Enhancement of nerve structure segmentation by a correntropy-based pre-image approach
Journal Title: TecnoLógicas - Year 2017, Vol 20, Issue 39
Abstract
Peripheral Nerve Blocking (PNB) is a commonly used technique forperformingregional anesthesia and managing pain. PNB comprises the administration of anestheticsin the proximity of a nerve. In this sense, the success of PNB procedures depends on an accurate location of the target nerve. Recently, ultrasound images (UI) havebeen widely used to locate nerve structures forPNB,since theyenable a non-invasive visualization of the target nerve and the anatomical structures around it. However, UIare affected by speckle noise, which makes it difficult to accuratelylocatea given nerve. Thus, it is necessary to perform a filtering step to attenuate the speckle noise without eliminating relevant anatomical details that are required for high-level tasks, suchas segmentation of nerve structures. In this paper, we propose an UI improvement strategy with the use of a pre-image-based filter. In particular, we map the input images bya nonlinear function (kernel). Specifically,we employ a correntropy-based mappingas kernel functionalto code higher-order statistics of the inputdata under both nonlinear and non-Gaussian conditions. We validate our approach againstan UI dataset focused on nerve segmentation for PNB. Likewise, our Correntropy-based Pre-Image Filtering (CPIF) is applied as a pre-processing stage to segment nerve structures in a UI. The segmentation performance is measured in terms of the Dice coefficient. According to the results, we observe that CPIF finds a suitable approximation for UI by highlighting discriminative nerve patterns.
Authors and Affiliations
J. Gil-González, A. Álvarez-Meza, M. Álvarez-López
Keywords
Related Articles
- EP ID EP348408
- DOI 10.22430/22565337.717
- Views 82
- Downloads 0
Fabrication of mems devices – a scanning micro mirror case study
This paperpresents theworkingprinciple, design,and fabrication of a silicon-based scanning micromirror with a new type of actionmechanism as an example of MEMS (Micro-Electro-Mechanical Systems). Micromirro...
Performance of clustering techniques for solving multi depot vehicle routing problem
The vehicle routing problem considering multiple depots is classified as NP-hard. MDVRP determines simultaneously the routes of a set of vehicles and aims to meet a set of clients with a known demand. The objective funct...
A comparative study of hysteresis band PWM techniques for current control in shunt active power filters
This paper evaluates the performance of an active power filter using three hysteresis band current control techniques: fixed-band, adaptive-band, and Space Vector Modulation. The characteristics of...
Photovoltaic Potential Estimation by Means of Data Mining in Four Colombian Cities
This work analyzes the photovoltaic potential of four cities in Colombia—Bogotá, Cúcuta, Manizales, and Pasto—using information collected in situ and data mining strategies. The methodology of this study is based on clus...
Optimization of non-stationary Stackelberg models using a self-adaptive evolutionary algorithm
Stackelberg’sgame models involve an important family of Game Theory problems with direct application on economics scenarios. Their main goal is to find an optimal equilibrium between the decision...