pr\u00e9sentent<\/p>\n\n\n\n
Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en :<\/p>\n\n\n\n
le JEUDI 16 JANVIER 2025 \u00e0 14h00<\/p>\n\n\n\n
\u00e0<\/p>\n\n\n\n
Amphith\u00e9\u00e2tre 2
T\u00e9l\u00e9com SudParis, 19 rue Marguerite PEREY 91120 PALAISEAU,<\/p>\n\n\n\n
Membres du jury :<\/strong><\/p>\n\n\n\n M. Mounim A. EL YACOUBI<\/strong>, Professeur, T\u00e9l\u00e9com SudParis, FRANCE – Directeur de these Invit\u00e9 :<\/strong><\/p>\n\n\n\n Mme JEANCOLAS Laetitia<\/strong>, post-doctorante, Institut du cerveau de l’H\u00f4pital de la Piti\u00e9-Salp\u00eatri\u00e8re, FRANCE<\/p>\n\n\n\n R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\n Cette th\u00e8se vise \u00e0 d\u00e9velopper des biomarqueurs num\u00e9riques robustes pour la d\u00e9tection pr\u00e9coce de la maladie de Parkinson (MP) en analysant des vid\u00e9os faciales afin d’identifier les changements associ\u00e9s \u00e0 l’hypomimie. Dans ce contexte, nous introduisons de nouvelles contributions \u00e0 l’\u00e9tat de l’art : l’une fond\u00e9e sur l\u2019apprentissage automatique superficiel et l\u2019autre fond\u00e9e sur l’apprentissage profond. La premi\u00e8re m\u00e9thode utilise des mod\u00e8les d’apprentissage automatique qui exploitent des caract\u00e9ristiques faciales extraites manuellement, en particulier les d\u00e9riv\u00e9s des unit\u00e9s d’action faciale (AUs). Ces mod\u00e8les int\u00e8grent des m\u00e9canismes d’interpr\u00e9tabilit\u00e9 qui permettent d’expliquer leur processus de d\u00e9cision aupr\u00e8s des parties prenantes, mettant en \u00e9vidence les caract\u00e9ristiques faciales les plus distinctives pour la MP. Nous examinons l’influence du sexe biologique sur ces biomarqueurs num\u00e9riques, les comparons aux donn\u00e9es de neuroimagerie et aux scores cliniques, et les utilisons pour pr\u00e9dire la gravit\u00e9 de la MP. La deuxi\u00e8me m\u00e9thode exploite l’apprentissage profond pour extraire automatiquement des caract\u00e9ristiques \u00e0 partir de vid\u00e9os faciales brutes et des donn\u00e9es de flux optique en utilisant des mod\u00e8les fondamentaux bas\u00e9s sur les Vision Transformers pour vid\u00e9os. Pour pallier le manque de donn\u00e9es d’entra\u00eenement, nous proposons des techniques avanc\u00e9es d’apprentissage par transfert adaptatif, en utilisant des mod\u00e8les fondamentaux entra\u00een\u00e9s sur de grands ensembles de donn\u00e9es pour la classification de vid\u00e9os. De plus, nous int\u00e9grons des m\u00e9canismes d’interpr\u00e9tabilit\u00e9 pour \u00e9tablir la relation entre les caract\u00e9ristiques extraites automatiquement et les AUs faciales extraites manuellement, am\u00e9liorant ainsi la clart\u00e9 des d\u00e9cisions des mod\u00e8les. Enfin, nos caract\u00e9ristiques faciales g\u00e9n\u00e9r\u00e9es proviennent \u00e0 la fois de donn\u00e9es transversales et longitudinales, ce qui offre un avantage significatif par rapport aux travaux existants. Nous utilisons ces enregistrements pour analyser la progression de l’hypomimie au fil du temps avec ces marqueurs num\u00e9riques, et sa corr\u00e9lation avec la progression des scores cliniques. La combinaison des deux approches propos\u00e9es permet d’obtenir une AUC (Area Under the Curve) de classification de plus de 90%, d\u00e9montrant l’efficacit\u00e9 des mod\u00e8les d’apprentissage automatique et d’apprentissage profond dans la d\u00e9tection de l’hypomimie chez les patients atteints de MP \u00e0 un stade pr\u00e9coce via des vid\u00e9os faciales. Cette recherche pourrait permettre une surveillance continue de l’hypomimie en dehors des environnements hospitaliers via la t\u00e9l\u00e9m\u00e9decine. Abstract :<\/strong><\/p>\n\n\n\n This thesis aims to develop robust digital biomarkers for early detection of Parkinson’s disease (PD) by analyzing facial videos to identify changes associated with hypomimia. In this context, we introduce new contributions to the state of the art: one based on shallow machine learning and the other on deep learning. The first method employs machine learning models that use manually extracted facial features, particularly derivatives of facial action units (AUs). These models incorporate interpretability mechanisms that explain their decision-making process for stakeholders, highlighting the most distinctive facial features for PD. We examine the influence of biological sex on these digital biomarkers, compare them against neuroimaging data and clinical scores, and use them to predict PD severity. The second method leverages deep learning to automatically extract features from raw facial videos and optical flow using foundational models based on Video Vision Transformers. To address the limited training data, we propose advanced adaptive transfer learning techniques, utilizing foundational models trained on large-scale video classification datasets. Additionally, we integrate interpretability mechanisms to clarify the relationship between automatically extracted features and manually extracted facial AUs, enhancing the comprehensibility of the model\u2019s decisions. Finally, our generated facial features are derived from both cross-sectional and longitudinal data, which provides a significant advantage over existing work. We use these recordings to analyze the progression of hypomimia over time with these digital markers, and its correlation with the progression of clinical scores. Combining these two approaches allows for a classification AUC (Area Under the Curve) of over 90%, demonstrating the efficacy of machine learning and deep learning models in detecting hypomimia in early-stage PD patients through facial videos. This research could enable continuous monitoring of hypomimia outside hospital settings via telemedicine.<\/p>\n","protected":false},"excerpt":{"rendered":" L’Ecole doctorale : Ecole Doctorale de l’Institut Polytechnique de Paris et le Laboratoire de recherche SAMOVAR – Services r\u00e9partis, Architectures, Mod\u00e9lisation, Validation, Administration des R\u00e9seaux pr\u00e9sentent l\u2019AVIS DE SOUTENANCE de Monsieur Anas FILALI RAZZOUKI Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en […]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[286,169],"tags":[],"class_list":["post-6760","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaires-armedia","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6760","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=6760"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6760\/revisions"}],"predecessor-version":[{"id":6761,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6760\/revisions\/6761"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=6760"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=6760"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=6760"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
M. Hui YU<\/strong>, Full professor, University of Glasgow, ROYAUME-UNI – Rapporteur
M. Julian FIERREZ AGUILAR <\/strong>, Full professor, Universit\u00e9 autonome de Madrid, ESPAGNE – Rapporteur
Mme Chrystalina ANTONIADES<\/strong>, Associate Professor, University of Oxford, ROYAUME-UNI – Examinateur
M. Holger FROEHLICH<\/strong>, Full professor, University of Bonn & Fraunhofer SCAI, ALLEMAGNE – Examinateur
M. Jean-Christophe CORVOL<\/strong>, Full professor, Sorbonne Universit\u00e9 & H\u00f4pital de la Piti\u00e9-Salp\u00eatri\u00e8re, FRANCE – Examinateur
Mme Dijana PETROVSKA<\/strong>, Emeritus Associate Professor, T\u00e9l\u00e9com SudParis, FRANCE – Co-encadrant de these<\/p>\n\n\n\n<\/h2>\n\n\n\n
\u00ab MARQUEURS NUM\u00c9RIQUES FACIAUX DE L\u2019HYPOMIMIE FOND\u00c9S SUR L’APPRENTISSAGE PROFOND POUR LA D\u00c9TECTION PR\u00c9COCE ET L’ANALYSE DE LA MALADIE DE PARKINSON \u00bb<\/h2>\n\n\n\n
pr\u00e9sent\u00e9 par Monsieur Anas FILALI RAZZOUKI<\/h2>\n\n\n\n
<\/p>\n\n\n\n