A Perspective on Deep Imaging

By Ge Wang. IEEE Access, 2016

418 citations recorded by the source corpus.

The combination of tomographic imaging and deep learning, or machine learning in general, promises to empower not only image analysis but also image reconstruction. The latter aspect is considered in this perspective article with an emphasis on medical imaging to develop a new generation of image reconstruction theories and techniques. This direction might lead to intelligent utilization of domain knowledge from big data, innovative approaches for image reconstruction, and superior performance in clinical and preclinical applications. To realize the full impact of machine learning for tomographic imaging, major theoretical, technical and translational efforts are immediately needed.

Subfields: Biomedical Engineering, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/63be611dc8cf09ed081b4ad2b1756420b782b0be

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Convolutional Neural Network based Metal Artifact Reduction in X-ray Computed Tomography (2017, methodology): “For example, the convolutional neural network (CNN) has been applied to medical imaging for low dose CT reconstruction and artifacts reduction [25]–[34].”
A Gentle Introduction to Deep Learning in Medical Image Processing (2018, background): “With such integrated networks, multi-task learning is enabled, for example, training of networks that deliver optimal reconstruction quality and the best volumetric overlap of the resulting segmentation at the same time, as already conjectured in [116].”
A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution (2018, background): “A forward-thinking review has been published on the subject of applying deep learning for CT [38].”
Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging (2019, background): “However, the theory behind how the network functions has yet to be established (50).”
On Interpretability of Artificial Neural Networks: A Survey (2020, background): “eep learning [71] has become the mainstream approach in many important domains targeting common objects such as text [40], images [182], videos [132], and graphs [88].”
Learning a Variational Network for Reconstruction of Accelerated MRI Data (2017, background): “While deep learning has resulted in clear breakthroughs in Computer Vision, the application of deep learning to medical image reconstruction is just beginning (36).”
Deep learning in medical image registration: a survey (2019, neutral): “In 2016,Wang [107] postulated that deep neural networks could be used to perform image reconstruction.”
Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction (2018, background): “Recently, deep learning techniques have attracted a major attention for tomographic image reconstruction, which is a new area of research [1, 2, 3].”
Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT (2017, background): “CNN using directional wavelets is more efﬁcient in removing low-dose related CT noises. This work was followed by many novel extensions for low-dose CT [17], [18], [19], [20], [21], [22], [23], [24], [25], [26], [27]. Unlike these low-dose artifacts from reduced tube currents, the streaking artifact”
Data Analysis Strategies in Medical Imaging (2018, background): “Although deep learning has recently achieved impressive successes in practice, a strong theoretical backing is yet to be established (36).”
Deep-learning tomography (2018, methodology): “In particular, DNNs provide excellent results for imaging inverse problems such as denoising (Burger et al., 2012; Xie et al., 2012), super-resolution (Dong et al., 2016), compressed sensing (Adler et al., 2017), and X-ray computed tomography (Wang, 2016; Würfl et al., 2016).”
Artificial intelligence in radiology (2018, neutral): “A strong theoretical understanding of deep learning is yet to be established 101 despite the reported successes across many fields — explaining why deep learning layers that lie between inputs and outputs are labelled as ‘hidden layers’ (Box 1; Fig.”
Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss (2017, background): “The recent explosive development of deep neural networks suggests new thinking and huge potential for the medical imaging field [22], [23].”
Redefining Radiology: A Review of Artificial Intelligence Integration in Medical Imaging (2023, background): “On the other hand, the software must be robust, intuitive, and designed to integrate within existing radiological systems, necessitating close collaboration between AI developers, radiologists, and other healthcare professionals [102].”