Rapid semi-automatic segmentation of real-time magnetic resonance images for parametric vocal tract analysis

2010 ◽  
Author(s):  
Michael I. Proctor ◽  
Daniel Bone ◽  
Athanasios Katsamanis ◽  
Shrikanth S. Narayanan
Keyword(s):  
Magnetic Resonance ◽  
Real Time ◽  
Vocal Tract ◽  
Automatic Segmentation ◽  
Magnetic Resonance Images

Semantic Edge Detection for Tracking Vocal Tract Air-Tissue Boundaries in Real-Time Magnetic Resonance Images

2017 ◽  
Author(s):  
Krishna Somandepalli ◽  
Asterios Toutios ◽  
Shrikanth S. Narayanan
Keyword(s):  
Magnetic Resonance ◽  
Edge Detection ◽  
Real Time ◽  
Vocal Tract ◽  
Magnetic Resonance Images

scholarly journals Semi-automatic method for analysing vocal tract morphology from real-time magnetic resonance images

2021 ◽  
Author(s):  
Michel Belyk ◽  
Christopher Carignan ◽  
Carolyn McGettigan
Keyword(s):  
Magnetic Resonance ◽  
Real Time ◽  
Vocal Tract ◽  
Structural Features ◽  
Magnetic Resonance Images ◽  
Training Data ◽  
Surrounding Tissue ◽  
User Input ◽  
Internal Structures ◽  
Automated Processing

Real-time magnetic resonance imaging is a technique that provides high contrast videographic data of the vocal tract that allow researchers to observe the internal structures that shape the sounds of speech. However, structural features need to be extracted from these vocal tract images to make them useful to researchers. We have developed a semi-automated processing pipeline that produces outlines of the vocal tract to quantify vocal tract morphology. Our approach uses simple tissue classification constrained to pixels that analysts have identified as likely to contain the vocal tract and surrounding tissue. This approach is supplemented with multiple opportunities for the analyst to intervene in order to ensure that outputs are robust to errors. Although this approach is more labour intensive than more fully automated alternatives, these costs are offset by the benefits of improving the quality of measurements. We demonstrate that this pipeline can be generalised to a range of datasets and that it remains reliable across analysts, particularly among analysts with vocal tract expertise. The pipeline’s reliance on user input presents a challenge to scalability if applied to very large. Measurements produced by this pipeline could be provide a broader scope of training data for fully automated methods in an effort to improve their generalisability.

scholarly journals Deep-learning-based segmentation of the vocal tract and articulators in real-time magnetic resonance images of speech

2021 ◽  
Vol 198 ◽  
pp. 105814
Author(s):  
Matthieu Ruthven ◽  
Marc E. Miquel ◽  
Andrew P. King
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance ◽  
Real Time ◽  
Vocal Tract ◽  
Magnetic Resonance Images

scholarly journals Implementation of Iterative bilateral filtering for removal of Rician noise in MR images using FPGA

2020 ◽  
Vol 9 (3) ◽  
pp. 279-284
Keyword(s):  
Magnetic Resonance ◽  
Real Time ◽  
Visual Analysis ◽  
Similarity Index ◽  
Structural Similarity ◽  
Bilateral Filter ◽  
Magnetic Resonance Images ◽  
Rician Noise ◽  
Diagnostic Quality ◽  
Index Matrix

Magnetic resonance image noise reduction is important to process further and visual analysis. Bilateral filter is denoises image and also preserves edge. It proposes Iterative bilateral filter which reduces Rician noise in the magnitude magnetic resonance images and retains the fine structures, edges and it also reduces the bias caused by Rician noise. The visual and diagnostic quality of the image is retained. The quantitative analysis is based on analysis of standard quality metrics parameters like peak signal-to-noise ratio and mean structural similarity index matrix reveals that these methods yields better results than the other proposed denoising methods for MRI. Problem associated with the method is that it is computationally complex hence time consuming. It is not recommended for real time applications. To use in real time application a parallel implantation of the same using FPGA is proposed.

scholarly journals Treatment of hepatocellular carcinoma using the Smart Fusion needle navigation system: conversion from real-time 4D-echo data

2021 ◽  
pp. 46
Author(s):  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Magnetic Resonance ◽  
Real Time ◽  
Navigation System ◽  
Magnetic Resonance Images ◽  
The Body ◽  
Target Point ◽  
Ultrasound Images ◽  
Volume Data ◽  
Needle Position

Advances in ultrasound systems have improved the accuracy of hepatocellular carcinoma (HCC) diagnosis and treatment. We have been treating HCC using real-time 4D and Live 3D-echo technologies. However, these treatment methods have drawbacks such as vibrations during puncture and a limited angle of needle insertion. To overcome these problems, systems that can display ultrasound images simultaneously with computed tomography (CT) and magnetic resonance images in a real-time manner for reference purposes have been reported. These systems have recently been equipped with a needle tip navigation system, making it possible to reliably visualize tumors and determine the needle tip position in a tumor. These developments have enabled the safe treatment of HCC. Treatment using needle navigation is performed as follows: A Canon APLIO800 ultrasound system is used with a conventional convex probe (PVT-375BT) and a micro-convex probe (PVT-382BT). The system function is known as Smart Fusion. Ultrasound images can be displayed with volume data from other modalities, such as CT and magnetic resonance imaging (MRI), in relation to the positional information using a magnetic sensor. This enables the use of CT/MRI data as reference for accurate puncture and treatment of lesions that are difficult to identify by ultrasound alone. Axis alignment is also completed by displaying the xiphoid process on a CT image and having the system learn the orientation of the probe placed perpendicular to the body axis. Then, landmark alignment is performed and fine-adjusted by aligning a target point near the lesion with the same point as displayed on CT (Fig. 1). Case presentation A 7x-year-old woman was found to have elevated tumor markers and a liver tumor identified by regular blood testing and CT performed in August 20xx and was admitted to our hospital for treatment. Abdominal ultrasonography showed a hypoechoic lesion measuring approximately 3 cm in diameter in liver S6, which led to a diagnosis of HCC. For treatment, microwave therapy was selected at the patient’s request. Microwaves were delivered using a Medtronic Emprint ablation system with a 3.0-cm needle for ablation. During treatment, the needle position was confirmed by needle navigation before ablation (Fig. 2) because the tumor needed to be ablated in an overlapping manner (Fig. 3).

Vocal Tract Configurations in Tenors' Passaggio in Different Vowel Conditions—A Real-Time Magnetic Resonance Imaging Study

2014 ◽  
Vol 28 (2) ◽  
pp. 262.e1-262.e8 ◽  
Author(s):  
Matthias Echternach ◽  
Louisa Traser ◽  
Bernhard Richter
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Real Time ◽  
Vocal Tract ◽  
Imaging Study ◽  
Magnetic Resonance Imaging Study ◽  
Resonance Imaging
Sign in / Sign up

Export Citation Format

Share Document