Deep Learning Pose Estimation for Multi-Label Recognition of Combined Hyperkinetic Movement Disorders
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910006631202816 |
|---|---|
| author | Cif, Laura Demailly, Diane Horvàth, Gabriella A. Escobar, Juan Dario Ortigoza Dorison, Nathalie Jiménez, Mayté Castro Hubsch, Cécile A. Wirth, Thomas Hariz, Gun-Marie Huby, Sophie Dornadic, Morgan Souei, Zohra Rehman, Muhammad Mushhood Ur Hemm, Simone Boulayme, Mehdi Moraud, Eduardo M. Bloch, Jocelyne Vasques, Xavier |
| author_facet | Cif, Laura Demailly, Diane Horvàth, Gabriella A. Escobar, Juan Dario Ortigoza Dorison, Nathalie Jiménez, Mayté Castro Hubsch, Cécile A. Wirth, Thomas Hariz, Gun-Marie Huby, Sophie Dornadic, Morgan Souei, Zohra Rehman, Muhammad Mushhood Ur Hemm, Simone Boulayme, Mehdi Moraud, Eduardo M. Bloch, Jocelyne Vasques, Xavier |
| contents | Hyperkinetic movement disorders (HMDs) such as dystonia, tremor, chorea, myoclonus, and tics are disabling motor manifestations across childhood and adulthood. Their fluctuating, intermittent, and frequently co-occurring expressions hinder clinical recognition and longitudinal monitoring, which remain largely subjective and vulnerable to inter-rater variability. Objective and scalable methods to distinguish overlapping HMD phenotypes from routine clinical videos are still lacking. Here, we developed a pose-based machine-learning framework that converts standard outpatient videos into anatomically meaningful keypoint time series and computes kinematic descriptors spanning statistical, temporal, spectral, and higher-order irregularity-complexity features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00163 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deep Learning Pose Estimation for Multi-Label Recognition of Combined Hyperkinetic Movement Disorders Cif, Laura Demailly, Diane Horvàth, Gabriella A. Escobar, Juan Dario Ortigoza Dorison, Nathalie Jiménez, Mayté Castro Hubsch, Cécile A. Wirth, Thomas Hariz, Gun-Marie Huby, Sophie Dornadic, Morgan Souei, Zohra Rehman, Muhammad Mushhood Ur Hemm, Simone Boulayme, Mehdi Moraud, Eduardo M. Bloch, Jocelyne Vasques, Xavier Computer Vision and Pattern Recognition Neurons and Cognition Hyperkinetic movement disorders (HMDs) such as dystonia, tremor, chorea, myoclonus, and tics are disabling motor manifestations across childhood and adulthood. Their fluctuating, intermittent, and frequently co-occurring expressions hinder clinical recognition and longitudinal monitoring, which remain largely subjective and vulnerable to inter-rater variability. Objective and scalable methods to distinguish overlapping HMD phenotypes from routine clinical videos are still lacking. Here, we developed a pose-based machine-learning framework that converts standard outpatient videos into anatomically meaningful keypoint time series and computes kinematic descriptors spanning statistical, temporal, spectral, and higher-order irregularity-complexity features. |
| title | Deep Learning Pose Estimation for Multi-Label Recognition of Combined Hyperkinetic Movement Disorders |
| topic | Computer Vision and Pattern Recognition Neurons and Cognition |
| url | https://arxiv.org/abs/2602.00163 |