請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93939完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳中平 | zh_TW |
| dc.contributor.advisor | Chung-Ping Chen | en |
| dc.contributor.author | 周信頤 | zh_TW |
| dc.contributor.author | Hsin-Yi Chou | en |
| dc.date.accessioned | 2024-08-09T16:33:32Z | - |
| dc.date.available | 2024-08-10 | - |
| dc.date.copyright | 2024-08-09 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-02 | - |
| dc.identifier.citation | [1] World Health Organization. Depressive disorder. 2023.
[2] Cheng-Ta Li et. al. Treatment-Resistant Depression Part A. Elsevier, 2023. [3] Jean-Pierre Lépine and Mike Briley. The increasing burden of depression. Neuropsychiatric disease and treatment, 7(sup1):3–7, 2011. [4] Wolfgang Marx, Brenda WJH Penninx, Marco Solmi, Toshi A Furukawa, Joseph Firth, Andre F Carvalho, and Michael Berk. Major depressive disorder. Nature Reviews Disease Primers, 9(1):44, 2023. [5] Cheng-Ta Li and Ming-Been Lee. Evidence-based somatic treatments and brain abnormalities for suicidality in patients with depression. Journal of Suicidology, 17(1):3–13, 2022. [6] American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders. American Psychiatric Publishing, Arlington, VA, 5th edition, 2013. [7] Max Hamilton. A rating scale for depression. Journal of neurology, neurosurgery, and psychiatry, 23(1):56, 1960. [8] A John Rush, Madhukar H Trivedi, Stephen R Wisniewski, Andrew A Nierenberg,Jonathan W Stewart, Diane Warden, George Niederehe, Michael E Thase, Philip W Lavori, Barry D Lebowitz, et al. Acute and longer-term outcomes in depressed out-patients requiring one or several treatment steps: a star* d report. American Journal of Psychiatry, 163(11):1905–1917, 2006. [9] Diane Warden, A John Rush, Madhukar H Trivedi, Maurizio Fava, and Stephen R Wisniewski. The star* d project results: a comprehensive review of findings. Current psychiatry reports, 9(6):449–459, 2007. [10] Giuseppe Maina, Marina Adami, Giuseppe Ascione, Emi Bondi, Domenico De Be-rardis, Dario Delmonte, Silvia Maffezzoli, Giovanni Martinotti, Alessandra Nivoli,Elena Ottavianelli, et al. Nationwide consensus on the clinical management oftreatment-resistant depression in italy: a delphi panel. Annals of General Psychiatry, 22(1):48, 2023. [11] Abebaw Fekadu, Sarah Wooderson, Catherine Donaldson, Kalypso Markopoulou,Brendan Masterson, Lucia Poon, and Anthony J Cleare. A multidimensional tool toquantify treatment resistance in depression: the maudsley staging method. Journal of Clinical Psychiatry, 70(2):177, 2009. [12] Nida Aslam, Irfan Ullah Khan, Asma Bashamakh, Fatima A Alghool, Menna Aboulnour, Noorah M Alsuwayan, Rawa＇a K Alturaif, Samiha Brahimi, Sumayh S Aljameel, and Kholoud Al Ghamdi. Multiple sclerosis diagnosis using machine learning and deep learning: challenges and opportunities. Sensors, 22(20):7856, 2022. [13] Pierpaolo Alongi, Riccardo Laudicella, Francesco Panasiti, Alessandro Stefano, Albert Comelli, Paolo Giaccone, Annachiara Arnone, Fabio Minutoli, Natale Quartuccio, Chiara Cupidi, et al. Radiomics analysis of brain [18f] fdg pet/ct to predict alzheimer＇s disease in patients with amyloid pet positivity: A preliminary report on the application of spm cortical segmentation, pyradiomics and machine-learning analysis. Diagnostics, 12(4):933, 2022. [14] Jie Mei, Christian Desrosiers, and Johannes Frasnelli. Machine learning for the diag- nosis of parkinson’s disease: a review of literature. Frontiers in aging neuroscience,13:633752, 2021. [15] Min-Yi Chen. Using fdg-pet brain signals for diagnosing major depressive disorder based on machine learning and deep learning. July 2022. 基於機器學習與深度學習之 FDG-PET 腦造影分類模型基於重度憂鬱症之診斷. [16] Loveleen Gaur, Mohan Bhandari, Tanvi Razdan, Saurav Mallik, and Zhongming Zhao. Explanation-driven deep learning model for prediction of brain tumour status using mri image data. Frontiers in genetics, 13:822666, 2022. [17] Yixin Wang, Jinwei Lang, Joey Zhaoyu Zuo, Yaqin Dong, Zongtao Hu, Xiuli Xu, Yongkang Zhang, Qinjie Wang, Lizhuang Yang, Stephen TC Wong, et al. The radiomic-clinical model using the shap method for assessing the treatment response of whole-brain radiotherapy: a multicentric study. European Radiology,32(12):8737–8747, 2022. [18] Wayne C Drevets, Joseph L Price, and Maura L Furey. Brain structural and func-tional abnormalities in mood disorders: implications for neurocircuitry models of depression. Brain structure and function, 213:93–118, 2008. [19] Cheng-Ta Li, Tung-Ping Su, Shyh-Jen Wang, Pei-Chi Tu, and Jen-Chuen Hsieh.Prefrontal glucose metabolism in medication-resistant major depression. The BritishJournal of Psychiatry, 206(4):316–323, 2015. [20] Lauren Atkinson, Anjali Sankar, Tracey M Adams, and Cynthia HY Fu. Recentadvances in neuroimaging of mood disorders: structural and functional neural cor-relates of depression, changes with therapy, and potential for clinical biomarkers.Current Treatment Options in Psychiatry, 1:278–293, 2014. [21] Cheng-Ta Li, Shyh-Jen Wang, Jussi Hirvonen, Jen-Chuen Hsieh, Ya-Mei Bai, Chen-Jee Hong, Ying-Jay Liou, and Tung-Ping Su. Antidepressant mechanism of add-onrepetitive transcranial magnetic stimulation in medication-resistant depression using cerebral glucose metabolism. Journal of affective disorders, 127(1-3):219–229,2010. [22] Nora Runia, Dilan E Yücel, Anja Lok, Kiki de Jong, Damiaan AJP Denys, Guido Avan Wingen, and Isidoor O Bergfeld. The neurobiology of treatment-resistant depression: A systematic review of neuroimaging studies. Neuroscience & Biobehavioral Reviews, 132:433–448, 2022. [23] Zongling He, Qian Cui, Junjie Zheng, Xujun Duan, Yajing Pang, Qing Gao, Shao-qiang Han, Zhiliang Long, Yifeng Wang, Jiao Li, Xiao Wang, Jingping Zhao, and Huafu Chen. Frequency-specific alterations in functional connectivity in treatment-resistant and -sensitive major depressive disorder. Journal of Psychiatric Research,82:30–39, 2016. [24] Joseph L Price and Wayne C Drevets. Neurocircuitry of mood disorders. Neuropsychopharmacology, 35(1):192–216, 2010. [25] Peishan Dai, Tong Xiong, Xiaoyan Zhou, Yilin Ou, Yang Li, Xiaoyan Kui, Zail-iang Chen, Beiji Zou, Weihui Li, Zhongchao Huang, et al. The alterations of brain functional connectivity networks in major depressive disorder detected by machine learning through multisite rs-fmri data. Behavioural brain research, 435:114058, 2022. [26] Chien-Sheng Chen. Eeg analysis for prediction of antidepressant responses of transcranial magnetic stimulation in major depressive disorder based on attentional convolution time series prototypical neural network model and classical/quantum machine learning approaches. 2021. [27] Chih-An Lai. Manipulated eeg signals predict severity of depression, refractoriness,and suicide risk in patients with major depressive disorder based on machine learning approaches. 2023. [28] Ismet Sarikaya, Ali Sarikaya, and Abdelhamid H Elgazzar. Current status of 18f-fdg pet brain imaging in patients with dementia. Journal of nuclear medicine technology, 46(4):362–367, 2018. [29] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017. [30] Abebaw Fekadu, Sarah C Wooderson, Kalypso Markopoulou, and Anthony J Cleare. The maudsley staging method for treatment-resistant depression: prediction of longer-term outcome and persistence of symptoms. Journal of Clinical Psychiatry,70(7):952, 2009. [31] Wellcome Trust Centre for Neuroimaging. SPM12, 2014. Functional Imaging Laboratory, Institute of Neurology, University College London, London, UK. [32] Cheng-Ta Li, Mu-Hong Chen, Chi-Hung Juan, Ren-Shyan Liu, Wei-Chen Lin,Ya-Mei Bai, and Tung-Ping Su. Effects of prefrontal theta-burst stimulation on brain function in treatment-resistant depression: a randomized sham-controlled neuroimaging study. Brain stimulation, 11(5):1054–1062, 2018. [33] Corinna Cortes and Vladimir Vapnik. Support-vector networks. Machine learning,20:273–297, 1995. [34] James. 資料分析機器學習第 3.4 講：支援向量機 (support vector machine) 介紹. 2023. [35] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau,M. Brucher, M. Perrot, and E. Duchesnay. Support vector machines —scikit-learn 1.5.0 documentation. 2011. [36] Leo Breiman. Random forests. Machine learning, 45(1):5–32, 2001. [37] Abhinav Jaswal and Jonathan Liu. Random forest algorithm: A complete guide.2023. [38] David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. Learning representations by back-propagating errors. Nature, 323(6088):533–536, 1986. [39] DataCamp. Multilayer perceptrons in machine learning, 2023. [40] IndianTechWarrior. Perceptrons and multi-layer perceptrons, 2023. [41] Logistic regression, 2021. [42] OpenClassrooms. Understand the logistic regression algorithm. 2021. [43] Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. pages 785–794, 2016. [44] Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, 2017. [45] Anna Veronika Dorogush, Vasily Ershov, and Andrey Gulin. Catboost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363, 2018. [46] Catboost, 2021. [47] Sakshi Gupta. Xgboost vs. catboost vs. lightgbm: How do they compare? 2020. [48] Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. Optuna: A next-generation hyperparameter optimization framework. pages 2623–2631, 2019. [49] Eric Brochu, Vlad M Cora, and Nando De Freitas. A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv preprint arXiv:1012.2599,2010. [50] James Bergstra, Rémi Bardenet, Yoshua Bengio, and Balázs Kégl. Algorithms for hyper-parameter optimization. Advances in neural information processing systems,24, 2011. [51] Qiuyue Wang and Greg Page. Hard-voting and soft-voting classification ensembles:An introduction, 2020. [52] Muhammad Saqlain, Bilguun Jargalsaikhan, and Jong Yun Lee. A voting ensembleclassifier for wafer map defect patterns identification in semiconductor manufactur-ing. IEEE Transactions on Semiconductor Manufacturing, 32(2):171–182, 2019. [53] Syed Waseem Abbas Sherazi, Jang-Whan Bae, and Jong Yun Lee. A soft voting ensemble classifier for early prediction and diagnosis of occurrences of major adverse cardiovascular events for stemi and nstemi during 2-year follow-up in patients with acute coronary syndrome. PloS one, 16(6):e0249338, 2021. [54] Ron Kohavi et al. A study of cross-validation and bootstrap for accuracy estimation and model selection. 14(2):1137–1145, 1995. [55] Payam Refaeilzadeh, Lei Tang, and Huan Liu. Cross-validation. Encyclopedia of Database Systems, 2009. [56] Scikit learn Developers. Cross-validation indices, 2023. [57] Nitesh V Chawla, Kevin W Bowyer, Lawrence O Hall, and W Philip Kegelmeyer. Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357, 2002. [58] ITHome. 資料科學家幫你理解：smote 技術 - 如何用少數群體過取樣解決不平 衡資料集的問題, 2023. [59] Parul Gautam. Understanding confusion matrix, 2018. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93939 | - |
| dc.description.abstract | 重度憂鬱症是嚴重且易反覆發作的精神疾病，對患者的生活品質會造成重大影響，若不及早正確治療將可能發展成慢性病。憂鬱症的治療是新興關注議題，世界衛生組織 (WHO) 更預估於 2030 年，憂鬱症將會成為影響全人類最嚴重的疾病之一。而部分重度憂鬱症患者使用多種常規抗憂鬱症藥物的治療效果不佳，需要採用如 rTMS(重覆經顱磁刺激) 等方式或個別化進一步治療，為頑固型憂鬱症(Treatment-resistant Depression)。近年來的大量研究更指出，除了頑固性、嚴重性不一外，重度憂鬱症在不同腦區代謝之異常亦有其異質性。因此，如何在臨床評估時提供更為精準的頑固性、嚴重性預測及腦區特異對於患者的治療進程至關重要。在此研究中，將共 219 位重度憂鬱症之患者 FDG-PET 腦部正子造影作為資料集，分別針對:(1) 頑固性及 (2) 嚴重性運用七個機器學習模型，並透過 optuna調整超參數並進行集成學習投票，預測、量化出患者結果；其中在頑固性模型部分，我們更進一步分析整體訓練集之腦區特徵 SHAP Value，運用在測試集腦區顯著特徵預測。在獨立測試集上我們的模型達到之預測準確度結果分別為: 頑固性83.3%，嚴重性 87.0%，並分析出對於頑固性模型來說重要的腦區特徵，包括前額葉皮質、梭狀回、赫氏迴、顳極等，並和過往相關研究比較進行討論。 | zh_TW |
| dc.description.abstract | Major depressive disorder (MDD) is a severe and recurrent mental illness that significantly impacts patients’ quality of life. If not treated correctly and promptly, it can develop into a chronic condition. The treatment of depression has gained significant attention, with the World Health Organization (WHO) projecting that by 2030, it will rank among the most serious health conditions impacting humanity. Some patients with major depressive disorder do not respond well to standard antidepressant medications and require personalized treatments or advanced methods such as repetitive transcranial magnetic stimulation (rTMS). These cases are termed treatment-resistant depression (TRD). Recent studies have highlighted the heterogeneity in metabolic abnormalities across different brain regions in MDD, including variability in resistance and severity. Thus, providing precise predictions for resistance, severity, and specific brain regions is crucial for improving treatment outcomes.
This study involved FDG-PET brain imaging of 219 MDD patients, employing seven machine-learning models to predict and quantify (1) resistance and (2) severity. Hyperparameters were tuned using Optuna, and ensemble learning voting was used for predictions. For the resistance model, SHAP values of brain region features were analyzed on the training set and applied to significant features in the test set. The achieved prediction accuracies on the independent test set were 83.3% for resistance and 87.0% for severity. Important brain region features for the resistance model included the prefrontal cortex, fusiform gyrus, Heschl’s gyrus, temporal pole, etc., with comparisons made to previous related studies. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-09T16:33:32Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-09T16:33:32Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Contents
Acknowledgements ii 摘要 iv Abstract v Contents vii List of Figures x List of Tables xiii Chapter 1 Introduction 1 1.1 Major Depressive Disorder . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Clinical assessment for MDD . . . . . . . . . . . . . . . . . . . . . 2 1.3 Treatment Resistant Depression . . . . . . . . . . . . . . . . . . . . 2 1.4 Fluorodeoxyglucose Positron Emission Tomography . . . . . . . . . 4 1.5 Thesis Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 Chapter 2 Previous Research 7 2.1 Brain Dysfunction in MDD, TRD . . . . . . . . . . . . . . . . . . . 7 2.2 Machine Learning on MDD Analysis & Previous Work . . . . . . . . 8 2.3 Aims and Hypothesis . . . . . . . . . . . . . . . . . . . . . . . . . . 10 Chapter 3 Data Acquisition 12 3.1 Patients Recruitment . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2 Psychiatric Evaluations . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.3 PET Data Acquisition . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.4 Demographics of Refractoriness Model . . . . . . . . . . . . . . . . 14 3.5 Demographics of Severity Model . . . . . . . . . . . . . . . . . . . 14 Chapter 4 Methodology 16 4.1 FDG-PET Data Preprocessing . . . . . . . . . . . . . . . . . . . . . 16 4.2 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.2.1 Model Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.2.2 Support Vector Machine . . . . . . . . . . . . . . . . . . . . . . . 21 4.2.3 Random Forest . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 4.2.4 Multi-layer Perceptron . . . . . . . . . . . . . . . . . . . . . . . . 23 4.2.5 Logistic Regression . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.2.6 Extreme Gradient Boosting . . . . . . . . . . . . . . . . . . . . . . 25 4.2.7 Light Gradient Boosting Machine . . . . . . . . . . . . . . . . . . 26 4.2.8 Categorical Boosting . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.2.9 Hyperparameters tuning and Optuna . . . . . . . . . . . . . . . . . 27 4.3 Ensemble Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 4.4 Cross Validation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.5 Data balancing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4.6 SHAP Values and Feature Analysis . . . . . . . . . . . . . . . . . . 32 Chapter 5 Experiment Results 35 5.1 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.1.1 Confusion Matrix . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.1.2 Accuracy, Precision, Recall, Specificity, and F1-score . . . . . . . . 36 5.1.3 P-value (Accuracy > NIR) . . . . . . . . . . . . . . . . . . . . . . 37 5.2 Model Performance on Refractoriness Classification . . . . . . . . . 37 5.3 SHAP Value Analysis Results of Refractoriness Classification Models 39 5.4 Model Performance on Severity Classification . . . . . . . . . . . . 41 5.5 The User Interface of PET Prediction Tool - AIPreDIC . . . . . . . . 42 Chapter 6 Discussion 44 Chapter 7 Conclusion 49 Chapter 8 Future Work 51 References 53 Appendix A — SHAP Analysis Results 61 A.1 Specific 5-Fold Results for Each Model . . . . . . . . . . . . . . . . 61 | - |
| dc.language.iso | en | - |
| dc.title | 基於 FDG-PET 與機器學習量化重度憂鬱症患者之臨床嚴重性及關鍵腦區特徵剖析 | zh_TW |
| dc.title | Based on FDG-PET and Machine Learning to Quantify the Clinical Severity and Analyze Key Brain Region Features in Patients with Major Depressive Disorder | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.coadvisor | 李正達 | zh_TW |
| dc.contributor.coadvisor | Cheng-Ta Li | en |
| dc.contributor.oralexamcommittee | 陳文翔;謝明憲 | zh_TW |
| dc.contributor.oralexamcommittee | Wen-Shiang Chen;Ming-Hsien Hsieh | en |
| dc.subject.keyword | 頑固型憂鬱症,正子造影,機器學習,SHAP,嚴重程度,大腦異常, | zh_TW |
| dc.subject.keyword | Treatment-Resistant Depression,Positron Emission Tomography,Machine Learning,SHAP,Severity,Brain Abnormality, | en |
| dc.relation.page | 78 | - |
| dc.identifier.doi | 10.6342/NTU202402515 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-08-06 | - |
| 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-112-2.pdf 目前未授權公開取用 | 7.35 MB | Adobe PDF |
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。