenting the thyroid in US images. The obtained results showed that features corresponding to energy ratios between different modelled texture frequency bands allowed to clearly distinguish between thyroid and non-thyroid texture. A simple k-means clustering algorithm has been used for separating US image patches as belonging to thyroid or not. Segmentation of thyroid was performed in two different datasets obtaining Dice coefficients over 85%.

Novel Similarity Metric for Image-Based Out-Of-Plane Motion Estimation in 3D Ultrasound.

Over the past decade, Freehand 3D Ultrasound(US) reconstruction using only image information has become a widely researched topic because it eliminates the need for an external tracking system and provides real-time volumetric information. But most of the state-of-art methods are inhibited by their inability to find a simple and robust similarity metric that could learn and estimate the spatial transformation between two US slices in a US sweep. In this work, we propose a novel similarity metric (TexSimAR), which computes the similarity value between two consecutive US images by correlating the parametric representation of the image-texture instead of the image itself. The purpose of this approach is to capture and compare the dynamics in the texture characteristics of two US images. We modelled these dynamics using a parametrical auto-regressive (AR) model. Experiments were performed on forearm datasets of three subjects. For every pair of consecutive US slices, we computed our TexSimAR similarity value and out-of-plane transformation from the ground truth to train a Support Vector Machine (SVM) based regression model, which was then used to predict the out-of-plane transformation with the similarity value as input. The proposed method shows promising results with predictions better than state-of-the-art methods even with 1/8th of training data compared to other methods in the literature.

Novel Ultrasound Texture Based Similarity Metric Using Autoregressive Modelling.

Designing an ultrasound (US) specific similarity metric is essential in integrating advanced techniques like image segmentation and registration to US based interventional procedures. Applying conventional similarity metrics to ultrasound images is hampered by intrinsic noise patterns in an US image. In this work, we propose a texture based similarity metric (TexSimAR) using Autoregressive (AR) modelling. The key idea is to treat an US image as data resulting from a dynamical process which can be parametrically modelled. Using this approach it is possible to compute a parametric spectrum of individual US images and subsequently use it to estimate a similarity value between them. For evaluation, we used thyroid US images and similarity values were calculated between thyroid and non-thyroid regions. A cost function was designed to compare TexSimAR with other conventional similarity metrics. TexSimAR clearly distinguished between thyroid and non-thyroid regions outperfoming the conventional similarity metrics.

In-room ultrasound fusion combined with fully compatible 3D-printed holding arm - rethinking interventional MRI.

There is no real need to discuss the potential advantages - mainly the excellent soft tissue contrast, nonionizing radiation, flow, and molecular information - of magnetic resonance imaging (MRI) as an intraoperative diagnosis and therapy system particularly for neurological applications and oncological therapies. Difficult patient access in conventional horizontal-field superconductive magnets, very high investment and operational expenses, and the need for special nonferromagnetic therapy tools have however prevented the widespread use of MRI as imaging and guidance tool for therapy purposes. The interventional use of MRI systems follows for the last 20+ years the strategy to use standard diagnostic systems and add more or less complicated and expensive components (eg, MRI-compatible robotic systems, specially shielded in-room monitors, dedicated tools and devices made from low-susceptibility materials, etc) to overcome the difficulties in the therapy process. We are proposing to rethink that approach using an in-room portable ultrasound (US) system that can be safely operated till 1 m away from the opening of a 3T imaging system. The live US images can be tracked using an optical inside-out approach adding a camera to the US probe in combination with optical reference markers to allow direct fusion with the MRI images inside the MRI suite. This leads to a comfortable US-guided intervention and excellent patient access directly on the MRI patient bed. This was combined with an entirely mechanical MRI-compatible 7 degrees of freedom holding arm concept, which shows that this test environment is a different way to create a cost-efficient and effective setup that combines the advantages of MRI and US by largely avoiding the drawbacks of current interventional MRI concepts.