This thesis studies representation learning for medical imaging data analysis. We propose a deep learning framework that is composed of data representation and feature learning. The data representation module deals with challenges arising from the need to analyze the various types of data from medical imaging. Examples of such data include 1D physiological signals, 2D high-resolution images and 3D human shape. The framework uses deep convolutional neural networks (CNN) and deep recurrent neural networks (RNN) for feature learning from the data representations. Through validations, the proposed framework proves effective in learning representations for detecting abnormalities in the physiological signals and the medical images, as well as identifying landmarks from the human shape data. The framework starts from converting the various types of medical imaging data to 2D visual representations unanimously. Transfer learning is a technique for addressing data insufficiency problems in deep learning. With this technique, the framework uses deep CNNs pre-trained on large-scale 2D image sets to extract deep features from the data representations. In applications where the medical data are in a sequential form, the framework also integrates deep RNNs to conduct representation learning in spatial, spectral and temporal domains. We introduce the representation learning framework through selected tasks, including detecting cardiac murmurs from phonocardiograms (PCGs), recognizing masses and calcifications in mammograms, and locating anatomical landmarks on First of all, I would like to thank my thesis advisors, Prof. Rafik Goubran and Dr. Chang Shu. I acknowledge them for their guidance, advice and time during this journey. This thesis would not have been possible without their great support. I appreciate the feedback and comments from my thesis defense committee. In particular, Prof. Farida Cheriet provided constructive comments and suggestions on how to improve my thesis. Prof. Michel Nakhla gave me suggestions on how to introduce the framework to people outside of the field. Prof. Robert Laganière motivated me with challenging questions. Prof. Richard Yu inspired me to frame my work in a broader perspective. Their inputs have helped me to improve my thesis. I would like to thank my colleagues and friends. When I started doing the study, I received training on medical device research from Prof. Tofy Mussivand at Ottawa Heart Institute. Prof. Xiaodan Zhu gave me advice on integrating deep learning with many applications. I have learned from Dr. Hongyu Guo and Prof. Yifeng Li through multiple technical discussions. I would also like to thank my managers at National Research Council Canada. Dr. Joel Martin has been very supportive during my Ph.D. study. I also received support from Mr. Louis Borgeat for doing the study. Last but not least, I am very grateful for my family's constant support over the years. vTable of Contents Abstract ii Acknowledgments v Table of Contents vi List of Tables x List of Figures xii Window-sweep...