Deep learning methods for medical image computing.

Thesis (Ph. D.)--University of Rochester. Department of Computer Science, 2020.A long-standing goal of the medical community is to present and analyze medical images efficiently and intelligently. On the one hand, it means to find efficient ways to acquire high-quality medical images that can readily be used by healthcare providers. On the other hand, it means to discover intelligent ways to interpret medical images to facilitate the healthcare delivery. To this end, researchers and medical professionals usually seek to use computerized systems that are empowered by machine learning techniques for the processing of medical images. A pivotal step in applying machine learning is to obtain informative representations that well describe medical images. Conventionally, this is performed with manual feature engineering which however requires considerable domain expertise in medicine. A possible workaround is to allow the model to automatically discover latent representations about the target domain from raw data. To this end, this thesis focuses on deep learning which is only a subset of the broader family of machine learning, but has recently made unprecedented progress and exhibits incredible ability in discovering intricate structures from high dimensional data. For many computer vision tasks, deep learning approaches have achieved state-of-the-art performance by a significant margin. This thesis develops deep learning models and techniques for medical image analysis, reconstruction and synthesis. In medical image analysis, we concentrate on understanding the content of the medical images and giving guidance to medical practitioners. In particular, we investigate deep learning ways to address classification, detection, segmentation and registration of medical images. In medical image reconstruction and synthesis, we propose to use deep learning ways to inherently learn the medical data space and effectively synthesize realistic medical images. For the reconstruction, we aim to generate high-quality medical images with fewer artifacts. For the synthesis, our goal is to generate realistic medical images to help the learning of medical image analysis or reconstruction models. The contribution of this thesis work is threefold. First, we propose a variety of approaches in leveraging deep learning to solve problems in medicine. Second, we show the importance and effectiveness of medical knowledge fusion in the design of deep learning architectures. Third, we show the potential of deep generative models in addressing medical image reconstruction and synthesis problems