請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87724
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 曾宇鳳 | zh_TW |
dc.contributor.advisor | Yufeng Jane Tseng | en |
dc.contributor.author | 楊淯元 | zh_TW |
dc.contributor.author | Yu-Yuan Yang | en |
dc.date.accessioned | 2023-07-19T16:07:46Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-07-19 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-04-10 | - |
dc.identifier.citation | 1. Parkinson, J., An essay on the shaking palsy. The Journal of neuropsychiatry and clinical neurosciences, 2002. 14(2): p. 223-236.
2. Dauer, W. and S. Przedborski, Parkinson's Disease: Mechanisms and Models. Neuron, 2003. 39(6): p. 889-909. 3. Postuma, R.B., et al., MDS clinical diagnostic criteria for Parkinson's disease. Movement Disorders, 2015. 30(12): p. 1591-1601. 4. Goetz, C.G., et al., Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS): Scale presentation and clinimetric testing results. Movement Disorders, 2008. 23(15): p. 2129-2170. 5. Singh, N., V. Pillay, and Y.E. Choonara, Advances in the treatment of Parkinson's disease. Progress in Neurobiology, 2007. 81(1): p. 29-44. 6. Zesiewicz, T.A., Parkinson Disease. Continuum (Minneap Minn), 2019. 25(4): p. 896-918. 7. Armstrong, M.J. and N. McFarland, Recognizing and treating atypical Parkinson disorders. Handb Clin Neurol, 2019. 167: p. 301-320. 8. Fanciulli, A. and G.K. Wenning, Multiple-system atrophy. N Engl J Med, 2015. 372(3): p. 249-63. 9. Greene, P., Progressive Supranuclear Palsy, Corticobasal Degeneration, and Multiple System Atrophy. Continuum (Minneap Minn), 2019. 25(4): p. 919-935. 10. Wenning, G.K., et al., The Movement Disorder Society Criteria for the Diagnosis of Multiple System Atrophy. Movement Disorders, 2022. 37(6): p. 1131-1148. 11. Sarapata, G., et al., Video-based activity recognition for automated motor assessment of Parkinson’s disease. 2022. 12. Morinan, G., et al., Computer vision quantification of whole-body Parkinsonian bradykinesia using a large multi-site population. npj Parkinson's Disease, 2023. 9(1). 13. Sibley, K.G., et al., Video-based analyses of Parkinson’s disease severity: A brief review. Journal of Parkinson's Disease, 2021. 11(s1): p. S83-S93. 14. Coravos, A., S. Khozin, and K.D. Mandl, Developing and adopting safe and effective digital biomarkers to improve patient outcomes. npj Digital Medicine, 2019. 2(1). 15. Zhang, H., et al., Deep Learning Identifies Digital Biomarkers for Self-Reported Parkinson's Disease. Patterns, 2020. 1(3): p. 100042. 16. Society, T.M.D. UPDRS評估量表中文版. 2020; Available from: http://www.tmds.org.tw/files/knowledge/N20200525153048_001.pdf. 17. Tăuţan, A.-M., B. Ionescu, and E. Santarnecchi, Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques. Artificial Intelligence in Medicine, 2021. 117: p. 102081. 18. Mei, J., C. Desrosiers, and J. Frasnelli, Machine learning for the diagnosis of Parkinson's disease: a review of literature. Frontiers in aging neuroscience, 2021. 13: p. 633752. 19. Zhang, Q., mPower Voice Activity Monitoring and Classification for Parkinson’s Diagnosis. 2018. 20. Bot, B.M., et al., The mPower study, Parkinson disease mobile data collected using ResearchKit. Sci Data, 2016. 3: p. 160011. 21. Salchow-Hömmen, C., et al., Emerging Portable Technologies for Gait Analysis in Neurological Disorders. Frontiers in Human Neuroscience, 2022. 16: p. 768575. 22. Zhang, J., Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson’s disease. npj Parkinson's Disease, 2022. 8(1). 23. Ho, M.-Y., Look, Listen, and Diagnose: a deep learning-based comprehensive Parkinson's disease evaluation system with 3D point cloud and acoustic features., in Graduate Institute of Biomedical Electronics and Bioinformatics. 2021, National Taiwan University. 24. Park, K.W., et al., Potential Pitfalls of Remote and Automated Video Assessments of Movements Disorders. Movement Disorders, 2023. 25. Dror, B., et al. Automatic assessment of Parkinson's Disease from natural hands movements using 3D depth sensor. in 2014 IEEE 28th Convention of Electrical & Electronics Engineers in Israel (IEEEI). 2014. IEEE. 26. Ferraris, C., et al., A Self-Managed System for Automated Assessment of UPDRS Upper Limb Tasks in Parkinson’s Disease. Sensors, 2018. 18(10): p. 3523. 27. Butt, A.H., et al. Leap motion evaluation for assessment of upper limb motor skills in Parkinson's disease. in 2017 international conference on rehabilitation robotics (ICORR). 2017. IEEE. 28. Chen, Y., et al., PD-Net: Quantitative Motor Function Evaluation for Parkinson's Disease via Automated Hand Gesture Analysis, in Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021. p. 2683-2691. 29. Butt, A.H., et al., Objective and automatic classification of Parkinson disease with Leap Motion controller. BioMedical Engineering OnLine, 2018. 17(1): p. 168. 30. Moshkova, A., et al. Parkinson’s disease detection by using machine learning algorithms and hand movement signal from LeapMotion sensor. in 2020 26th Conference of Open Innovations Association (FRUCT). 2020. IEEE. 31. Gao, C., et al., Objective assessment of bradykinesia in Parkinson’s disease using evolutionary algorithms: clinical validation. Translational Neurodegeneration, 2018. 7(1). 32. Guo, Z., et al., Vision-Based Finger Tapping Test in Patients With Parkinson's Disease via Spatial-Temporal 3D Hand Pose Estimation. IEEE J Biomed Health Inform, 2022. 26(8): p. 3848-3859. 33. Afifi, M., 11K Hands: Gender recognition and biometric identification using a large dataset of hand images. Multimedia Tools and Applications, 2019. 78: p. 20835-20854. 34. Moon, G., et al. InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image. in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XX 16. 2020. Springer. 35. Cornman, H.L., J. Stenum, and R.T. Roemmich, Video-based quantification of human movement frequency using pose estimation: A pilot study. PLoS One, 2021. 16(12): p. e0261450. 36. Sibley, K., et al., An Evaluation of KELVIN, an Artificial Intelligence Platform, as an Objective Assessment of the MDS UPDRS Part III. Journal of Parkinson's Disease, 2022(Preprint): p. 1-12. 37. Cao, Z., et al., OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021. 43(1): p. 172-186. 38. Li, H., et al., Automated assessment of Parkinsonian finger-tapping tests through a vision-based fine-grained classification model. Neurocomputing, 2021. 441: p. 260-271. 39. Pang, Y., et al., Automatic detection and quantification of hand movements toward development of an objective assessment of tremor and bradykinesia in Parkinson's disease. J Neurosci Methods, 2020. 333: p. 108576. 40. Hoang, T.-H., et al., Towards a Comprehensive Solution for a Vision-based Digitized Neurological Examination. IEEE Journal of Biomedical and Health Informatics, 2022. 26(8): p. 4020-4031. 41. Wei, S.-E., et al. Convolutional pose machines. in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2016. 42. Newell, A., K. Yang, and J. Deng. Stacked hourglass networks for human pose estimation. in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14. 2016. Springer. 43. Guo, R., et al., A tree-structure-guided graph convolutional network with contrastive learning for the assessment of parkinsonian hand movements. Medical Image Analysis, 2022. 81: p. 102560. 44. Contributors, M. OpenMMLab Pose Estimation Toolbox and Benchmark. 2020 [cited 2020 2020-08-31]; Available from: https://github.com/open-mmlab/mmpose. 45. Toshev, A. and C. Szegedy. Deeppose: Human pose estimation via deep neural networks. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. 46. He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. 47. Yang, N., et al., Automatic Detection Pipeline for Accessing the Motor Severity of Parkinson’s Disease in Finger Tapping and Postural Stability. IEEE Access, 2022. 10: p. 66961-66973. 48. Mathis, A., et al., DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nature neuroscience, 2018. 21(9): p. 1281-1289. 49. Williams, S., et al., The discerning eye of computer vision: Can it measure Parkinson's finger tap bradykinesia? Journal of the Neurological Sciences, 2020. 416: p. 117003. 50. Ge, L., et al. 3D Hand Shape and Pose Estimation from a Single RGB Image. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019. 51. Vignoud, G., et al., Video-based automated analysis of MDS-UPDRS III parameters in Parkinson disease. bioRxiv, 2022. 52. Lugaresi, C., et al., Mediapipe: A framework for building perception pipelines. arXiv preprint arXiv:1906.08172, 2019. 53. Güney, G., et al., Video-Based Hand Movement Analysis of Parkinson Patients before and after Medication Using High-Frame-Rate Videos and MediaPipe. Sensors, 2022. 22(20): p. 7992. 54. Zhao, A. and J. Li, Two-channel lstm for severity rating of parkinson’s disease using 3d trajectory of hand motion. Multimedia Tools and Applications, 2022. 81(23): p. 33851-33866. 55. Sandler, M., et al. Mobilenetv2: Inverted residuals and linear bottlenecks. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. 56. Williams, S., et al., Supervised classification of bradykinesia in Parkinson’s disease from smartphone videos. Artificial Intelligence in Medicine, 2020. 110: p. 101966. 57. Liu, Y., et al., Vision-Based Method for Automatic Quantification of Parkinsonian Bradykinesia. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019. 27(10): p. 1952-1961. 58. Stamate, C., et al., PDKit: A data science toolkit for the digital assessment of Parkinson’s Disease. PLOS Computational Biology, 2021. 17(3): p. e1008833. 59. Christ, M., et al., Time series feature extraction on basis of scalable hypothesis tests (tsfresh–a python package). Neurocomputing, 2018. 307: p. 72-77. 60. Jha, A., et al., The CloudUPDRS smartphone software in Parkinson’s study: cross-validation against blinded human raters. npj Parkinson's Disease, 2020. 6(1). 61. Stamate, C., et al., The cloudUPDRS app: A medical device for the clinical assessment of Parkinson’s Disease. Pervasive and Mobile Computing, 2018. 43: p. 146-166. 62. Noyce, A.J., et al., Bradykinesia-akinesia incoordination test: validating an online keyboard test of upper limb function. PLoS One, 2014. 9(4): p. e96260. 63. Shribman, S., et al., The BRAIN test: a keyboard-tapping test to assess disability and clinical features of multiple sclerosis. Journal of Neurology, 2018. 265: p. 285-290. 64. Akram, N., et al., Developing and assessing a new web-based tapping test for measuring distal movement in Parkinson's disease: a Distal Finger Tapping test. Sci Rep, 2022. 12(1): p. 386. 65. Wilkins, K.B., et al., Quantitative Digitography Measures Motor Symptoms and Disease Progression in Parkinson’s Disease. Journal of Parkinson's Disease, 2022. 12(Preprint): p. 1-12. 66. Liu, W., et al., Vision-based estimation of MDS-UPDRS scores for quantifying Parkinson's disease tremor severity. Medical Image Analysis, 2023. 85: p. 102754. 67. Wu, H.-Y., et al., Eulerian video magnification for revealing subtle changes in the world. ACM transactions on graphics (TOG), 2012. 31(4): p. 1-8. 68. Wu, Y., et al., Detectron2. 2019. 69. Contributors, M., OpenMMLab Pose Estimation Toolbox and Benchmark. 2020. 70. Fang, H.-S., et al., Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. 71. Docekal, J., et al. Human Keypoint Detection for Close Proximity Human-Robot Interaction. 2022. IEEE. 72. Chicco, D. and G. Jurman, The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 2020. 21(1). 73. Chmura Kraemer, H., V.S. Periyakoil, and A. Noda, Kappa coefficients in medical research. Statistics in Medicine, 2002. 21(14): p. 2109-2129. 74. McHugh, M.L., Interrater reliability: the kappa statistic. Biochem Med (Zagreb), 2012. 22(3): p. 276-82. 75. Lu, L., et al., A Multichannel CNN-GRU Model for Human Activity Recognition. IEEE Access, 2022. 10: p. 66797-66810. 76. Rupprechter, S., et al., A clinically interpretable computer-vision based method for quantifying gait in parkinson’s disease. Sensors, 2021. 21(16): p. 5437. 77. Morinan, G., et al., Computer-vision based method for quantifying rising from chair in Parkinson's disease patients. Intelligence-Based Medicine, 2022. 6: p. 100046. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87724 | - |
dc.description.abstract | 巴金森氏症候群是國人常見的神經退化性疾病,通常好發於60歲以上的老年人,其臨床上典型症狀包含四肢顫抖、無力、動作緩慢、易駝背、走姿手臂擺幅減少、步行時有小碎步等。MDS-UPDRS巴金森症狀衡量表為醫師臨床上評估症狀嚴重程度之依據,其中第三部分針對動作能力進行評估,包含手指打拍、手掌握合、前臂迴旋等三項手部動作。然而,醫師雖然能以此量表敘述作為評估症狀的依據,但其量表定義未能完全量化,臨床診斷上,常須依靠醫師的經驗及主觀判斷。此外,當患者未到醫院就醫時,難以自我量化評估手部功能是否因藥物控制而獲得改善。因此,為了解決評分不一致以及遠端自我評估的問題,本研究志在開發一巴金森症狀線上評估系統,供使用者上傳自我錄製的手部動作影片,透過深度學習的模型架構來預測手部的MDS-UPDRS巴金森症狀衡量表分數,並同時呈現量化的數值指標,以達到客觀且快速的初步自我評估之目的。本篇研究將以手指打拍為例,完整說明系統流程架構、模型訓練方法與網頁介面建構,並透過分析臨床特徵與預測值之關聯性,以驗證模型精準度及適用範圍。
此研究採用自2020年至2022年於台大醫院總院與癌醫分院收案之資料集,進行210個試驗,有186位受試者參與試驗,包含健康受試者、典型巴金森氏症患者、多重系統退化症患者等,共收集了840部影片。每次試驗,受試者將錄製左、右手各約十秒之短手指打拍影片兩次。透過Google所開發之MediaPipe應用程式介面(API),可以將手部關鍵點雲特徵從影片中擷取出來,並藉由空洞卷積深度學習模型,以進行模型MDS-UPDRS量表分數之分類任務,同時搭配3D點雲特徵旋轉、隨機切割兩項資料增強技術,以平衡並過取樣資料集,藉此提升模型之精準度。另一方面,手部關鍵點雲特徵也可以用於計算大拇指與食指之距離,可作為量化指標以供分析驗證深度學習模型之效度。 結果顯示以資料增強技術有助於深度模型的訓練。此外,在不同架構的模型中,原始的PDHandNet設計有較好的適用性與計算效率。在多類別MDS-UPDRS的左手及右手分類任務的測試集中,分別具有88.0% 與81.5% 的可容許準確度以及0.4328與0.3177的Cohen Kappa係數。儘管其準確度仍有進步空間,深度學習預測模型的預測結果,經手部定量參數(如:頻率、振幅)以及外部資料集PDMotorDB驗證,仍能區分臨床上的巴金森症狀之嚴重程度。 本研究將深度學習模型與手部定量參數算法匯集成一手部分析預測應用程式介面(Hand Predictor API),並建立FastEval Parkinsonism網頁 (https://fastevalp.cmdm.tw/),供使用者能夠經由手機或電腦上傳各式裝置所錄製之彩色手指打拍影片,並快速地進行分析。此網頁有三項特點:其一,經由Hand Predictor API所計算之多個評估指標、手部參數之變化、影片將同時呈現於同一頁面,供使用者能相互參照。其二,為了使左右手的資訊能相互參照,前述之評估指標將以80-20分數量表以雷達圖方式表示,能夠清楚表達左右手的優劣勢以及是否有出現不對稱的巴金森典型特徵。最後,若使用者可以定期量測各項評估指標,將可以即時追蹤其自身的狀態,同時,醫師能根據變化適時調整治療策略,實現個人化醫療。 總結而言,本研究之系統有助於一般老年使用者的家中自我評估巴金森氏症狀,並能協助醫生有效的做量化評估病人隨時間之左右手狀態,能減輕醫師的負擔,提升綜合醫療服務品質。 | zh_TW |
dc.description.abstract | Parkinson’s disease (PD) is a common neurodegenerative disease that usually occurs in elders over 60 year of age. The Motor Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) is the gold standard for physicians to clinically evaluate the severity of clinical symptoms (or parkinsonism). The finger-tapping task comprises a motor assessment for bradykinesia, a kind of parkinsonism, in the third part of the MDS-UPDRS. However, although clinicians can assess the patient’s symptoms using this scale description, the evaluation scale is not fully quantified. Thus, the clinical and time-consuming evaluation largely depends on the physician’s experience and subjective judgement. Furthermore, it is hard to monitor the patients’ latest movement status of movements at home.
Thus, an online self-evaluation system for parkinsonism was developed to address the issues of the inconsistency of movement evaluation and the difficulty of self-monitoring. This system allows users to upload self-recorded hand movement videos and predict the MDS-UPDRS score for each hand based on the deep learning-based model. The quantitative hand parameters are also provided to make users preliminarily assess the health status of hands objectively and quickly. This study used take finger tapping as an example to fully explain the system’s framework and model-building procedures and the construction of the web interface. In addition, the accuracy and applicability domain of the model was verified by analyzing the correlation between clinical characteristics and predicted values. This study collected data from 210 trials from 186 participants at the National Taiwan University Hospital from 2020 to 2022. Finger-tapping videos for each hand were recorded for about 10 seconds twice per trial. The MediaPipe application programming interface (API) developed by Google was used to extract the key point cloud features of the hand from the video. Then, a dilated convolution neural network, combined with two data enhancement technologies (3D key point rotation and the random cropping technique) was used to predict the MDS-UPDRS score. Finally, the distance between the thumb and index finger was calculated from the 3D key points of the hand as a quantitative indicator to verify the performance of the deep learning model. The results showed that data augmentation techniques were helpful for training deep models. In addition, among models with different architectures, the original PDHandNet design had better applicability and computational efficiency. In the test sets of the left-hand and right-hand classification tasks of the multi-category MDS-UPDRS, the acceptable accuracies were 88.0% and 81.5%, and the Cohen Kappa coefficients were 0.4328 and 0.3177, respectively. While there was room for improvement, the prediction results from the DL model can distinguish the severity of clinical Parkinson's symptoms after verifying by hand quantitative parameters and the external data set, PDMotorDB. In this study, the algorithms were integrated into a hand analysis application programming interface (Hand Predictor API), and FastEval Parkinsonism (https://fastevalp.cmdm.tw/) was established for users to access. Users can upload and instantly analyze the videos FastEval Parkinsonism has three main features. First, the multiple evaluation indicators calculated by the Hand Predictor API, the changes in hand parameters, and the resulting videos are displayed on the same page for users to refer to. Second, to allow cross-referencing of left and right hand information, the above-mentioned evaluation indicators are expressed as a radar chart with an 80-20 scoring scale, which clearly shows the clinical symmetry of the left and right hands. Finally, if users can regularly measure various evaluation indicators, they will be able to track their own status in real-time. In summary, the system developed here is helpful for the self-assessment of Parkinson's symptoms at home by older individuals and can assist doctors in effectively quantifying the status of the left and right hands of patients over time, which can reduce the burden on doctors and improve comprehensive medical services quality. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-07-19T16:07:46Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-07-19T16:07:46Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 口試委員審定書 i
謝辭 ii 中文摘要 iv Abstract vi Contents ix List of Figures xiii List of Tables xx Chapter 1. Introduction 1 1.1. Background 1 1.1.1. Clinical background of parkinsonism 1 1.1.2. Artificial intelligence-assisted (AI-assisted) healthcare systems 4 1.1.3. Digital biomarkers 5 1.2. Motivation 5 Chapter 2. Related Works 8 2.1. Finger tapping analysis 9 2.1.1. Extraction of hand skeleton points 10 2.1.2. Hand parameters 12 2.1.3. Parameter-based machine learning classification 16 2.1.4. End-to-end deep learning classification 17 2.2. Other hand-related movements for clinical diagnosis 18 2.2.1. Modified finger taps 18 2.2.2. Open–close hand movement 18 2.2.3. Pronation–supination movements 19 2.2.4. Rest tremor 20 Chapter 3. Main Contributions 22 Chapter 4. Materials and Methods 24 4.1. Overview workflows 24 4.2. Patient recruitment and video recording 25 4.3. Evaluation of ground-truth MDS-UPDRS score 27 4.3.1. The scoring policy with the second evaluator 27 4.3.2. Transformation from the MDS-UPDRS scores to binary labels 28 4.4. From RGB videos to 3D key points 29 4.4.1. Raw 3D hand key points 29 4.4.2. Quality control of key points – error frames ratio 31 4.4.3. Normalization 32 4.4.4. Null value processing 32 4.5. MDS-UPDRS score predicted by deep learning models 33 4.5.1. Evaluation metrics 34 4.5.2. Data augmentation – 3D rotation of hand key points 36 4.5.3. Data augmentation – random cropping 37 4.5.4. Balance dataset and oversampling technique 39 4.5.5. Model architectures 40 4.5.6. Hyperparameters and environment 45 4.5.7. Data post-processing for inference 46 4.5.8. Determination of AI-predicted MDS-UPDRS score 47 4.6. Quantitative hand parameters 48 4.6.1. Peak 48 4.6.2. Short-time Fourier transformation (STFT)-based features 48 4.7. API – Hand Predictor 49 4.8. Website designs and frameworks 50 Chapter 5. Results 52 5.1. Data collection 52 5.1.1. Demographics 52 5.1.2. Asymmetrical symptoms in HC, SHS, PD, and MSA 54 5.1.3. Comparison of MDS-UPDRS scores between a clinician and the second evaluator 56 5.1.4. Quality control of key points 58 5.1.5. Splitting the training, validation, and testing dataset 59 5.2. Prediction of MDS-UPDRS score 60 5.2.1. Hyperparameters optimization for binary classification subtasks 60 5.2.2. Binary classifiers with different model architectures 74 5.2.3. Performance of deep-learning binary classifiers with multiple MDS-UPDRS score evaluators 77 5.2.4. Comparison of the performance and the predicted MDS-UPDRS scores from models with 3D key point rotation settings 79 5.2.5. Outer validation with the PDMotorDB dataset 93 5.3. Demonstration of hand parameters 97 5.3.1. Correlation between the peak and intensity 97 5.3.2. Comparison of the healthy control and patient from case studies 98 5.3.3. The most representative hand parameters in the inner dataset – FI value 102 5.3.4. Consideration of speed and amplitude in the PDMotorDB dataset 110 5.4. Functionality of FastEval Parkinsonism 119 5.4.1. Register and login 120 5.4.2. Upload, view, analyze, and archive the file 121 5.4.3. Multiple evaluation indices for hand movements 124 5.4.4. Symmetric comparison of hand movements 125 5.4.5. Monitoring the status of hand movements 128 Chapter 6. Discussion 129 6.1. Consistency between AI-based systems and doctors 129 6.1.1. Acceptable accuracy 129 6.1.2. Inter-rater coefficient 130 6.1.3. Verification by hand parameters 130 6.1.4. Evaluator-depended score accuracy 132 6.1.5. Diminishing effect driven by the recording view 133 6.2. Clinical symptom representation 137 6.3. Pros and cons in the previous analysis frameworks for PD compared to our designs 142 6.3.1. KELVINTM 142 6.3.2. CloudUPDRS 143 6.3.3. FastEval Parkinsonism 144 6.4. Limitation 145 Chapter 7. Conclusion 147 References 148 Appendices 156 7.1. Abbreviations 156 7.2. Data availability 159 7.3. Author information 160 | - |
dc.language.iso | en | - |
dc.title | FastEval Parkinsonism:基於深度學習以手部影像建構之帕金森氏症狀線上即時自我評估系統—以手指打拍為例 | zh_TW |
dc.title | FastEval Parkinsonism: An instant deep learning–based online self-evaluation system for the diagnosis of Parkinson’s symptoms with hand videos using finger tapping | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 張瑞峰;蘇柏翰;郭明哲 | zh_TW |
dc.contributor.oralexamcommittee | Ruey-Feng Chang;Bo-Han Su;Ming-Che Kuo | en |
dc.subject.keyword | 巴金森氏症,多重系統退化症,MDS-UPDRS 巴金森症狀衡量表,手指打拍,深度學習,健康自我評估系統, | zh_TW |
dc.subject.keyword | Parkinson’s disease,multiple system atrophy,Movement Disorder Societysponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS),finger tapping,deep learning,self-assessment healthcare system, | en |
dc.relation.page | 162 | - |
dc.identifier.doi | 10.6342/NTU202300716 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2023-04-11 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 生醫電子與資訊學研究所 | - |
顯示於系所單位: | 生醫電子與資訊學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-2.pdf 目前未授權公開取用 | 12.27 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。