Biomedical image reconstruction: from the foundations to deep neural networks

DOI10.1561/2000000101MaRDI QIDQ5213208zbMATH OpenOpenAlexWikidataFDO

Authors Michael T. McCann, M. Unser

Publication date 31 January 2020

Published in Foundations and Trends® in Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1901.03565

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Research exposition (monographs, survey articles) pertaining to biology (92-02) Biomedical imaging and signal processing (92C55)

Abstract: This tutorial covers biomedical image reconstruction, from the foundational concepts of system modeling and direct reconstruction to modern sparsity and learning-based approaches. Imaging is a critical tool in biological research and medicine, and most imaging systems necessarily use an image-reconstruction algorithm to create an image; the design of these algorithms has been a topic of research since at least the 1960's. In the last few years, machine learning-based approaches have shown impressive performance on image reconstruction problems, triggering a wave of enthusiasm and creativity around the paradigm of learning. Our goal is to unify this body of research, identifying common principles and reusable building blocks across decades and among diverse imaging modalities. We first describe system modeling, emphasizing how a few building blocks can be used to describe a broad range of imaging modalities. We then discuss reconstruction algorithms, grouping them into three broad generations. The first are the classical direct methods, including Tikhonov regularization; the second are the variational methods based on sparsity and the theory of compressive sensing; and the third are the learning-based (also called data-driven) methods, especially those using deep convolutional neural networks. There are strong links between these generations: classical (first-generation) methods appear as modules inside the latter two, and the former two are used to inspire new designs for learning-based (third-generation) methods. As a result, a solid understanding of all of three generations is necessary for the design of state-of-the-art algorithms.

Recommendations

• A review on deep learning in medical image reconstruction
• Deep Learning--Based Dictionary Learning and Tomographic Image Reconstruction
• Deep learning for photoacoustic tomography from sparse data
• Computed tomography reconstruction using deep image prior and learned reconstruction methods
• Tomographic image reconstruction using training images

Cited in

(12)

• A review on deep learning in medical image reconstruction
• Recent development of dual-dictionary learning approach in medical image analysis and reconstruction
• Computed tomography reconstruction using deep image prior and learned reconstruction methods
• Solving inverse problems using data-driven models
• Bilevel Methods for Image Reconstruction
• Model-Based Deep Learning
• On mathematical modeling in image reconstruction and beyond
• Stability of data-dependent ridge-regularization for inverse problems
• Convergence analysis of the discretization of continuous-domain inverse problems
• The troublesome kernel: on hallucinations, no free lunches, and the accuracy-stability tradeoff in inverse problems
• Data-driven regularization with weak convexity for robust image reconstruction
• Universal architectures for the learning of polyhedral norms and convex regularizers

This page was built for publication: Biomedical image reconstruction: from the foundations to deep neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5213208)