成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	簡崇曜 Chien, Chung-Yao
論文名稱：	機器學習演算法應用在巴金森病功能性神經影像-臨床面相 The Application of Machine Learning Algorithm in Functional Neuroimaging of Parkinson’s Disease - In the clinical aspect
指導教授：	陳天送 Chen, Tain-Song 林宙晴 Lin, Chou-Ching
學位類別：	博士 Doctor
系所名稱：	工學院 - 生物醫學工程學系 Department of BioMedical Engineering
論文出版年：	2022
畢業學年度：	111
語文別：	英文
論文頁數：	143
中文關鍵詞：	巴金森病、非典型巴金森症、認知功能障礙、神經影像學、多巴胺轉運體單光子放射電腦斷層影像、功能性磁振造影、機器學習、深度學習、特徵選取、基因演算法、主動輪廓模式
外文關鍵詞：	Parkinson’ disease, atypical parkinsonian syndrome, cognitive impairment, neuroimaging, DAT-SPECT, fMRI, machine learning, deep learning, feature selection, genetic algorithm, active contour model
ORCID：	0000-0002-2227-9589
相關次數：	點閱：183 下載：41
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

巴金森病是第二常見神經退化性疾病，從症狀出現被診斷到失能可能有十至二十年的時間。病人與醫療人員須共同面對病程中所有狀況。簡而言之，在診斷巴金森病初期，必須與其他非典型巴金森症狀疾病鑑別診斷以確立治療計畫；開始藥物治療後到病程中期，必須掌握巴金森病本身症狀-尤其非動作症狀的發展以及藥物可能的副作用，而認知功能的障礙與否會是決定藥物增減調整的一大因素；到病程中後期，影響生活品質與病患自主能力最主要的症狀是步態凍僵，藥物治療對此效果不彰而必須佐以精確有效的步態訓練與復健甚至個人化的治療。此三者：初期鑑別診斷、中期認知功能、以及中後期步態凍僵目前在臨床上沒有客觀的生物標記以供診斷、預測與追蹤。功能性神經影像是非侵入性、高重複性且資訊豐富的檢查，提供臨床照護重大價值。即使目前研究報告眾多，仍未針對臨床需求提供解決方案。本論文將以此臨床需求發想，回顧過去研究報告並探討未能臨床應用之可能原因-傳統分析方法的限制，進而引用機器學習分析方式，試圖發展出能解決臨床需求的方式。
研究背景可分成兩部分。第一部分重點簡述巴金森病與其背後病理機轉，在退化過程中所有動作症狀與非動作症狀相對應的病態生理基礎，連結現行的功能性神經檢查之間的可相對應性。針對前述三項臨床需求目前研究文獻廣泛地回顧神經影像學相關報告以了解當前進展。第二部分將細究文獻中各項功能性影像分析方法，探討缺乏臨床應用的可能原因：傳統線性分析方法無法呈現大量參數之特徵；簡述機器學習分析方法目前之應用以及解決傳統線性分析方法之限制的可行性。研究動機方面，針對前兩項臨床需求設定目標：第一，在功能性影像學之分子影像中，透過機器學習方式解決過去線性分析無法區別巴金森病與非典型巴金森症狀疾病之限制，提高巴金森病前期診斷正確率；第二，利用線上資料庫之功能性磁振造影影像，透過機器學習方式尋找特徵以區分巴金森個案是否患有認知功能障礙，並且在當地資料庫驗證其特徵協助判斷個案認知功能障礙與否。
在研究方法與結果部分，第一，回顧國立成功大學附設醫院之多巴胺轉運體單光子放射電腦斷層影像，巴金森病105位及非典型巴金森症狀疾病100位之影像透過深度學習訓練出分類器，再以另外共57位巴金森病及非典型巴金森症狀疾病個案之影像驗證之，透過主動輪廓模式前處理取得紋狀體區域影像，分類器表現效能接近巴金森病臨床診斷指引納入影像協助診斷項目之條件。第二，收錄多中心轉介之線上影像資料庫 (Parkinson’s Progression Markers Initiative, PPMI) 共181位之靜息態功能性磁振造影，利用功能性連結之參數以機器學習方式訓練分類器，過程使用基因演算法及特徵選取，縮短訓練時間並且提高分類效能。最後以國立成功大學附設醫院之25位個案驗證此分類器，其分類準確度、敏感度與特異性皆接近9成。
討論部分將針對各項結果探討，深究其臨床應用之可行性，討論未足之處以盼未來發展落實解決臨床需求。

Parkinson’s disease is the second most common neurodegenerative disorder, the disease course lasts 10 to 20 years since the subject’s motor symptoms appear till one’s total dependency in activity of daily living. After making the diagnosis, in the early phase of the disease, one important issue is to confirm diagnosis of Parkinson’s disease and discrimination from atypical parkinsonian syndromes. Comparing with Parkinson’s disease, the treatment plan and the prognosis will be quite different in atypical parkinsonian syndrome. Since pharmacological therapy have started, clinician not only adjusting dosage of drug according to motor symptoms but also should be aware of many non-motor symptoms, adverse effects from medicine and their interactions. One important factor for judgement of titrating or tapering drug dosage is cognitive status. Clinician may decrease or halt medications when subject’s cognition impaired to avoid devastating behavioral and psychotic symptoms even as the motor dysfunction might obtain benefit from increasing medication. In the middle to late phase of the disease, the symptom ‘freezing of gait’ is most influential to quality of life and patient’s autonomy. The effect of pharmacological treatment tent to be limited. Freezing of gait calls for precise physiotherapy and even personalized training. However, currently there is no biomarkers for early differential diagnosis, identification of cognitive status and freezing of gait. Functional neuroimaging is a non-invasive, repeatable, and informative study, which providing high value for clinical practice. Despite of numerous research reports about neuroimaging and Parkinson’s disease, up to date many unmet needs in clinical practice remain. This dissertation is based on this concept to review literature and discover possible reason- the limitation of conventional analysis. Further on, through machine learning algorithm, this work develops solutions for utilization of neuroimaging to the unmet need.
There are two parts in the Introduction. First part is to describe Parkinson’s disease and the mechanism to its symptoms. The connection between the pathophysiology of motor and non-motor symptoms during this degenerative course and functional neuroimaging studies. The review of latest development of neuroimaging studies is also presented. Second part of the introduction is to explore the conventional methodology of analyzing functional neuroimaging and discover the limitations. That is the short of linear analysis which cannot represent the features of larger number of parameters at the same times. Then how machine learning outperforms conventional approaches is also described. Upon the motivation, 2 aims are set to achieve this goal. Aim1, in molecular imaging, to overcome the limitation of linear analysis by machine learning algorithm and promote the accuracy of early diagnosis. Aim2, in an online dataset, feature selection by machine learning algorithm to find parameters and weights that distinguish image (subject) of cognitive impairment. The features for classification are then validated by a local dataset.
In the Methodology and Results parts, Aim1 was to collect 105 subjects of Parkinson’s disease and 100 subjects of atypical parkinsonian syndrome with their images of dopamine-transporter single proton emission computerized tomography. All images were preprocessed by active contour model to obtain striatal region image. Then deep learning classifier was trained by segmented images and then validated by another dataset of total 57 subjects including Parkinson’s disease and atypical parkinsonian syndrome. The classification result was close to enrollment threshold in clinical diagnostic criteria for Parkinson’s disease. In Aim2, raw images of resting-state functional magnetic resonance image from a multi-center source of online dataset (Parkinson’s Progression Markers Initiative, PPMI) and total subject number of 181 were collected. Using functional connectivity value as parameters trained a classifier discriminating cognitive impairment or not. The parameters were determined genetic algorithm and sequential backward feature selection, which shortened training time and promoted the performance of classification. The final validation was made by a local dataset with 25 subjects of Parkinson’s disease and the accuracy, sensitivity and specificity were all close to 90%.
The Discussion part not only probed into the results but also investigated the possibility of clinical applications, focusing on the advantage and disadvantage in order to develop solution to clinical need in the future.

摘要------------------------------------------------------------------------------------I
Abstract------------------------------------------------------------------------------ III
誌謝----------------------------------------------------------------------------------VII
List of tables-------------------------------------------------------------------------XIII
List of figures-----------------------------------------------------------------------XIV
List of abbreviations----------------------------------------------------------------XIX
Background
1.	Parkinson’s disease & clinical neuroimaging-----------------------------------1
1.1. Pathology & disease progression in Parkinson’s disease---------------------1
1.2. Structural image in Parkinson’s disease--------------------------------------9
1.2.1. T1W images & regional atrophy----------------------------------------------9
1.2.2. Diffusion, nigrosome 1 & neuromelanin imaging--------------------------11
1.3. Functional images for Parkinson’s disease----------------------------------13
1.3.1. Molecular imaging----------------------------------------------------------13
1.3.2. Functional MRI--------------------------------------------------------------15
1.4. Limitation in current neuroimaging in Parkinson’s disease-----------------18
2. Conventional computational techniques for functional neuroimaging--------19
2.1. Molecular image: DAT-SPECT-------------------------------------------------20
2.2. Task-based functional MRI----------------------------------------------------21
2.3. Resting-state functional MRI--------------------------------------------------23
2.4. Limitation of linear algorithm upon the clinical need-------------------------25
3. Clinical application of machine learning technique in neuroimaging----------26
3.1. Segmentation & object detection--------------------------------------------28
3.2. Classification & prediction----------------------------------------------------29
3.3. Identify novel biomarkers-----------------------------------------------------30
Motivation & goals
1. Motivation: Personalized therapy in Parkinson’s disease---------------------32
2.	Main goal-----------------------------------------------------------------------34
2.1. Aim 1: To overcome the limitation of conventional linear analysis - Differential diagnosis in early phase of PD------------------------------------------------------34
2.2. Aim 2: Features derived from machine learning algorithm to be validated in different datasets - Identification of cognitive impairment in PD from online datasets to local datasets------------------------------------------------------------35
3.	Purpose-------------------------------------------------------------------------35
Methodology
1.	2-D convolutional neural network algorithm analyzes molecular image------37
1.1. Subjects (intra-dataset) & data collection------------------------------------37
1.2. Conventional semi-quantitative measurement & analysis through linear method------------------------------------------------------------------------------41
1.3. Image preprocessing: adaptive mask design, intensity correction & selecting ROI by active contour model--------------------------------------------------------41
1.4. Transfer learning for differential diagnosis by images of original, scalp-eliminated & striatal region---------------------------------------------------------48
2.	Machine learning feature selection of functional connectivity in rs-fMRI & validation by another dataset-------------------------------------------------------50
2.1. Subjects & data collection----------------------------------------------------50
2.2. First step of feature selection: though genetic algorithm: SVM, kNN, naive Bayes & decision tree----------------------------------------------------------------54
2.3. Second step of feature selection: classifier training through leave-one-out cross validation----------------------------------------------------------------------55
2.4. Prediction in the local dataset at a subject level by the classifier trained from online dataset------------------------------------------------------------------------56
2.5. Group analyses by conventional methods between datasets for comparison-----------------------------------------------------------------------------------------57
3. The evaluation of performance of machine learning models – validation index-----------------------------------------------------------------------------------------60
4. The equipment, hardware and software----------------------------------------61
4.1. Medical equipment for functional neuroimaging----------------------------61
4.2. Hardware and software-------------------------------------------------------63
Results
1.	Computer-vision aided differential diagnosis of Parkinson’s disease and atypical parkinsonian syndromes---------------------------------------------------64
1.1. Conventional parameter and linear analysis----------------------------------64
1.2. Support vector machine for conventional parameter------------------------62
1.3. Deep learning-----------------------------------------------------------------67
2.	Cognitive state discrimination by functional connectivity in different datasets-----------------------------------------------------------------------------------------71
2.1. Characteristics in different dataset through conventional analysis-----------73
2.2. Selecting a model with a better accuracy by adding pre-selection with genetic algorithm--------------------------------------------------------------------83
2.3. Sequential feature selection & classifier training through partition of leave-one-out------------------------------------------------------------------------------86
2.4. Performance of the online-dataset trained classifier in a local dataset-------91
Discussion
1. Pros & cons of CNN methods for DAT-SPECT to discriminate PD & APS------93
2.	Discrepancies in conventional methods vs common features in machine learning algorithms in analysis of rs-fMRI-------------------------------------------96
3.	Advantages of applying machine learning algorithms in clinical aspect-----102
3.1. Binary classification through conventional analysis and machine learning algorithm---------------------------------------------------------------------------102
3.2. The clinical utility of applying machine learning algorithms----------------103
3.3. The explainability of machine learning and biological correlation----------107
4.	What to feed to the machine? ------------------------------------------------115
Future work
1.	Exploration of enigmatic phenomenon to empower tailored therapy - Featuring rhythmic auditory stimulation therapy in freezing of gait through machine learning algorithm-------------------------------------------------------116
2. 3-D convolutional neural network algorithm in task-based functional MRI--119
Appendix 1-------------------------------------------------------------------------121
Appendix 2-------------------------------------------------------------------------131
Appendix 3-------------------------------------------------------------------------135
Reference---------------------------------------------------------------------------136
                                    

1. Gibb, W.R. and A.J. Lees, The relevance of the Lewy body to the pathogenesis of idiopathic Parkinson's disease. J Neurol Neurosurg Psychiatry, 1988. 51(6): p. 745-52.
2. Dickson, D.W., Neuropathology of Parkinson disease. Parkinsonism Relat Disord, 2018. 46 Suppl 1: p. S30-S33.
3. Goedert, M., et al., 100 years of Lewy pathology. Nat Rev Neurol, 2013. 9(1): p. 13-24.
4. Braak, H., et al., Stanley Fahn Lecture 2005: The staging procedure for the inclusion body pathology associated with sporadic Parkinson's disease reconsidered. Mov Disord, 2006. 21(12): p. 2042-51.
5. Irwin, D.J., V.M.Y. Lee, and J.Q. Trojanowski, Parkinson's disease dementia: convergence of α-synuclein, tau and amyloid-β pathologies. Nature Reviews Neuroscience, 2013. 14(9): p. 626-636.
6. Postuma, R.B., et al., MDS clinical diagnostic criteria for Parkinson's disease. Mov Disord, 2015. 30(12): p. 1591-601.
7. Tolosa, E., et al., Challenges in the diagnosis of Parkinson's disease. The Lancet Neurology, 2021. 20(5): p. 385-397.
8. Mitchell, T., et al., Emerging Neuroimaging Biomarkers Across Disease Stage in Parkinson Disease: A Review. JAMA Neurol, 2021. 78(10): p. 1262-1272.
9. Aarsland, D., et al., Parkinson disease-associated cognitive impairment. Nat Rev Dis Primers, 2021. 7(1): p. 47.
10. Virmani, T., et al., Clinicopathological characteristics of freezing of gait in autopsy-confirmed Parkinson's disease. Mov Disord, 2015. 30(14): p. 1874-84.
11. Vercruysse, S., et al., Explaining freezing of gait in Parkinson's disease: motor and cognitive determinants. Mov Disord, 2012. 27(13): p. 1644-51.
12. Lagravinese, G., et al., Gait initiation is influenced by emotion processing in Parkinson's disease patients with freezing. Mov Disord, 2018. 33(4): p. 609-617.
13. Jung, J.H., et al., Motor Cerebellar Connectivity and Future Development of Freezing of Gait in De Novo Parkinson's Disease. Mov Disord, 2020. 35(12): p. 2240-2249.
14. Fox, S.H., et al., International Parkinson and movement disorder society evidence-based medicine review: Update on treatments for the motor symptoms of Parkinson's disease. Mov Disord, 2018. 33(8): p. 1248-1266.
15. Weiss, D., et al., Freezing of gait: understanding the complexity of an enigmatic phenomenon. Brain, 2020. 143(1): p. 14-30.
16. Heim, B., et al., Magnetic resonance imaging for the diagnosis of Parkinson's disease. J Neural Transm (Vienna), 2017. 124(8): p. 915-964.
17. Paviour, D.C., et al., Regional brain volumes distinguish PSP, MSA-P, and PD: MRI-based clinico-radiological correlations. Mov Disord, 2006. 21(7): p. 989-96.
18. Huppertz, H.J., et al., Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classification. Movement Disorders, 2016.
19. Ray, N.J., et al., In vivo cholinergic basal forebrain atrophy predicts cognitive decline in de novo Parkinson's disease. Brain, 2018. 141(1): p. 165-176.
20. Schulz, J., et al., Nucleus basalis of Meynert degeneration precedes and predicts cognitive impairment in Parkinson's disease. Brain, 2018. 141(5): p. 1501-1516.
21. Gargouri, F., et al., Multimodal magnetic resonance imaging investigation of basal forebrain damage and cognitive deficits in Parkinson's disease. Mov Disord, 2019. 34(4): p. 516-525.
22. Mihaescu, A.S., et al., Brain degeneration in Parkinson's disease patients with cognitive decline: a coordinate-based meta-analysis. Brain Imaging Behav, 2019. 13(4): p. 1021-1034.
23. Delgado-Alvarado, M., et al., Biomarkers for dementia and mild cognitive impairment in Parkinson's disease. Mov Disord, 2016. 31(6): p. 861-81.
24. Herman, T., et al., Gray matter atrophy and freezing of gait in Parkinson's disease: Is the evidence black-on-white? Mov Disord, 2014. 29(1): p. 134-9.
25. Paviour, D.C., et al., Diffusion-weighted magnetic resonance imaging differentiates Parkinsonian variant of multiple-system atrophy from progressive supranuclear palsy. Mov Disord, 2007. 22(1): p. 68-74.
26. Bajaj, S., et al., Diffusion-weighted MRI distinguishes Parkinson disease from the parkinsonian variant of multiple system atrophy: A systematic review and meta-analysis. PLoS One, 2017. 12(12): p. e0189897.
27. Cochrane, C.J. and K.P. Ebmeier, Diffusion tensor imaging in parkinsonian syndromes: a systematic review and meta-analysis. Neurology, 2013. 80(9): p. 857-64.
28. Worker, A., et al., Diffusion tensor imaging of Parkinson's disease, multiple system atrophy and progressive supranuclear palsy: a tract-based spatial statistics study. PLoS One, 2014. 9(11): p. e112638.
29. Hall, J.M., et al., Diffusion alterations associated with Parkinson's disease symptomatology: A review of the literature. Parkinsonism Relat Disord, 2016. 33: p. 12-26.
30. Bharti, K., et al., Neuroimaging advances in Parkinson's disease with freezing of gait: A systematic review. Neuroimage Clin, 2019. 24: p. 102059.
31. Cheng, Z., et al., Imaging the Nigrosome 1 in the substantia nigra using susceptibility weighted imaging and quantitative susceptibility mapping: An application to Parkinson's disease. NeuroImage: Clinical, 2020.
32. Lee, J., et al., The clinical application of nigrosome 1 detection on high-resolution susceptibility-weighted imaging in the evaluation of suspected Parkinsonism: The real-world performance and pitfalls. PLoS One, 2020. 15(4): p. e0231010.
33. Sulzer, D., et al., Neuromelanin detection by magnetic resonance imaging (MRI) and its promise as a biomarker for Parkinson's disease. NPJ Parkinsons Dis, 2018. 4: p. 11.
34. Ohtsuka, C., et al., Differentiation of early-stage parkinsonisms using neuromelanin-sensitive magnetic resonance imaging. Parkinsonism Relat Disord, 2014. 20(7): p. 755-60.
35. Kashihara, K., T. Shinya, and F. Higaki, Reduction of neuromelanin-positive nigral volume in patients with MSA, PSP and CBD. Intern Med, 2011. 50(16): p. 1683-7.
36. Matsuura, K., et al., Neuromelanin magnetic resonance imaging in Parkinson's disease and multiple system atrophy. Eur Neurol, 2013. 70(1-2): p. 70-7.
37. Politis, M., Neuroimaging in Parkinson disease: from research setting to clinical practice. Nature Reviews Neurology, 2014. 10(12): p. 708-722.
38. Darcourt, J., et al., EANM procedure guidelines for brain neurotransmission SPECT using (123)I-labelled dopamine transporter ligands, version 2. Eur J Nucl Med Mol Imaging, 2010. 37(2): p. 443-50.
39. Eckert, T., et al., FDG PET in the differential diagnosis of parkinsonian disorders. Neuroimage, 2005. 26(3): p. 912-21.
40. Eckert, T., et al., Abnormal metabolic networks in atypical parkinsonism. Mov Disord, 2008. 23(5): p. 727-33.
41. Schindlbeck, K.A. and D. Eidelberg, Network imaging biomarkers: insights and clinical applications in Parkinson's disease. Lancet Neurol, 2018. 17(7): p. 629-640.
42. Varrone, A., et al., EANM procedure guidelines for PET brain imaging using [18F]FDG, version 2. Eur J Nucl Med Mol Imaging, 2009. 36(12): p. 2103-10.
43. Albrecht, F., et al., FDG-PET hypometabolism is more sensitive than MRI atrophy in Parkinson's disease: A whole-brain multimodal imaging meta-analysis. Neuroimage Clin, 2019. 21: p. 101594.
44. Meyer, P.T., et al., (18)F-FDG PET in Parkinsonism: Differential Diagnosis and Evaluation of Cognitive Impairment. J Nucl Med, 2017. 58(12): p. 1888-1898.
45. van der Zee, S., et al., Cholinergic Denervation Patterns Across Cognitive Domains in Parkinson's Disease. Mov Disord, 2021. 36(3): p. 642-650.
46. Kim, R., et al., Presynaptic striatal dopaminergic depletion predicts the later development of freezing of gait in de novo Parkinson's disease: An analysis of the PPMI cohort. Parkinsonism Relat Disord, 2018. 51: p. 49-54.
47. Bohnen, N.I., et al., Extra-nigral pathological conditions are common in Parkinson's disease with freezing of gait: an in vivo positron emission tomography study. Mov Disord, 2014. 29(9): p. 1118-24.
48. Franciotti, R., et al., Default mode network links to visual hallucinations: A comparison between Parkinson's disease and multiple system atrophy. Mov Disord, 2015. 30(9): p. 1237-47.
49. Functional MRI of disease progression in Parkinson disease and atypical parkinsonian syndromes. Neurology, 2016.
50. Filippi, M., E. Sarasso, and F. Agosta, Resting-state Functional MRI in Parkinsonian Syndromes. Mov Disord Clin Pract, 2019. 6(2): p. 104-117.
51. Wolters, A.F., et al., Resting-state fMRI in Parkinson's disease patients with cognitive impairment: A meta-analysis. Parkinsonism Relat Disord, 2019. 62: p. 16-27.
52. Bezdicek, O., et al., Mild cognitive impairment disrupts attention network connectivity in Parkinson's disease: A combined multimodal MRI and meta-analytical study. Neuropsychologia, 2018. 112: p. 105-115.
53. Lang, S., et al., Network basis of the dysexecutive and posterior cortical cognitive profiles in Parkinson's disease. Mov Disord, 2019. 34(6): p. 893-902.
54. Amboni, M., et al., Resting-state functional connectivity associated with mild cognitive impairment in Parkinson's disease. J Neurol, 2015. 262(2): p. 425-34.
55. Rektorova, I., Imaging Parkinson's disease using functional and diffusion MRI. Parkinsonism Relat Disord, 2019. 62: p. 1-2.
56. Snijders, A.H., et al., Gait-related cerebral alterations in patients with Parkinson’s disease with freezing of gait. Brain, 2011. 134(1): p. 59-72.
57. Peterson, D.S., et al., Gait-Related Brain Activity in People with Parkinson Disease with Freezing of Gait. PLOS ONE, 2014. 9(3): p. e90634.
58. Gilat, M., et al., Brain activation underlying turning in Parkinson's disease patients with and without freezing of gait: a virtual reality fMRI study. NPJ Parkinsons Dis, 2015. 1: p. 15020.
59. Fling, B.W., et al., Functional Reorganization of the Locomotor Network in Parkinson Patients with Freezing of Gait. PLOS ONE, 2014. 9(6): p. e100291.
60. Vervoort, G., et al., Dual-task-related neural connectivity changes in patients with Parkinson’ disease. Neuroscience, 2016. 317: p. 36-46.
61. Fereshtehnejad, S.M., et al., Clinical criteria for subtyping Parkinson's disease: biomarkers and longitudinal progression. Brain, 2017. 140(7): p. 1959-1976.
62. Campbell, M.C., et al., Parkinson disease clinical subtypes: key features & clinical milestones. Ann Clin Transl Neurol, 2020. 7(8): p. 1272-1283.
63. Brendel, M., et al., Comprehensive subtyping of Parkinson's disease patients with similarity fusion: a case study with BioFIND data. NPJ Parkinsons Dis, 2021. 7(1): p. 83.
64. Myers, P.S., et al., Distinct progression patterns across Parkinson disease clinical subtypes. Ann Clin Transl Neurol, 2021. 8(8): p. 1695-1708.
65. Simuni, T., et al., Clinical and dopamine transporter imaging characteristics of non-manifest LRRK2 and GBA mutation carriers in the Parkinson's Progression Markers Initiative (PPMI): a cross-sectional study. The Lancet Neurology, 2020.
66. Wilson, H., et al., Serotonergic pathology and disease burden in the premotor and motor phase of A53T α-synuclein parkinsonism: a cross-sectional study. The Lancet Neurology, 2019. 18(8): p. 748-759.
67. Wile, D.J., et al., Serotonin and dopamine transporter PET changes in the premotor phase of LRRK2 parkinsonism: cross-sectional studies. The Lancet Neurology, 2017. 16(5): p. 351-359.
68. Boon, L.I., et al., Functional connectivity between resting-state networks reflects decline in executive function in Parkinson's disease: A longitudinal fMRI study. Neuroimage Clin, 2020. 28: p. 102468.
69. Myers, P.S., et al., Proteinopathy and Longitudinal Cognitive Decline in Parkinson Disease. Neurology, 2022. 99(1): p. e66.
70. Klobušiaková, P., et al., Connectivity Between Brain Networks Dynamically Reflects Cognitive Status of Parkinson’s Disease: A Longitudinal Study. Journal of Alzheimer's Disease, 2019. 67: p. 971-984.
71. Richter, W. and M. Richter, The shape of the fMRI BOLD response in children and adults changes systematically with age. NeuroImage, 2003. 20(2): p. 1122-1131.
72. Chapter 40 - Analysis of fMRI Time Series: Linear Time-Invariant Models, Event-Related fMRI, and Optimal Experimental Design, in Human Brain Function (Second Edition), R.S.J. Frackowiak, et al., Editors. 2004, Academic Press: Burlington. p. 793-822.
73. Bullmore, E. and O. Sporns, Complex brain networks: graph theoretical analysis of structural and functional systems. Nature Reviews Neuroscience, 2009. 10(3): p. 186-198.
74. Chougar, L., et al., Automated Categorization of Parkinsonian Syndromes Using Magnetic Resonance Imaging in a Clinical Setting. Mov Disord, 2021. 36(2): p. 460-470.
75. Khosla, M., et al., Machine learning in resting-state fMRI analysis. Magn Reson Imaging, 2019. 64: p. 101-121.
76. Litjens, G., et al., A survey on deep learning in medical image analysis. Med Image Anal, 2017. 42: p. 60-88.
77. T, S. and T. A, Comparison of diagnostic performance of deep convolutional neural network using fine-tuning and feature extraction on dopamine transporter single photon emission tomography images. Journal of Nuclear Medicine, 2019.
78. Dawud, A.M., K. Yurtkan, and H. Oztoprak, Application of Deep Learning in Neuroradiology: Brain Haemorrhage Classification Using Transfer Learning. Comput Intell Neurosci, 2019. 2019: p. 4629859.
79. Huang, H., et al., Modeling Task fMRI Data Via Deep Convolutional Autoencoder. IEEE Trans Med Imaging, 2018. 37(7): p. 1551-1561.
80. Hu, J., et al., A Multichannel 2D Convolutional Neural Network Model for Task-Evoked fMRI Data Classification. Comput Intell Neurosci, 2019. 2019: p. 5065214.
81. Sardi, S.P. and T. Simuni, New Era in disease modification in Parkinson's disease: Review of genetically targeted therapeutics. Parkinsonism Relat Disord, 2019. 59: p. 32-38.
82. van der Eijk, M., et al., Moving from physician-centered care towards patient-centered care for Parkinson's disease patients. Parkinsonism Relat Disord, 2013. 19(11): p. 923-7.
83. Titova, N. and K.R. Chaudhuri, Personalized medicine in Parkinson's disease: Time to be precise. Mov Disord, 2017. 32(8): p. 1147-1154.
84. Bloem, B.R., et al., Integrated and patient-centred management of Parkinson's disease: a network model for reshaping chronic neurological care. The Lancet Neurology, 2020. 19(7): p. 623-634.
85. van den Heuvel, L., et al., Quadruple Decision Making for Parkinson's Disease Patients: Combining Expert Opinion, Patient Preferences, Scientific Evidence, and Big Data Approaches to Reach Precision Medicine. J Parkinsons Dis, 2020. 10(1): p. 223-231.
86. van Halteren, A.D., et al., Personalized Care Management for Persons with Parkinson's Disease. J Parkinsons Dis, 2020. 10(s1): p. S11-S20.
87. Helmich, R.C., D.E. Vaillancourt, and D.J. Brooks, The Future of Brain Imaging in Parkinson's Disease. J Parkinsons Dis, 2018. 8(s1): p. S47-S51.
88. Olde Dubbelink, K.T., et al., Resting-state functional connectivity as a marker of disease progression in Parkinson's disease: A longitudinal MEG study. Neuroimage Clin, 2013. 2: p. 612-9.
89. Guevara, C., et al., Retrospective Diagnosis of Parkinsonian Syndromes Using Whole-Brain Atrophy Rates. Front Aging Neurosci, 2017. 9: p. 99.
90. Ballarini, T., et al., Regional gray matter changes and age predict individual treatment response in Parkinson's disease. Neuroimage Clin, 2019. 21: p. 101636.
91. Zeighami, Y., et al., Assessment of a prognostic MRI biomarker in early de novo Parkinson's disease. Neuroimage Clin, 2019. 24: p. 101986.
92. Obuchowski, N.A. and J.A. Bullen, Receiver operating characteristic (ROC) curves: review of methods with applications in diagnostic medicine. Phys Med Biol, 2018. 63(7): p. 07TR01.
93. Chang, L., A Method for Attenuation Correction in Radionuclide Computed Tomography. IEEE Transactions on Nuclear Science, 1978. 25(1): p. 638-643.
94. Choi, H., et al., Refining diagnosis of Parkinson's disease with deep learning-based interpretation of dopamine transporter imaging. NeuroImage: Clinical, 2017. 16: p. 586-594.
95. Badoud, S., et al., Discriminating among degenerative parkinsonisms using advanced 123I-ioflupane SPECT analyses. NeuroImage: Clinical, 2016.
96. Nicastro, N., et al., Classification of degenerative parkinsonism subtypes by support-vector-machine analysis and striatal (123)I-FP-CIT indices. J Neurol, 2019. 266(7): p. 1771-1781.
97. Joling, M., et al., Lower 123I-FP-CIT binding to the striatal dopamine transporter, but not to the extrastriatal serotonin transporter, in Parkinson's disease compared with dementia with Lewy bodies. NeuroImage: Clinical, 2018.
98. Joling, M., et al., Striatal DAT and extrastriatal SERT binding in early-stage Parkinson's disease and dementia with Lewy bodies, compared with healthy controls: An 123 I-FP-CIT SPECT study. NeuroImage: Clinical, 2019.
99. Nazari, M., et al., Explainable AI to improve acceptance of convolutional neural networks for automatic classification of dopamine transporter SPECT in the diagnosis of clinically uncertain parkinsonian syndromes. Eur J Nucl Med Mol Imaging, 2022. 49(4): p. 1176-1186.
100. Zhao, Y., et al., Decoding the dopamine transporter imaging for the differential diagnosis of parkinsonism using deep learning. European Journal of Nuclear Medicine and Molecular Imaging, 2022. 49(8): p. 2798-2811.
101. Vlaar, A.M., et al., Meta-analysis of the literature on diagnostic accuracy of SPECT in parkinsonian syndromes. BMC Neurol, 2007. 7: p. 27.
102. Telesford, Q., et al., Reproducibility of Graph Metrics in fMRI Networks. Frontiers in Neuroinformatics, 2010. 4.
103. Wang, Y. and T.-Q. Li, Dimensionality of ICA in resting-state fMRI investigated by feature optimized classification of independent components with SVM. Frontiers in Human Neuroscience, 2015. 9.
104. Franco, A.R., et al., Impact of analysis methods on the reproducibility and reliability of resting-state networks. Brain Connect, 2013. 3(4): p. 363-74.
105. Abós, A., et al., Discriminating cognitive status in Parkinson’s disease through functional connectomics and machine learning. Scientific Reports, 2017. 7(1): p. 45347.
106. Bhidayasiri, R., Will Artificial Intelligence Outperform the Clinical Neurologist in the Near Future? Yes. Mov Disord Clin Pract, 2021. 8(4): p. 525-528.
107. Loh, H.W., et al., Application of Deep Learning Models for Automated Identification of Parkinson's Disease: A Review (2011-2021). Sensors (Basel), 2021. 21(21).
108. Nicastro, N., et al., Dopaminergic imaging in degenerative parkinsonisms, an established clinical diagnostic tool. J Neurochem, 2021.
109. Ahsan, M.M., S.A. Luna, and Z. Siddique, Machine-Learning-Based Disease Diagnosis: A Comprehensive Review. Healthcare (Basel), 2022. 10(3).
110. Golan, H., O. Volkov, and E. Shalom, Nuclear imaging in Parkinson's disease: The past, the present, and the future. J Neurol Sci, 2022. 436: p. 120220.
111. D’Cruz, N., et al., Thalamic morphology predicts the onset of freezing of gait in Parkinson’s disease. npj Parkinson's Disease, 2021. 7(1): p. 20.
112. Nutt, J.G., et al., Freezing of gait: moving forward on a mysterious clinical phenomenon. The Lancet Neurology, 2011. 10(8): p. 734-744.
113. Grahn, J.A. and M. Brett, Impairment of beat-based rhythm discrimination in Parkinson's disease. Cortex, 2009. 45(1): p. 54-61.
114. Grahn, J.A. and J.B. Rowe, Feeling the beat: premotor and striatal interactions in musicians and nonmusicians during beat perception. J Neurosci, 2009. 29(23): p. 7540-8.
115. Teki, S., et al., Distinct neural substrates of duration-based and beat-based auditory timing. J Neurosci, 2011. 31(10): p. 3805-12.
116. Fujioka, T., B. Ross, and L.J. Trainor, Beta-Band Oscillations Represent Auditory Beat and Its Metrical Hierarchy in Perception and Imagery. J Neurosci, 2015. 35(45): p. 15187-98.
117. Nozaradan, S., et al., Capturing with EEG the neural entrainment and coupling underlying sensorimotor synchronization to the beat. Cereb Cortex, 2015. 25(3): p. 736-47.
118. Damm, L., et al., Why do we move to the beat? A multi-scale approach, from physical principles to brain dynamics. Neurosci Biobehav Rev, 2020. 112: p. 553-584.
119. Braunlich, K., et al., Rhythmic auditory cues shape neural network recruitment in Parkinson's disease during repetitive motor behavior. Eur J Neurosci, 2019. 49(6): p. 849-858.
120. Grahn, J.A., The role of the basal ganglia in beat perception: neuroimaging and neuropsychological investigations. Ann N Y Acad Sci, 2009. 1169: p. 35-45.
121. Grahn, J.A., M.J. Henry, and J.D. McAuley, FMRI investigation of cross-modal interactions in beat perception: audition primes vision, but not vice versa. Neuroimage, 2011. 54(2): p. 1231-43.
122. Merchant, H., et al., Finding the beat: a neural perspective across humans and non-human primates. Philos Trans R Soc Lond B Biol Sci, 2015. 370(1664): p. 20140093.
123. Nozaradan, S., et al., Specific contributions of basal ganglia and cerebellum to the neural tracking of rhythm. Cortex, 2017. 95: p. 156-168.
124. Fujioka, T., et al., Internalized timing of isochronous sounds is represented in neuromagnetic beta oscillations. J Neurosci, 2012. 32(5): p. 1791-802.
125. Cirelli, L.K., et al., Beat-induced fluctuations in auditory cortical beta-band activity: using EEG to measure age-related changes. Front Psychol, 2014. 5: p. 742.
126. Nozaradan, S., Exploring how musical rhythm entrains brain activity with electroencephalogram frequency-tagging. Philos Trans R Soc Lond B Biol Sci, 2014. 369(1658): p. 20130393.
127. Tierney, A. and N. Kraus, Neural entrainment to the rhythmic structure of music. J Cogn Neurosci, 2015. 27(2): p. 400-8.
128. Fujioka, T. and B. Ross, Beta-band oscillations during passive listening to metronome sounds reflect improved timing representation after short-term musical training in healthy older adults. Eur J Neurosci, 2017. 46(8): p. 2339-2354.
129. Li, Q., et al., Distinct neuronal entrainment to beat and meter: Revealed by simultaneous EEG-fMRI. Neuroimage, 2019. 194: p. 128-135.
130. Patel, A.D., et al., The influence of metricality and modality on synchronization with a beat. Exp Brain Res, 2005. 163(2): p. 226-38.
131. Repp, B.H., Hearing a melody in different ways: multistability of metrical interpretation, reflected in rate limits of sensorimotor synchronization. Cognition, 2007. 102(3): p. 434-54.
132. Thaut, M.H., et al., Distinct cortico-cerebellar activations in rhythmic auditory motor synchronization. Cortex, 2009. 45(1): p. 44-53.
133. Merchant, H., et al., Measuring time with different neural chronometers during a synchronization-continuation task. Proc Natl Acad Sci U S A, 2011. 108(49): p. 19784-9.
134. Bellinger, D., E. Altenmuller, and J. Volkmann, Perception of Time in Music in Patients with Parkinson's Disease-The Processing of Musical Syntax Compensates for Rhythmic Deficits. Front Neurosci, 2017. 11: p. 68.
135. Vikene, K., G.O. Skeie, and K. Specht, Abnormal phasic activity in saliency network, motor areas, and basal ganglia in Parkinson's disease during rhythm perception. Hum Brain Mapp, 2019. 40(3): p. 916-927.
136. Nishida, D., et al., The neural correlates of gait improvement by rhythmic sound stimulation in adults with Parkinson's disease - A functional magnetic resonance imaging study. Parkinsonism Relat Disord, 2021. 84: p. 91-97.
137. Gulberti, A., et al., Predictive timing functions of cortical beta oscillations are impaired in Parkinson's disease and influenced by L-DOPA and deep brain stimulation of the subthalamic nucleus. Neuroimage Clin, 2015. 9: p. 436-49.
138. Puyjarinet, F., et al., Heightened orofacial, manual, and gait variability in Parkinson's disease results from a general rhythmic impairment. NPJ Parkinsons Dis, 2019. 5: p. 19.
139. Tolleson, C.M., et al., Dysrhythmia of timed movements in Parkinson's disease and freezing of gait. Brain Res, 2015. 1624: p. 222-231.
140. Vercruysse, S., et al., Abnormalities and cue dependence of rhythmical upper-limb movements in Parkinson patients with freezing of gait. Neurorehabil Neural Repair, 2012. 26(6): p. 636-45.

校內：立即公開
校外：立即公開

簡易檢索 / 詳目顯示

相關論文