SCH: Computer Vision Algorithms to Detect Tics In Patients with Tourette Syndrome

SCH：用于检测抽动秽语综合征患者抽动的计算机视觉算法

• 批准号: 10817272
• 负责人: Joseph McGuire
• 金额: $ 30万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-18 至 2027-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10817272
• 关键词: Adverse effects; Affect; Algorithms; Architecture; Attention; Awareness; Behavior Therapy; Behavioral; Biomedical Engineering; Body part; Categories; Childhood; Classification; Clinical; Clinical assessments; Complex; Computer Vision Systems; Data; Detection; Discrimination; Evaluation; Exhibits; FDA approved; Face; Feedback; Gestures; Gilles de la Tourette syndrome; Goals; Grain; Health; Health Professional; Human; Impairment; Joints; Knowledge; Label; Learning; Learning Skill; Machine Learning; Modeling; Movement; Multiple Partners; Ontology; Outcome; Participant; Patient-Focused Outcomes; Patients; Performance; Pharmaceutical Preparations; Population; Process; Published Comment; Recommendation; Research; System; Techniques; Technology; Therapeutic; Tic disorder; Training; Work; Youth; automated algorithm; convolutional neural network; deep learning; design; digital; improved; innovation; innovative technologies; learning strategy; multimodality; neuropsychiatry; novel; sensor; side effect; skeletal; skills; spatiotemporal; supervised learning; therapy outcome; tool; treatment response; user-friendly; Adverse effects; Affect; Algorithms; Architecture; Attention; Awareness; Behavior Therapy; Behavioral; Biomedical Engineering; Body part; Categories; Childhood; Classification; Clinical; Clinical assessments; Complex; Computer Vision Systems; Data; Detection; Discrimination; Evaluation; Exhibits; FDA approved; Face; Feedback; Gestures; Gilles de la Tourette syndrome; Goals; Grain; Health; Health Professional; Human; Impairment; Joints; Knowledge; Label; Learning; Learning Skill; Machine Learning; Modeling; Movement; Multiple Partners; Ontology; Outcome; Participant; Patient-Focused Outcomes; Patients; Performance; Pharmaceutical Preparations; Population; Process; Published Comment; Recommendation; Research; System; Techniques; Technology; Therapeutic; Tic disorder; Training; Work; Youth; automated algorithm; convolutional neural network; deep learning; design; digital; improved; innovation; innovative technologies; learning strategy; multimodality; neuropsychiatry; novel; sensor; side effect; skeletal; skills; spatiotemporal; supervised learning; therapy outcome; tool; treatment response; user-friendly

Tourette Syndrome (TS) onsets in childhood, affects 1% of the population, and causes substantial impairment. Health professionals recommend behavior therapy as the first-line treatment for TS due to its efficacy and adverse effect profile. In behavior therapy, patients learn tic management skills and are assigned “homework” to solidify skill learning. Core skills involve building awareness to tic occurrence and implementing behavioral strategies to inhibit tic expression upon such awareness. Youth who exhibit a treatment response to behavior therapy continue to benefit for 10 years. However, more than 50% of patients do not achieve a treatment response and rely upon FDA-approved medications that have detrimental health effects. A key challenge with behavior therapy is the reliance on a human practice partner for “homework” due to accessibility and accuracy. Our team will create an activity-based recognition system and algorithms to identify and classify tics across activities and sensor viewpoints in patients with TS. This system will evolve into a therapeutic tool (i.e., a “digital practice partner”) that is scalable, accessible, and accurate in detecting tics. This will enable patients to effectively practice behavior therapy skills and achieve optimal long-term outcomes. First, we will develop a multi-view sensor system to observe tics in patients with TS and refine our hierarchical ontology of tics to annotate data collected from our sensor system. This will enable both a clinically interpretable and fine-grained classification of tic and non-tic movements. Second, we will design a novel spatio-temporal CNN called Tic-Net for fine-grained detection of facial and upper body tics in video data from multiple viewpoints, which will rely on facial action unit intensities and interpretable upper body part features that we design, temporal segmentation and detection networks, as well as contrastive and self-supervised learning losses to detect tics without requiring large amounts of annotations. Third, we will design a novel spatio-temporal Transformer architecture called Tic-DETR for fine-grained tic detection, which captures long-range interactions among face action units and/or skeletal joints across multiple views as well as relations between tic instances to produce interpretable detections of tics of varying durations from multiple viewpoints. Finally, we will compare detection outcomes between our algorithm and a human practice partner, evaluate the robustness of algorithms across viewpoints, and assess its clinical interpretability.

童年时期的Tourette综合征（TS）洋溢，影响1％的人口，并造成重大损害。卫生专业人员建议行为疗法作为TS的一线治疗，因为其有效性和不良效果。在行为疗法中，患者学习TIC管理技能，并被指定“作业”以巩固技能学习。核心技能涉及建立对发生的意识，并实施行为策略，以抑制这种意识的表达。对行为疗法的治疗反应的年轻人继续受益10年。但是，超过50％的患者未达到治疗反应，并依赖于有害健康影响的FDA批准药物。行为疗法的主要挑战是由于可及性和准确性而依赖人类实践伙伴“作业”。我们的团队将创建一种基于活动的识别系统和算法，以识别和对TS患者的活动和传感器观点进行识别和分类。该系统将演变为可扩展，易于访问且准确检测抽动的治疗工具（即“数字实践伙伴”）。这将使患者能够有效地练习行为疗法技能并实现最佳的长期结局。首先，我们将开发一个多视图传感器系统，以观察TS患者的抽动，并完善我们的TICS的分层本体，以注释从我们的传感器系统中收集的数据。这将使TIC和非TIC运动的临床解释和细粒度分类既可以。其次，我们将设计一个名为TIC-NET的新型时空CNN，用于从多个角度进行视频数据中对面部和上身抽动的细粒度检测，这将依赖于面部动作单元的强度和可解释的上半身的特征，我们设计，临时细分和临时段和检测网络，以及不需要的学习损失，而不需要大量的学习损失。第三，我们将设计一种称为TIC-DET的新型时空变压器结构，用于细粒度的TIC检测，该检测捕获了跨多个视图的面部动作单元和/或骨骼关节之间的长距离相互作用，以及TIC实例之间的关系，从多个角度来看，从多个角度来看，可以产生可解释的泰式检测。最后，我们将比较我们的算法与人类实践伙伴之间的检测结果，评估跨观点算法的鲁棒性，并评估其临床解释性。