Trassandra Jewelle Ipapo
ABSTRACT
Stroke and amyotrophic lateral sclerosis manifest symptoms that affect facial motion in patients. Tracking these movements and assessing the severity of the impairment can be achieved with facial alignment technology and classification algorithms. Using the Toronto NeuroFace Dataset consisting of patients and healthy individuals performing clinical examination tasks, this study focuses on score estimation of clinical examinations to determine oro-facial dysfunction severity. Facial landmarks extracted using the 2D FAN were used to determine features under range of motion, speed of motion, and symmetry. Speech language pathologist scores from the dataset were transformed using ordinal encoding, then oversampled using random oversampling. The features and transformed scores were fed into random forest classifier models to predict a score using a scale of 1 to 4 for each feature category. The results show that the proposed method is able to estimate oro-facial dysfunction severity and classify between healthy individuals and patients. The average performance of the model setups are comparable to that of the baseline in terms of accuracy (<5% difference), accuracy±1 (<2% difference), binary accuracy (<3% difference), and specificity (<7% difference).
- [n. d.]. Orofacial Myofunctional Disorders. https://www.asha.org/public/speech/disorders/orofacial-myofunctional-disorders/Google Scholar
- [n. d.]. What is a Neurologic Disorder?https://www.childneurologyfoundation.org/what-is-a-neurologic-disorder/Google Scholar
- 2020. Estimating Local Healthcare Capacity to Deal with COVID-19 Case Surge: Analysis and Recommendations. https://up.edu.ph/estimating-local-healthcare-capacity-to-deal-with-covid-19-case-surge-analysis-and-recommendations/Google Scholar
- 2022. Treat and Recover from Stroke. https://www.cdc.gov/stroke/treatments.htm?CDC_AA_refVal=https%3A%2F%2Fwww.cdc.gov%2Fstroke%2Frecovery.htmGoogle Scholar
- Andrea Bandini, Jordan R. Green, Silvia Orlandi, Babak Taati, Lorne Zinman, and Yana Yunusova. 2018. Automatic Detection of Amyotrophic Lateral Sclerosis (ALS) from Video-Based Analysis of Facial Movements: Speech and Non-Speech Tasks. 150–157. https://doi.org/10.1109/FG.2018.00031Google ScholarDigital Library
- Andrea Bandini, Jordan R. Green, Brian Richburg, and Yana Yunusova. 2018. Automatic Detection of Orofacial Impairment in Stroke. In Proc. Interspeech 2018. 1711–1715. https://doi.org/10.21437/Interspeech.2018-2475Google ScholarCross Ref
- Andrea Bandini, Sia Rezaei, Diego L. Guarín, Madhura Kulkarni, Derrick Lim, Mark I. Boulos, Lorne Zinman, Yana Yunusova, and Babak Taati. 2021. A New Dataset for Facial Motion Analysis in Individuals With Neurological Disorders. IEEE Journal of Biomedical and Health Informatics 25, 4 (2021), 1111–1119. https://doi.org/10.1109/JBHI.2020.3019242Google ScholarCross Ref
- Ivan Paul Bondoc, Viannery Mabag, Clarisse Anne Dacanay, and Natasha Daryle Macapagal. 2017. Speech-language pathology research in the Philippines in retrospect: Perspectives from a developing country. International Journal of Speech-Language Pathology 19, 6 (2017), 628–636. https://doi.org/10.1080/17549507.2016.1226954Google ScholarCross Ref
- Adrian Bulat and Georgios Tzimiropoulos. 2017. How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230, 000 3D facial landmarks). CoRR abs/1703.07332 (2017). https://doi.org/10.48550/arXiv.1703.07332Google ScholarCross Ref
- Bappaditya Debnath, Mary O’Brien, Motonori Yamaguchi, and Ardhendu Behera. 2022. A review of computer vision-based approaches for physical rehabilitation and assessment. Multimedia Systems 28 (2022), 209–239. https://doi.org/10.1007/s00530-021-00815-4Google ScholarDigital Library
- Eibe Frank and Mark Hall. 2001. A Simple Approach to Ordinal Classification. Springer Berlin Heidelberg, Berlin, Heidelberg. 145–156 pages.Google Scholar
- Supasid Jirawatnotai, Pojanan Jomkoh, Tsz Yin Voravitvet, Wuttipong Tirakotai, and Natthawut Somboonsap. 2021. Computerized Sunnybrook facial grading scale (SBface) application for facial paralysis evaluation. Arch Plast Surg 48, 3 (2021), 269–277. https://doi.org/10.5999/aps.2020.01844Google ScholarCross Ref
- Mandy Lu, Kathleen Poston, Adolf Pfefferbaum, Edith V. Sullivan, Li Fei-Fei, Kilian M. Pohl, Juan Carlos Niebles, and Ehsan Adeli. 2020. Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson’s Disease Motor Severity. Med Image Comput Comput Assist Interv. 12263 (2020), 637–647. https://doi.org/10.1007/978-3-030-59716-0_61Google ScholarDigital Library
- Gary H. McCullough, Robert T. Wertz, Russell H. Mills John C. Rosenbek, Katherine B. Ross, and John R. Ashford. 2000. Inter- and intrajudge reliability of a clinical examination of swallowing in adults. Dysphagia 15, 2 (2000), 58–67. https://doi.org/10.1007/s004550010002Google ScholarCross Ref
- Stanford Medicine. 2023. What is Synkinesis?https://med.stanford.edu/ohns/OHNS-healthcare/facialnervecenter/conditions-we-treat/synkinesis.html#: :text=Synkinesis%20describes%20unwanted%20contractions%20of,spasms%20during%20routine%20facial%20movementsGoogle Scholar
- Patricia B. Mirasol. 2022. State clinics barely fill healthcare void in the Philippines. (2022). https://www.bworldonline.com/top-stories/2022/03/14/435670/state-clinics-barely-fill-healthcare-void-in-the-philippines/Google Scholar
- Gareth Morinan, Yuwei Peng, Samuel Rupprechter, Rimona S. Weil, Louise-Ann Leyland, Thomas Foltynie, Krista Sibley, Fahd Baig, Francesca Morgante, Ro’ee Gilron, Robert Wilt, Philip Starr, and Jonathan O’Keeffe. 2022. Computer-vision based method for quantifying rising from chair in Parkinson’s disease patients. Intelligence-Based Medicine 6 (2022), 100046. https://doi.org/10.1016/j.ibmed.2021.100046Google ScholarCross Ref
- National Institute of Neurological Disorders and Stroke. [n. d.]. Amyotrophic Lateral Sclerosis (ALS) Fact Sheet. https://www.ninds.nih.gov/health-information/patient-caregiver-education/fact-sheets/amyotrophic-lateral-sclerosis-als-fact-sheet#topGoogle Scholar
- M. Pediaditis, M. Tsiknakis, V. Bologna, and P. Vorgia. 2011. Model-free vision-based facial motion analysis in epilepsy. In 2011 10th International Workshop on Biomedical Engineering. 1–4. https://doi.org/10.1109/IWBE.2011.6079051Google ScholarCross Ref
- Samuel Rupprechter, Gareth Morinan, Yuwei Peng, Thomas Foltynie, Krista Sibley, Rimona S. Weil, Louise-Ann Leyland, Fahd Baig, Francesca Morgante, Ro’ee Gilron, Robert Wilt, Philip Starr, Robert A. Hauser, and Jonathan O’Keeffe. 2021. A Clinically Interpretable Computer-Vision Based Method for Quantifying Gait in Parkinson’s Disease. Sensors 21, 16 (2021). https://doi.org/10.3390/s21165437Google ScholarCross Ref
- W. S. W. Samsudin, K. Sundaraj, A. Ahmad, and H. Salleh. 2016. Initial assessment of facial nerve paralysis based on motion analysis using an optical flow method. Technology and Health Care 24, 2 (2016), 287–294. https://doi.org/10.3233/THC-151103Google ScholarDigital Library
Index Terms
- Clinical Score Estimation for Determining Oro-Facial Dysfunction Severity
Recommendations
Frontal face synthesis based on multiple pose-variant images for face recognition
ICB'07: Proceedings of the 2007 international conference on Advances in BiometricsPose variance remains a challenging problem for face recognition. In this paper, a stereoscopic synthesis method for generating a frontal face image is proposed to improve the performance of automatic face recognition system. Through this method, a ...
Classification of severity of trachea stenosis from EEG signals using ordinal decision-tree based algorithms and ensemble-based ordinal and non-ordinal algorithms
Highlights- EEG signals are used for the identification of airway obstruction levels.
- A new ...
AbstractMachine learning is integrated nowadays in many data-driven applications that attempt to model the behavior of a system. Thus, the implementation of machine-learning algorithms for medical applications is growing, enabling doctors to ...
Comments