Using ultrasound tongue imaging to analyse maximum performance tasks in children with Autism: a pilot study

Usability of Two Ultrasound Tongue Imaging Devices in Speech-Language Pathology

PURPOSE

Ultrasound tongue imaging is a promising tool in speech-language pathology; however, little is known about the usability of ultrasound scanners for speech-language pathologists (SLPs), who typically have low familiarity with ultrasound imaging. This study looks at the usability of two ultrasound scanner models for SLPs: a Sonosite all-in-one scanner with a wired probe, and a Clarius wireless probe scanner, used with a tablet app.

METHOD

Twelve SLPs and phonetics experts (all female) participated in two filmed sessions in our lab where they learned to use the two models of scanners with custom-written manuals. Each scanner was used in each session to complete a simple task including recording videos of their or the experimenter's tongue. After each use of a scanner, participants completed a modified and translated version of the System Usability Scale. The time required to complete the task was measured. Two expert judges rated the quality of the video recordings.

RESULTS

Participants took less time to complete the task and improved their choice of settings from the first to the second session, regardless of the scanner being used. In the usability scale, SLPs showed a higher satisfaction with the wireless tablet interface than with the all-in-one ultrasound interface. The tablet interface with the wireless scanner also allowed better choices of settings. However, in the second session, positioning of the probe was better with the all-in-one scanner, which has a smaller and lighter probe.

CONCLUSIONS

For SLPs, the usability of a wireless ultrasound scanner with a mobile application seems better than that of an all-in-one scanner. However, its cumbersome probe seems to hamper probe positioning. Future studies should include a lightweight ultrasound scanner that connects via USB to a laptop or tablet and provide image interpretation training for the SLPs.

DAFT-Net: Dual Attention and Fast Tongue Contour Extraction Using Enhanced U-Net Architecture

In most silent speech research, continuously observing tongue movements is crucial, thus requiring the use of ultrasound to extract tongue contours. Precisely and in real-time extracting ultrasonic tongue contours presents a major challenge. To tackle this challenge, the novel end-to-end lightweight network DAFT-Net is introduced for ultrasonic tongue contour extraction. Integrating the Convolutional Block Attention Module (CBAM) and Attention Gate (AG) module with entropy-based optimization strategies, DAFT-Net establishes a comprehensive attention mechanism with dual functionality. This innovative approach enhances feature representation by replacing traditional skip connection architecture, thus leveraging entropy and information-theoretic measures to ensure efficient and precise feature selection. Additionally, the U-Net's encoder and decoder layers have been streamlined to reduce computational demands. This process is further supported by information theory, thus guiding the reduction without compromising the network's ability to capture and utilize critical information. Ablation studies confirm the efficacy of the integrated attention module and its components. The comparative analysis of the NS, TGU, and TIMIT datasets shows that DAFT-Net efficiently extracts relevant features, and it significantly reduces extraction time. These findings demonstrate the practical advantages of applying entropy and information theory principles. This approach improves the performance of medical image segmentation networks, thus paving the way for real-world applications.

Newfound features associated with Hennekam Syndrome (Intestinal Lymphangiectasia-Lymphedema-Intellectual-Disability Syndrome) complicated with comorbid Waldmann's Disease resulting in Celiac Disease

Key Clinical Message

Adequate evaluation of patients with Hennekam Syndrome (HS) is challenging for physicians, because of multi-organ involvement and complex pathophysiology. We report the first case in an African American with lymphedema, who developed protein-losing enteropathy (PLE) and was successfully diagnosed with HS from cause-and-effect complications by Waldmann's Disease (WD) and comorbid Celiac Disease (CD).

Abstract

As far as we know, this is the 51st case of HS worldwide and the first one in an African American. The examined patient met all diagnostic criteria for HS, suggesting a dysfunction in the development of the lymphatic system, with associated comorbidities including developmental delay, gastrointestinal pathologies, facial and hearing abnormalities, and cardiac defects. Primary intestinal lymphangiectasia (WD) is a consequence of HS, which ultimately results in PLE and worsening interstitial lymph buildup. Based on our findings, CD, a complication not yet reported in HS, may arise from WD. Other autoimmune diseases may be seen in HS: a previous report demonstrated positive anti-thyroid stimulating hormone antibodies in HS patients. We propose that in HS, increased interstitial lymph (WD, if intestinal) with protein loss induces TNF-α- and IL-6-mediated immune reactions in the affected visceral organs, causing autoimmune pathologies. The interstitial lymph fluid-induced TNF-α and IL-6-mediated immunopathogenic reactions lead to inflammation and subsequent destruction of the intestinal mucosa. The chronic inflammatory increase in TGF-β causes gastric mucosa hypertrophy, which results in gastric fold thickening. Eventually, wider tight junctions develop, increasing gastric mucosa permeability, and leading to gastropathy. Considering the examined patient's history of gastroenteritis and the literature stating that CD is a non-mucosal cause of gastropathy and PLE, it is suggested that sequelae of GI complications occur in a cause-and-effect chain in HS. HS results in WD, which causes CD, resulting in hypertrophic gastropathy and loss of parietal and chief cells, eventually leading to malabsorption and PLE (Figure 1). HS primarily affects various organs due to inflammatory-mediated damage and accumulation of lymph fluid. Other findings for HS include keratoconjunctivitis sicca (dry eye disease), fibrous lymphedema exhibiting lymphorrhea, chylous ascites, anemia, and parathyroid abnormalities. Immune impairment in HS predisposes patients to autoimmune disorders, therefore autoimmunity (CD) and WD are concomitant comorbidities of HS. HS-associated comorbidities are primarily due to inflammation and damage to immune cell transport or underlying health conditions affecting proper lymphatic function. However, it is suggested that HS mutations may disrupt the development of the lymphatic system leading to further complication. complications can be compound heterozygous, and there is a need for further research to identify nearby genes that can cause concomitant co-morbidity.

Oromotor skills in autism spectrum disorder: A scoping review

Oromotor functioning plays a foundational role in spoken communication and feeding, two areas of significant difficulty for many autistic individuals. However, despite years of research and established differences in gross and fine motor skills in this population, there is currently no clear consensus regarding the presence or nature of oral motor control deficits in autistic individuals. In this scoping review, we summarize research published between 1994 and 2022 to answer the following research questions: (1) What methods have been used to investigate oromotor functioning in autistic individuals? (2) Which oromotor behaviors have been investigated in this population? and (3) What conclusions can be drawn regarding oromotor skills in this population? Seven online databases were searched resulting in 107 studies meeting our inclusion criteria. Included studies varied widely in sample characteristics, behaviors analyzed, and research methodology. The large majority (81%) of included studies report a significant oromotor abnormality related to speech production, nonspeech oromotor skills, or feeding within a sample of autistic individuals based on age norms or in comparison to a control group. We examine these findings to identify trends, address methodological aspects hindering cross-study synthesis and generalization, and provide suggestions for future research.

Tongue Contour Tracking and Segmentation in Lingual Ultrasound for Speech Recognition: A Review

Lingual ultrasound imaging is essential in linguistic research and speech recognition. It has been used widely in different applications as visual feedback to enhance language learning for non-native speakers, study speech-related disorders and remediation, articulation research and analysis, swallowing study, tongue 3D modelling, and silent speech interface. This article provides a comparative analysis and review based on quantitative and qualitative criteria of the two main streams of tongue contour segmentation from ultrasound images. The first stream utilizes traditional computer vision and image processing algorithms for tongue segmentation. The second stream uses machine and deep learning algorithms for tongue segmentation. The results show that tongue tracking using machine learning-based techniques is superior to traditional techniques, considering the performance and algorithm generalization ability. Meanwhile, traditional techniques are helpful for implementing interactive image segmentation to extract valuable features during training and postprocessing. We recommend using a hybrid approach to combine machine learning and traditional techniques to implement a real-time tongue segmentation tool.