VŨ DUY THANH MACHINE LEARNING TOOLS FOR DIAGNOSIS OF ALZHEIMER’S DISEASE USING WHOLE GENOME SEQUENCING DATA AND MRI AND PET IMAGES LUẬN VĂN THẠC SĨ NGÀNH ĐIỆN TỬ, NĂNG LƯỢNG ĐIỆN, TỰ ĐỘNG HÓA CHUYÊN NGÀNH KỸ THUẬT TRUYỀN THÔNG VÀ DỮ LIỆU NGƯỜI HƯỚNG DẪN KHOA HỌC GS. Nguyễn Linh Trung GS. Laurent Le Brusquet LAUSANNE, NĂM 2023 MACHINE LEARNING TOOLS FOR DIAGNOSIS OF ALZHEIMER’S DISEASE USING WHOLE GENOME SEQUENCING DATA AND MRI AND PET IMAGES Master thesis of Paris-Saclay University and VNU University of Engineering and Technology Specialization: M2 Data and Communication Engineering Research unit: Centre hospitalier universitaire vaudois Thesis presented at Lausanne, on 21 December 2023 Duy Thanh VU Committee Arnaud BOURNEL Paris-Saclay University Chairman Arthur TENENHAUS CNRS, CentraleSupelec, Paris-Saclay University Rapporteur Oliver Y. Chén CHUV and Université de Lausanne Supervisor NGUYEN Linh Trung VNU University of Engineering and Technology Co-supervisor Laurent LE BRUSQUET CNRS, CentraleSupelec, Paris-Saclay University Co-supervisor Pierre DUHAMEL CNRS, CentraleSupelec, Paris-Saclay University Examiner Master Thesis Thesis Supervision Oliver Y.
Chén CHUV and Université de Lausanne Supervisor. NGUYEN Linh Trung VNU University of Engineering and Technology Co-supervisor. Laurent LE BRUSQUET CNRS, CentraleSupelec, Paris-Saclay University Co-supervisor. Acknowledgements This internship thesis is my four-month full-time work at Oliver Chen’s lab at Centre Laboratoire d’Epalinges (CLE) CHUV/UNIL, under the supervision of Prof.
Oliver Chen at the University Hospital of Lausanne (CHUV) and the Uni- versity of Lausanne (UNIL), Prof. Nguyen Linh Trung at VNU University of Engineering and Technology, and Prof. Laurent Le Brusque at Paris-Saclay University. In this internship, I had the chance to have to work in a new environ- ment, meet new people, and a lot of new things to me.
Fortunately, I worked in a great environment with very nice people. Everything treats me well, so I can focus, feel comfortable accomplishing enjoyable and fulfilling tasks, and develop new things for my master’s thesis. Despite the limitations of this thesis, I am happy and proud of what I have accomplished so far. I hope to continue pursuing academic research in the long run.
I would like to express my first great appreciation to my two supervisors for their incredible mentorship and support. Professor Oliver Chen supports funding for this internship thesis. I had a chance to work with him after my bachelor’s degree. His kindness, encouragement, and guidance enabled me to discover my potential and improve my research skills significantly.
With his help, I am now a much better version of myself than I was two years ago. Linh Trung provided me with guidance and support from the beginning day I started doing research and he was also my supervisor during my bachelor’s degree. He inspired me to explore tensor methods for Alzheimer’s disease (AD) study and carefully help to my errors. Laurent specializes in tensor factozation, join analysis of heterogeneous data, and multiway data analysis.
I hope that after this thesis, we can still work together. All my supervisors gave me a lot of freedom to complete my thesis and provided useful comments and edits. I could not have done it without them. I am thankful to have met, worked with, and learned from wonderful colleagues and friends.
I would like to thank Dr. Nguyen Viet Dung and Dr. Le Trung Thanh for guiding me in tensor methods and tensor decomposition since the first time I started my undergraduate research. I want to thank Mr.
Pham Minh Tuan for our discussion on understanding AD, technical preprocessing, and brain positron emission tomography (PET). Special thanks to my labmates, Christelle, and Julien, for helping me when I arrived in Switzerland. I have learned a lot after many discussions on genetics, biology with Christelle, and statistics with Julien. They are all very nice people with many interesting stories that helped me learn and understand more people and life in Switzerland.
I also want to thank my friends, colleagues, and people at AVITECH and VNU-UET in Vietnam who helped me in my master’s program. This research has been done under the research project QG.62 “Multi-dimensional data analysis and applica- tion to Alzheimer’s disease diagnosis” of Vietnam National University, Hanoi. In addition, I would like to thank the Vingroup Innovation Foundation (VINIF) for their support of my master’s program, under code VINIF. I am grateful to my mom and my two sisters for their love and support.
Lastly, this thesis is a gift I specifically want to dedicate to my father in loving memory. I wish I could have completed this master’s degree a year earlier so that he could have read it and felt proud of me. Authorship I solemnly declare that my thesis, titled ’MACHINE LEARNING TOOLS FOR DIAGNOSIS OF ALZHEIMER’S DISEASE US- ING WHOLE GENOME SEQUENCING DATA AND MRI AND PET IMAGES’, is my own research work conducted under the guidance of Prof. NGUYEN Linh Trung, and Prof.
Laurent LE BRUSQUET. The sources used in the thesis are explicitly mentioned in the reference section, with proper citations. The data and results presented in the thesis are entirely truthful, and there is no copying from the works of others. If any discrepancies are found, I take full responsibility and am subject to any disciplinary actions imposed by the university., 2023 Student Vu Duy Thanh Abstract The early, timely, and accurate diagnosis of Alzheimer’s disease (AD), particularly its earlier sign – mild cognitive impairment (MCI), plays an important role in detecting, managing, and potentially treating the disease for both patients and clinicians.
Recent studies have shown that neuroimaging and genetic data provide complementary information for the diagnosis and prognosis of AD. Using fusion, one can integrate these multimodal, multivariate and potentially high-dimensional biomarkers to improve disease assessment. State-of-the-art fusion approaches typically involve linearly combining kernels or similarity matrices from various modalities. These strategies, however, often neglect the interactions among modalities and the fact that the relationship among multimodal data may not be linear.
In addition, existing combination methods omit neighborhood relationships. To address these issues, in this thesis, we present a machine-learning framework specifically designed for data fusion. The framework leverages the strengths of both tensor methods and deep learning to manage multivariate and multimodal data. More concretely, we design two new methods to exploit the inherent complementarity in such datasets by first learning and then fusing kernels within and among modalities.
Technically, the first method – deep kernel learning (DKL) – involves automatically combining multiple kernels through deep learning to uncover the intrinsic complex relationships among modalities. It is a generalized version of several multi-kernel learning methods. The second method – tensor kernel learning (TKL) – involves multi-kernel learning using non-negative CANDECOMP/PARAFAC (CP) decomposition. They serve as augmented kernels to facilitate the learning of optimal kernels and provide a better explanation.
These two methods complement each other in practice. To evaluate the efficiency of DKL and TKL, we use data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), encompassing 331 subjects including 121 cognitively normal individuals, 100 subjects with Mild Cognitive Impairment (MCI), and 110 AD patients. Overall, both DKL and TKL demonstrate improvements regarding AD as- sessment over single-modality approaches. When employed together, DKL and TKL provide new insights into data fusion and multi-kernel learning.
Finally, further simulation studies and data analysis show promises of the proposed methods in learning intricate inter- and intra-modality relationships suitable for both supervised and unsupervised settings.1 Biomarkers for Alzheimer’s Disease .2 Magnetic Resonance Imaging (MRI) .3 Positron emission tomography (PET) .4 Cerebrospinal fluid (CSF) biomarkers .2 Matrix decomposition and Tensor decomposition .1 Singular value decomposition (SVD) .2 Non-negative matrix factorization .3 Tensor notation and tensor operators .4 Different types of tensor decomposition .3 Kernel methods in machine learning. 31 1 3 A Framework for Kernel Combination/Fusion for Alzheimer’s disease accessment 33 3.2 Limitations of current fusion approaches .3 Overview of the proposed framework for kernel learning and kernel combination .2 Kernel construction/representation .3 Kernel learning/combination .1 Deep kernel learning (DKL) .2 Tensor kernel learning (TKL) .4 Feature learning through kernel by manifold learning .1 Dataset and preprocessing .3 Kernel combination using the DKL .1 Influence of different types of loss .2 Influence of number of layers and training iterations .4 Kernel combination using the TKL .1 Advantage of non-negative CP decomposition .2 Influence of rank on non-negative CP decomposition. 54 5 Conclusion and Future Works 55 5.1 CN vs AD .2 CN vs MCI .3 MCI vs AD .1 CN vs AD .2 CN vs MCI .3 MCI vs AD. 65 3 List of Figures 1.1 Structure of Chapter 2.2 Relationship between cell, chromosomes, genes, and DNA.3 Alleles and SNP encoding.5 Progression of Alzheimer’s disease in grey matter atrophy.6 Z score reduction of FDG-PET in a normal cognition subject who transitions to AD and another subject who transitions from MCI to AD.7 The top region shows decreased uptake values in FDG-PET images when comparing AD and high-risk populations to normal controls .8 The top region shows increased uptake values in PIB-PET images when comparing AD and high-risk populations to normal controls .9 Example of a three-order tensor.10 Illustration for different types of three-way tensor decomposition .1 A Data Fusion Framework.2 Proposed DKL model for kernel combination.1 Cerebrospinal fluid (CSF) measures in this study.2 T1-weighted MRI and FDG-PET images of AD patients and healthy control patients.3 Processed T1-weighted MRI and FDG-PET images of AD patients and healthy control patients.4 Comparing results between three groups based on a single modality in (a) Accuracy and (b) AUC.5 Illustrate the kernel of each modality in both supervised and unsupervised kernels.6 Classification performance deteriorates when utilizing only 10 features to represent each subject, re- sulting in degraded results for MRI and PET compared to using the original features.7 Comparing the results of kernel combination using various loss functions in the proposed deep learn- ing model for a three binary group classification.8 Classification results at a train-testing split and at iteration 100 for five deep learning networks trained on five types of loss.9 Classification results at a train-testing split and at iteration 240 for five deep learning networks trained on five types of loss.10 Classification results at a train-testing split and at iteration 320 for five deep learning networks trained on five types of loss.11 Classification results at a train-testing split and at iteration 520 for five deep learning networks trained on five types of loss.12 Influence of number convolutional layers in the DKL on classification accuracy of three binary groups.13 CANDECOMP/PARAFAC (CP) decomposition breaks down the kernels of multiple modalities.14 The impact of the number of tensor ranks in nonnegative CPD on the reconstruction rate.15 The impact of rank on classification accuracy.1 Kernel combination for groups.
66 6 List of Tables 2.1 Associations between MRI and CSF, PET.1 Number of subjects used in the thesis. 41 7 Chapter 1 Introduction Dementia is a broad term used to describe a group of symptoms affecting cognitive functions such as memory, reasoning, and communication. It usually appears in people more than 65 years old. According to the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) of [1], dementia is characterized by several key criteria: (i) significant cognitive decline in one or more domains, as reported by the individual, a knowledgeable informant, or a clinician, (ii) a decline in neurocognitive performance, typically evidenced by test scores falling two or more standard deviations below appropriate norms on formal testing or equivalent evaluation, and (iii) cognitive deficits that are substantial enough to interfere with daily functioning.
There are several types of dementia. Among them, Alzheimer’s disease (AD) is perhaps the most common form. Currently, there is no definitive treatment available for AD. As the global population continues to age, and the number of clinical trial disappointments rises, the prevalence of AD is increasing.
The estimated number of people living with AD worldwide was around 50 million in 2020, and it is projected to reach 152 million by 2050 [2]. As such, it presents significant health, medical and societal challenges. The study of AD is facing several challenges.