Negar M. Harandi

3D segmentation of the tongue in MRI: a minimally interactive model-based approach

Static magnetic resonance imaging partially resolves soft tissue details of the oropharynx, which are crucial in swallowing and speech studies. However, delineation of tongue tissue remains a challenge due to the lack of definitive boundary features. In this article, we propose a minimally interactive inter-subject mesh-to-image registration scheme to tackle 3D segmentation of the human tongue from MRI volumes. A tongue surface-mesh is first initialised using an exemplar expert-delineated template, which is then refined based on local intensity similarities between the source and target volumes. A shape-matching technique [Gilles B, Pai D. 2008. Fast musculoskeletal registration based on shape matching. Paper presented at: MICCAI 2008. Proceedings of the 11th International Conference on Medical Image Computing and Computer Assisted Intervention; New York, NY, USA] is applied for regularising the deformation. We enable effective minimal user interaction by incorporating additional boundary labels in areas ...

Subject-specific biomechanical modelling of the oropharynx: towards speech production

Biomechanical models of the oropharynx are beneficial to treatment planning of speech impediments by providing valuable insight into the speech function such as motor control. In this paper, we develop a subject-specific model of the oropharynx and investigate its utility in speech production. Our approach adapts a generic tongue–jaw–hyoid model [Stavness I, Lloyd JE, Payan Y, Fels S. 2011. Coupled hard-soft tissue simulation with contact and constraints applied to jaw–tongue–hyoid dynamics. Int J Numer Method Biomed Eng. 27(3):367–390] to fit and track dynamic volumetric MRI data of a normal speaker, subsequently coupled to a source-filter-based acoustic synthesiser. We demonstrate our models ability to track tongue tissue motion, simulate plausible muscle activation patterns, as well as generate acoustic results that have comparable spectral features to the associated recorded audio. Finally, we propose a method to adjust the spatial resolution of our subject-specific tongue model to match the fidelity level of our MRI data and speech synthesiser. Our findings suggest that a higher resolution tongue model – using similar muscle fibre definition – does not show a significant improvement in acoustic performance, for our speech utterance and at this level of fidelity; however, we believe that our approach enables further refinements of the muscle fibres suitable for studying longer speech sequences and finer muscle innervation using higher resolution dynamic data.

Variability in muscle activation of simple speech motions: A biomechanical modeling approach

Biomechanical models of the oropharynx facilitate the study of speech function by providing information that cannot be directly derived from imaging data, such as internal muscle forces and muscle activation patterns. Such models, when constructed and simulated based on anatomy and motion captured from individual speakers, enable the exploration of inter-subject variability of speech biomechanics. These models also allow one to answer questions, such as whether speakers produce similar sounds using essentially the same motor patterns with subtle differences, or vastly different motor equivalent patterns. Following this direction, this study uses speaker-specific modeling tools to investigate the muscle activation variability in two simple speech tasks that move the tongue forward (/ə-ɡis/) vs backward (/ə-suk/). Three dimensional tagged magnetic resonance imaging data were used to inversely drive the biomechanical models in four English speakers. Results show that the genioglossus is the workhorse muscle of the tongue, with activity levels of 10% in different subdivisions at different times. Jaw and hyoid positioners (inferior pterygoid and digastric) also show high activation during specific phonemes. Other muscles may be more involved in fine tuning the shapes. For example, slightly more activation of the anterior portion of the transverse is found during apical than laminal /s/, which would protrude the tongue tip to a greater extent for the apical /s/.

Subject-specific biomechanical modelling of the oropharynx with application to speech production

In this work, we develop a 3D subject-specific biomechanical model of the oropharynx in order to investigate and simulate speech production. Our muscle-activated model is generated based on the subject-specific anatomy captured from dynamic volumetric cine-MRI data. Our model includes an air-tight deformable airway that enables speech synthesis. We simulate our model based on actual tissue motion tracked from the tongue during speech production, which we extract from the tagged-MRI data. We quantitatively validate our model on MRI data achieving an average target point tracking error of 1.15mm ± 0.632, and an acoustic formant frequency estimation error of 6.01% ± 4.92%.

Minimally Interactive MRI Segmentation for Subject-Specific Modelling of the Tongue

Subject-Specific biomechanical modelling of the human tongue is beneficial for investigating the inter-subject variability in the physiology of the speech, chewing and swallowing. Delineation of the tongue tissue from MRI is essential for modelling, but still remains a challenge due to the lack of definitive boundary features. In this paper, we propose a minimally interactive inter-subject mesh-to-image registration scheme to tackle 3D segmentation of the tongue from MR volumes. An exemplar expert-delineated template is deformed to match the target volume, constrained based on a shape matching regularization technique. We enable effective minimal user interaction by incorporating additional boundary labels in areas where automatic segmentation is deemed inadequate. We validate our method on 12 normal-subjects. Results indicate an average dice overlap of 0.904 with the ground truth, achieved within 3 min of the expert interaction.

Active Viewing: A Study of Video Highlighting in the Classroom

Video is an increasingly popular medium for education. Motivated by the problem of video as a one-way medium, this paper investigates the ways in which learners» active interaction with video materials contributes to active learning. In this study, we examine active viewing behaviors, specifically seeking and highlighting within videos, which may suggest greater levels of participation and learning. We deployed a system designed for active viewing to an undergraduate class for a semester. The analysis of online activity traces and interview data provided novel findings on video highlighting behavior in educational contexts.

A 3D dynamic biomechanical swallowing model for training and diagnosis of dysphagia

We present a three dimensional (3D) biomechanical swallowing model of the oral, pharyngeal and laryngeal (OPAL) muscles and structures. Such modeling may aid in predicting functional outcomes in swallowing disorder (i.e. dysphagia) treatment and could significantly reduce therapy time. Our physics-based model captures the OPAL anatomical geometries and kinematics from 2D animations constructed from video-fluoroscopic (VF) evaluations of real patient swallowing events using the Modified Barium Swallow Impairment Profile (MBSImP™©) protocol. We investigate the upper airway dynamics with these clinically accurate kinematics and geometries. We use smoothed particle hydrodynamics (SPH) modeling of water-like and nectar-like fluid boluses, simulated within an airway-skin mesh that encompasses our modeled 3D structures and follows the models dynamics. We demonstrate that our model can simulate a bolus in a manner consistent with clinical data, and can robustly handle fluid with different viscosity incorporating a wide range of moving boundary conditions.

FRANK: A Hybrid 3D Biomechanical Model of the Head and Neck

Abstract We describe our approach to construct FRANK: a Functional Reference ANatomical Knowledge (FRANK) template of the head and neck. FRANK consists of a collection of anatomical components made of finite element models (FEM), rigid-bodies, spring-like structures, and various muscle types, all wrapped by an airtight parametrically controlled geometric covering. Its muscles can be activated to mimic complex actions such as swallowing, chewing, and speech, and its modular design allows for components to be replaced and tailored to target-specific applications. The underlying biomechanical modeling toolkit, ArtiSynth, uses a hybrid finite-element and multibody technique that is essential in allowing simulation of such processes within reasonable computation times. We also describe common challenges and various approaches to building hybrid models, such as FRANK, enabling the combination of organs into a unified framework. When combined with inverse modeling techniques, these hybrid models can be applied to a wide variety of applications, including modeling of function. We demonstrate some applications of FRANK, including swallowing, mastication, speech, and patient-specific anatomical modeling.