Test–retest repeatability of human speech biomarkers from static and real-time dynamic magnetic resonance imaging

Töger, Johannes; Sorensen, Tanner; Somandepalli, Krishna; Toutios, Asterios; Lingala, Sajan Goud; Narayanan, Shrikanth; Nayak, Krishna S.

doi:10.1121/1.4983081

Cited by 19 publications

(16 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been occasions in which ICC(1,1) and ICC(3,1) have been explicitly employed at times in the literature. For example, ICC(1,1) has been applied to brain networks based on resting‐state fMRI data (Wang et al, ), to functional near‐infrared spectroscopy (fNIRS) data (e.g., Bhambhani, Maikala, Farag, & Rowland, ; Plichta et al, ; Tian et al, ; Zhang et al, ), and to resting‐state data at the whole‐brain level (Zuo et al, ), and to task‐related data through LME at the regional level (Töger et al, ). However, we note that in a large number of publications, the adoption of the ICC type was neither explicitly explained nor justified, which makes precise interpretation difficult.…”

Section: Literature Survey Of Icc For Neuroimagingmentioning

confidence: 99%

Intraclass correlation: Improved modeling approaches and applications for neuroimaging

Chen

Taylor

Haller

et al. 2017

Human Brain Mapping

115

View full text Add to dashboard Cite

Intraclass correlation (ICC) is a reliability metric that gauges similarity when, for example, entities are measured under similar, or even the same, well-controlled conditions, which in MRI applications include runs/sessions, twins, parent/child, scanners, sites, and so on. The popular definitions and interpretations of ICC are usually framed statistically under the conventional ANOVA platform. Here, we provide a comprehensive overview of ICC analysis in its prior usage in neuroimaging, and we show that the standard ANOVA framework is often limited, rigid, and inflexible in modeling capabilities. These intrinsic limitations motivate several improvements. Specifically, we start with the conventional ICC model under the ANOVA platform, and extend it along two dimensions: first, fixing the failure in ICC estimation when negative values occur under degenerative circumstance, and second, incorporating precision information of effect estimates into the ICC model. These endeavors lead to four modeling strategies: linear mixed-effects (LME), regularized mixed-effects (RME), multilevel mixed-effects (MME), and regularized multilevel mixed-effects (RMME). Compared to ANOVA, each of these four models directly provides estimates for fixed effects and their statistical significances, in addition to the ICC estimate. These new modeling approaches can also accommodate missing data and fixed effects for confounding variables. More importantly, we show that the MME and RMME approaches offer more accurate characterization and decomposition among the variance components, leading to more robust ICC computation. Based on these theoretical considerations and model performance comparisons with a real experimental dataset, we offer the following general-purpose recommendations. First, ICC estimation through MME or RMME is preferable when precision information (i.e., weights that more accurately allocate the variances in the data) is available for the effect estimate; when precision information is unavailable, ICC estimation through LME or the RME is the preferred option. Second, even though the absolute agreement version, ICC(2,1), is presently more popular in the field, the consistency version, ICC(3,1), is a practical and informative choice for whole-brain ICC analysis that achieves a well-balanced compromise when all potential fixed effects are accounted for. Third, approaches for clear, meaningful, and useful result reporting in ICC analysis are discussed. All models, ICC formulations, and related statistical testing methods have been implemented in an open source program 3dICC, which is publicly available as part of the AFNI suite. Even though our work here focuses on the whole-brain level, the modeling strategy and recommendations can be equivalently applied to other situations such as voxel, region, and network levels.

show abstract

Section: Literature Survey Of Icc For Neuroimagingmentioning

confidence: 99%

Intraclass correlation: Improved modeling approaches and applications for neuroimaging

Chen

Taylor

Haller

et al. 2017

Human Brain Mapping

115

View full text Add to dashboard Cite

show abstract

“…Dynamic rtMRI data were collected during production of running speech from eight healthy volunteers (4F/4M, age: 28.3 ± 4.3). The details of the experimental protocol used can be found in [15]. All imaging was performed on a GE Signa Excite 1.5T scanner with a custom eight-channel upper airway coil [1].…”

Section: Data and Label Generationmentioning

confidence: 99%

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

Somandepalli¹,

Toutios²,

Narayanan³

2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

Recent developments in real-time magnetic resonance imaging (rtMRI) have enabled the study of vocal tract dynamics during production of running speech at high frame rates (e.g., 83 frames per second). Such large amounts of acquired data require scalable automated methods to identify different articulators (e.g., tongue, velum) for further analysis. In this paper, we propose a convolutional neural network with an encoderdecoder architecture to jointly detect the relevant air-tissue boundaries as well as to label them, which we refer to as 'semantic edge detection'. We pose this as a pixel labeling problem, with the outline contour of each articulator of interest as positive class and the remaining tissue and airway as negative classes. We introduce a loss function modified with additional penalty for misclassification at air-tissue boundaries to account for class imbalance and improve edge localization. We then use a greedy search algorithm to draw contours from the probability maps of the positive classes predicted by the network. The articulator contours obtained by our method are comparable to the true labels generated by iteratively fitting a manually created subject-specific template. Our results generalize well across subjects and different vocal tract postures, demonstrating a significant improvement over the structured regression baseline.

show abstract

“…Reconstruction was performed using the Berkeley Advanced Reconstruction Toolbox (BART) [11]. The MRI sequence and experiment protocol was previously reported ( [9], §2).…”

Section: Image Acquisition and Reconstructionmentioning

confidence: 99%

“…Advances in real-time magnetic resonance imaging (rtMRI) have achieved a balance among the competing factors of temporal resolution, spatial resolution, and signal-to-noise ratio that allows for the characterization of vocal tract shaping during speech production [7,8]. Alongside these advances in acquisition and reconstruction have grown computational approaches to extract quantitative imaging biomarkers from rtMRI [9]. Increasingly complex computational methods promise to provide * now at Lund University biomarkers of articulatory strategies [10].…”

Section: Introductionmentioning

confidence: 99%

Test-Retest Repeatability of Articulatory Strategies Using Real-Time Magnetic Resonance Imaging

et al. 2017

Self Cite

View full text Add to dashboard Cite

Real-time magnetic resonance imaging (rtMRI) provides information about the dynamic shaping of the vocal tract during speech production. This paper introduces and evaluates a method for quantifying articulatory strategies using rtMRI. The method decomposes the formation and release of a constriction in the vocal tract into the contributions of individual articulators such as the jaw, tongue, lips, and velum. The method uses an anatomically guided factor analysis and dynamical principles from the framework of Task Dynamics. We evaluated the method within a test-retest repeatability framework. We imaged healthy volunteers (n = 8, 4 females, 4 males) in two scans on the same day and quantified inter-study agreement with the intraclass correlation coefficient and mean within-subject standard deviation. The evaluation established a limit on effect size and intra-group differences in articulatory strategy which can be studied using the method.

show abstract

Test–retest repeatability of human speech biomarkers from static and real-time dynamic magnetic resonance imaging

Cited by 19 publications

References 72 publications

Intraclass correlation: Improved modeling approaches and applications for neuroimaging

Intraclass correlation: Improved modeling approaches and applications for neuroimaging

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

Test-Retest Repeatability of Articulatory Strategies Using Real-Time Magnetic Resonance Imaging

Contact Info

Product

Resources

About