帕金森氏症是一種無法完全治癒的慢性神經退化疾病，全球約有七百萬到一千萬的帕金森氏症患者。在疾病的診斷上，評量的方法十分主觀，仰賴於醫生與專家的經驗與患者當時的狀態，需要一種客觀有效的量化診斷方法。本研究使用影像處理和OpenPose的模型對受測者手部的測試數據進行量化分析，並以雙相機進行三維重建以追蹤三維座標運動軌跡，計算振幅、週期、速度等運動特徵。同時利用奇異譜分析方法捕捉受測者的手在運動過程中表顯出的病徵如顫抖、凍結、停頓與逐漸無力等資訊

將受測者的週期、振幅、速度等參數的最大值、最小值、平均值、標準差等統計學的特徵作為運動的特徵作為機器學習的輸入，使用隨機森林作為機器學習的演算法，在對於受測者是否為帕金森氏症患者的辨識上達到了81.82%的準確率。

本研究以電腦視覺為基礎，結合了影像處理、奇異譜分析方法與機器學習，降低環境與設備要求的同時突破了現有方法的分類準確率，期望能為醫師提供一種客觀有效的量化診斷方法與協助評估的數據，且不仰賴個人的經驗主觀判斷，進一步改善帕金森氏症患者的整體診斷與照護。

Parkinson's disease is a chronic neurodegenerative disease that cannot be completely cured. The method of assessment is relatively subjective, and the diagnosis relies on the experience of the doctor and the patient's status at the clinical session. An objective method that provides quantitative evaluation of the disease is needed.

This paper proposed a computer vision based method using image processing techniques and an OpenPose model to quantify subject's hand movements from video. Images from dual cameras were collected to complete 3D reconstruction for tracking the trajectory of the movements, which were used to calculate the subject's motion characteristics. Also, the singular spectrum analysis was used to capture the features of the symptoms, such as tremors, freezing, pauses and gradual weakness of the subject's hands during movement. In addition, by using the subject's motion characteristics as input to build the machine learning models (random forest and other four), we achieved 81.82% accuracy in identifying whether the subject has the Parkinson's disease or not. The ultimate goal is to provide physicians with quantified diagnostic data to assist in the assessment with relying less on the subjective judgment based on individual experience, and further improve the healthcare of Parkinson’s disease patients.

[1] Parkinson’s News Today. Parkinson’s Disease Statistics [Internet]. Available:
https://parkinsonsnewstoday.com/parkinsons-disease-statistics/
[2] M. D. S. T. F. o. R. S. f. P. s. Disease, "The unified Parkinson's disease rating scale (UPDRS): status and recommendations," Movement Disorders, vol. 18, no. 7, pp. 738-750, 2003.
[3] C. G. Goetz, S. Fahn, P. Martinez‐Martin, W. Poewe, C. Sampaio, G. T. Stebbins, M. B. Stern, B. C. Tilley, R. Dodel, and B. Dubois, "Movement Disorder Society‐sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS‐UPDRS): process, format, and clinimetric testing plan," Movement disorders, vol. 22, no. 1, pp. 41-47, 2007.
[4] E. Rovini, C. Maremmani, and F. Cavallo, "How wearable sensors can support Parkinson's disease diagnosis and treatment: a systematic review," Frontiers in neuroscience, vol. 11, p. 555, 2017.
[5] A. Salarian, H. Russmann, C. Wider, P. R. Burkhard, F. J. Vingerhoets, and K. Aminian, "Quantification of tremor and bradykinesia in Parkinson's disease using a novel ambulatory monitoring system," IEEE Transactions on Biomedical Engineering, vol. 54, no. 2, pp. 313-322, 2007.
[6] I. Schlesinger, O. Benyakov, I. Erikh, S. Suraiya, and Y. Schiller, "Parkinson's disease tremor is diminished with relaxation guided imagery," Movement disorders: official journal of the Movement Disorder Society, vol. 24, no. 14, pp. 2059-2062, 2009.
[7] R. López-Blanco, M. A. Velasco, A. Méndez-Guerrero, J. P. Romero, M. D. Del Castillo, J. I. Serrano, E. Rocon, and J. Benito-León, "Smartwatch for the analysis of rest tremor in patients with Parkinson's disease," Journal of the Neurological Sciences, vol. 401, pp. 37-42, 2019.
[8] D. A. Heldman, J. P. Giuffrida, and E. Cubo, "Wearable sensors for advanced therapy referral in Parkinson’s disease," Journal of Parkinson's disease, vol. 6, no. 3, pp. 631-638, 2016.
[9] D. Pan, R. Dhall, A. Lieberman, and D. B. Petitti, "A mobile cloud-based Parkinson’s disease assessment system for home-based monitoring," JMIR mHealth and uHealth, vol. 3, no. 1, p. e29, 2015.
[10] H. A. Siddiqui, J. Jimenez-Shahed, A. Viswanathan, and N. F. Ince, "A wireless sensor interface for the quantification of tremor using off the shelf components," in 2016 32nd Southern Biomedical Engineering Conference (SBEC), 2016, pp. 177-178: IEEE.
[11] J. Vanrenterghem, D. Gormley, M. Robinson, and A. Lees, "Solutions for representing the whole-body centre of mass in side cutting manoeuvres based on data that is typically available for lower limb kinematics," Gait & posture, vol. 31, no. 4, pp. 517-521, 2010.
[12] R. Agostino, A. Currà, M. Giovannelli, N. Modugno, M. Manfredi, and A. Berardelli, "Impairment of individual finger movements in Parkinson's disease," Movement disorders, vol. 18, no. 5, pp. 560-565, 2003.
[13] Á. Jobbágy, P. Harcos, R. Karoly, and G. Fazekas, "Analysis of finger-tapping movement," Journal of neuroscience methods, vol. 141, no. 1, pp. 29-39, 2005.
[14] S.-W. Chen, S.-H. Lin, L.-D. Liao, H.-Y. Lai, Y.-C. Pei, T.-S. Kuo, C.-T. Lin, J.-Y. Chang, Y.-Y. Chen, and Y.-C. Lo, "Quantification and recognition of parkinsonian gait from monocular video imaging using kernel-based principal component analysis," Biomedical engineering online, vol. 10, no. 1, p. 99, 2011.
[15] B. Galna, G. Barry, D. Jackson, D. Mhiripiri, P. Olivier, and L. Rochester, "Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease," Gait & posture, vol. 39, no. 4, pp. 1062-1068, 2014.
[16] D. Tang, H. Jin Chang, A. Tejani, and T.-K. Kim, "Latent regression forest: Structured estimation of 3d articulated hand posture," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 3786-3793.
[17] J. Tompson, M. Stein, Y. Lecun, and K. Perlin, "Real-time continuous pose recovery of human hands using convolutional networks," ACM Transactions on Graphics (ToG), vol. 33, no. 5, pp. 1-10, 2014.
[18] X. Sun, Y. Wei, S. Liang, X. Tang, and J. Sun, "Cascaded hand pose regression," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 824-832.
[19] T. Pfister, J. Charles, and A. Zisserman, "Flowing convnets for human pose estimation in videos," in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1913-1921.
[20] L. Pishchulin, E. Insafutdinov, S. Tang, B. Andres, M. Andriluka, P. V. Gehler, and B. Schiele, "Deepcut: Joint subset partition and labeling for multi person pose estimation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 4929-4937.
[21] S.-E. Wei, V. Ramakrishna, T. Kanade, and Y. Sheikh, "Convolutional pose machines," in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2016, pp. 4724-4732.
[22] 苏九林, "Hausdorff 距离在手势识别中的运用," 上海海运学院 上海海事大学, 2004.
[23] 周航, "基于计算机视觉的手势识别系统研究," 北京交通大学, 2008.
[24] Z. Cao, T. Simon, S.-E. Wei, and Y. Sheikh, "Realtime multi-person 2d pose estimation using part affinity fields," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7291-7299.
[25] T. Simon, H. Joo, I. Matthews, and Y. Sheikh, "Hand keypoint detection in single images using multiview bootstrapping," in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2017, pp. 1145-1153.
[26] Y. Pang, J. Christenson, F. Jiang, T. Lei, R. Rhoades, D. Kern, J. A. Thompson, and C. Liu, "Automatic detection and quantification of hand movements toward development of an objective assessment of tremor and bradykinesia in Parkinson's disease," Journal of Neuroscience Methods, vol. 333, p. 108576, 2020.
[27] C.-M. Chang, Y.-L. Huang, J.-C. Chen, and C.-C. Lee, "Improving Automatic Tremor and Movement Motor Disorder Severity Assessment for Parkinson’s Disease with Deep Joint Training," in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2019, pp. 3408-3411: IEEE.
[28] X. Yang, S. A. Shah, A. Ren, D. Fan, N. Zhao, D. Cao, F. Hu, M. U. Rehman, W. Wang, and K. M. Von Deneen, "Detection of essential tremor at the $ s $-band," IEEE journal of translational engineering in health and medicine, vol. 6, pp. 1-7, 2018.
[29] H. M. Bronte‐Stewart, L. Ding, C. Alexander, Y. Zhou, and G. P. Moore, "Quantitative digitography (QDG): a sensitive measure of digital motor control in idiopathic Parkinson's disease," Movement disorders: official journal of the Movement Disorder Society, vol. 15, no. 1, pp. 36-47, 2000.
[30] B. E. Sakar, M. E. Isenkul, C. O. Sakar, A. Sertbas, F. Gurgen, S. Delil, H. Apaydin, and O. Kursun, "Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings," IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 4, pp. 828-834, 2013.
[31] N. Golyandina, V. Nekrutkin, and A. A. Zhigljavsky, Analysis of time series structure: SSA and related techniques. CRC press, 2001.
[32] L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5-32, 2001.
[33] L. Breiman, J. Friedman, C. J. Stone, and R. A. Olshen, Classification and regression trees. CRC press, 1984.