{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:06:18Z","timestamp":1791392778197,"version":"4.3.3"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:00:00Z","timestamp":1758672000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Speech sound disorders (SSD) in children can significantly impact communication and development. Ultrasound tongue imaging (UTI) is a non-invasive method for visualising tongue motion during speech, offering a promising alternative for diagnosis and therapy. Deep learning (DL) techniques have shown great promise in automating the analysis of UTI data, although their clinical application for SSD remains underexplored.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This review aims to synthesise how DL has been utilised in UTI to support automated SSD detection, highlighting the advancement of techniques, key challenges, and future directions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A comprehensive search of IEEE Xplore, PubMed, ScienceDirect, Scopus, Taylor &amp;amp; Francis, and arXiv identified studies from 2010 through 2025. Inclusion criteria focused on studies using DL to analyse UTI data with relevance to SSD classification, feature extraction, or speech assessment. Eleven studies met the criteria: three directly tackled disordered speech classification tasks, while four addressed supporting tasks like tongue contour segmentation and tongue motion modelling. Promising results were reported in each category, but limitations such as small datasets, inconsistent evaluation, and limited generalisability were common.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>DL models demonstrate effectiveness in analysing UTI for articulatory assessment and show early potential in identifying SSD-related patterns. The included studies collectively outline a developmental pipeline, from foundational pre-processing to phoneme-level classification in typically developing speakers, and finally to preliminary attempts at classifying speech errors in children with SSD. This progression illustrates significant technological advances; however, it also emphasises gaps such as the lack of large, disorder-focused datasets and the need for integrated end-to-end systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The field of DL-driven UTI assessment for speech disorders is developing. Current studies provide a strong technical foundation and proof-of-concept for automatic SSD detection using ultrasound, but clinical translation remains limited. Future research should prioritise the creation of larger annotated UTI datasets of disordered speech, developing generalisable and interpretable models, and validating fully integrated DL-UTI pipelines in real-world speech therapy settings. With these advances, DL-based UTI systems have the potential to transform SSD diagnosis and treatment by providing objective, real-time articulatory feedback in a child-friendly manner.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1631134","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T05:43:15Z","timestamp":1758692595000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep learning in ultrasound tongue imaging: a systematic review toward automated detection of speech sound disorders"],"prefix":"10.3389","volume":"8","author":[{"given":"Saja","family":"Al Ani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joanne","family":"Cleland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Zoha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,24]]},"reference":[{"key":"ref1","article-title":"Deep learning-based multi-object tracking: a comprehensive survey from foundations to state-of-the-art","author":"Ad\u017eemovi\u0107","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1007\/s11517-024-03278-7","article-title":"TongueTransUNet: toward effective tongue contour segmentation using well-managed dataset","volume":"63","author":"Al-hammuri","year":"2025","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.3390\/diagnostics12112811","article-title":"Tongue contour tracking and segmentation in lingual ultrasound for speech recognition: a review","volume":"12","author":"Al-hammuri","year":"2022","journal-title":"Diagnostics"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"326","DOI":"10.5220\/0012592700003657","article-title":"Automated classification of phonetic segments in child speech using raw ultrasound imaging","volume-title":"Proceedings of the 17th international joint conference on biomedical engineering systems and technologies","author":"Ani","year":"2024"},{"key":"ref5","volume-title":"STAR: Articulation training for young children., in 6th international conference on spoken language processing (ICSLP 2000), (ISCA)","author":"Bunnell","year":"2000"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1111\/1754-9485.13261","article-title":"A review of medical image data augmentation techniques for deep learning applications","volume":"65","author":"Chlap","year":"2021","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"ref7","doi-asserted-by":"crossref","first-page":"399","DOI":"10.4324\/9780429320903-29","article-title":"Ultrasound tongue imaging","volume-title":"Manual of clinical phonetics","author":"Cleland","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1177\/10556656231202448","article-title":"Ultrasound tongue imaging in research and practice with people with cleft palate \u00b1 cleft lip","volume":"62","author":"Cleland","year":"2023","journal-title":"Cleft Palate Craniofacial J."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"103186","DOI":"10.1016\/j.specom.2025.103186","article-title":"Spatio-temporal masked autoencoder-based phonetic segments classification from ultrasound","volume":"169","author":"Dan","year":"2025","journal-title":"Speech Comm."},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1888","DOI":"10.21437\/Interspeech.2018-1736","article-title":"UltraSuite: a repository of ultrasound and acoustic data from child speech therapy sessions","volume-title":"Interspeech. ISCA. 2018","author":"Eshky","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1109\/TBME.2021.3117407","article-title":"Domain adaptation for medical image analysis: a survey","volume":"69","author":"Guan","year":"2022","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2313","DOI":"10.21437\/Interspeech.2023-297","article-title":"Exploiting cross-domain and cross-lingual ultrasound tongue imaging features for elderly and dysarthric speech recognition","volume-title":"INTERSPEECH 2023","author":"Hu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.neucom.2022.05.023","article-title":"A novel tongue segmentation method based on improved U-net","volume":"500","author":"Huang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref14","article-title":"Enhancing image classification with augmentation: data augmentation techniques for improved image classification","author":"Kumar","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/fcomm.2023.1176827","article-title":"Technology use in speech and language therapy: digital participation succeeds through acceptance and use of technology","volume":"8","author":"Leinweber","year":"2023","journal-title":"Front. Commun."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.specom.2022.05.004","article-title":"Wunet: a new network used for ultrasonic tongue contour extraction","volume":"141","author":"Li","year":"2022","journal-title":"Speech Comm."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1080\/02699200500113616","article-title":"Automatic contour tracking in ultrasound images","volume":"19","author":"Li","year":"2005","journal-title":"Clin. Linguist. Phon."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1080\/17549500802676859","article-title":"A systematic review of the association between childhood speech impairment and participation across the lifespan","volume":"11","author":"McCormack","year":"2009","journal-title":"Int. J. Speech Lang. Pathol."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e001761","DOI":"10.1136\/bmjoq-2021-001761","article-title":"Applying evidence to practice by increasing intensity of intervention for children with severe speech sound disorder: a quality improvement project","volume":"11","author":"McFaul","year":"2022","journal-title":"BMJ Open Qual."},{"key":"ref20","volume-title":"Children\u2019s speech: An evidence-based approach to assessment and intervention","author":"McLeod","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"2940","DOI":"10.1121\/1.5137212","article-title":"Bownet: dilated convolution neural network for ultrasound tongue contour extraction","volume":"146","author":"Mozaffari","year":"2019","journal-title":"J. Acoust. Soc. Am."},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.31234\/osf.io\/zv8y3","article-title":"The role of phonology-to-orthography consistency in predicting the degree of pupil dilation induced in processing reduced and unreduced speech","author":"Mukai","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3791\/55123","article-title":"Ultrasound images of the tongue: a tutorial for assessment and remediation of speech sound errors","author":"Preston","year":"2017","journal-title":"J. Vis. Exp."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.specom.2021.02.001","article-title":"Exploiting ultrasound tongue imaging for the automatic detection of speech articulation errors","volume":"128","author":"Ribeiro","year":"2021","journal-title":"Speech Comm."},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1109\/ICASSP.2019.8683564","article-title":"Speaker-independent classification of phonetic segments from raw ultrasound in child speech","volume-title":"ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"Ribeiro","year":"2019"},{"key":"ref26","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention\u2013MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.specom.2015.04.002","article-title":"Tabby talks: an automated tool for the assessment of childhood apraxia of speech","volume":"70","author":"Shahin","year":"2015","journal-title":"Speech Comm."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: a survey","volume":"88","author":"Shamshad","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"3874","DOI":"10.17605\/OSF.IO\/3BYVP","article-title":"A pilot fieldwork ultrasound study of tongue shape variability in children with and without speech sound disorder: international congress of phonetic sciences","author":"Smith","year":"2023","journal-title":"Proc. 20th Int. Congr. Phon. Sci. Prague 2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2024.1398393","article-title":"A survey on deep learning in medical ultrasound imaging","volume":"12","author":"Song","year":"2024","journal-title":"Front. Phys."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1080\/02699200500113558","article-title":"A guide to analysing tongue motion from ultrasound images","volume":"19","author":"Stone","year":"2005","journal-title":"Clin. Linguist. Phon."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1016\/j.media.2012.07.001","article-title":"Tongue contour tracking in dynamic ultrasound via higher-order MRFs and efficient fusion moves","volume":"16","author":"Tang","year":"2012","journal-title":"Med. Image Anal."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1044\/2015_JSLHR-S-14-0282","article-title":"Prevalence and predictors of persistent speech sound disorder at eight years old: findings from a population cohort study","volume":"59","author":"Wren","year":"2016","journal-title":"J. Speech Lang. Hear. Res."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.1121\/10.0028610","article-title":"A systematic review of the application of machine learning techniques to ultrasound tongue imaging analysis","volume":"156","author":"Xia","year":"2024","journal-title":"J. Acoust. Soc. Am."},{"key":"ref9001","first-page":"226","article-title":"Masked Modeling-Based Ultrasound Image Classification via Self-Supervised Learning","volume-title":"IEEE Open J Eng Med Biol","author":"Xu","year":"2024"},{"key":"ref35","first-page":"1","article-title":"Raw ultrasound-based phonetic segments classification via mask Modeling","volume-title":"ICASSP 2023\u20132023 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"You","year":"2023"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"5926","DOI":"10.1109\/ICASSP.2019.8683081","article-title":"Predicting tongue motion in Unlabeled ultrasound videos using convolutional Lstm neural networks","volume-title":"ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"Zhao","year":"2019"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1631134\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T05:43:19Z","timestamp":1758692599000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1631134\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,24]]},"references-count":37,"alternative-id":["10.3389\/frai.2025.1631134"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1631134","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,24]]},"article-number":"1631134"}}