What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. 
Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of machine learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.

An overview of deep learning in medical imaging focusing on MRI

Thank you for downloading magnetic resonance imaging physical principles and sequence design. As you may know, people have look numerous times for their chosen books like this magnetic resonance imaging physical principles and sequence design, but end up in harmful downloads. Rather than enjoying a good book with a cup of coffee in the afternoon, instead they juggled with some malicious bugs inside their laptop.

Magnetic Resonance Imaging Physical Principles And Sequence Design

What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of deep learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.

U-net is an image segmentation technique developed primarily for image segmentation tasks. These traits provide U-net with a high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in nearly all major image modalities, from CT scans and MRI to X-rays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. Given that U-net’s potential is still increasing, this narrative literature review examines the numerous developments and breakthroughs in the U-net architecture and provides observations on recent trends. We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net. In addition, we review the different image modalities and application areas that have been enhanced by U-net.

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

Demonstrate a novel fast method for reconstruction of multi-dimensional MR fingerprinting (MRF) data using deep learning methods.A neural network (NN) is defined using the TensorFlow framework and trained on simulated MRF data computed with the extended phase graph formalism. The NN reconstruction accuracy for noiseless and noisy data is compared to conventional MRF template matching as a function of training data size and is quantified in simulated numerical brain phantom data and International Society for Magnetic Resonance in Medicine/National Institute of Standards and Technology phantom data measured on 1.5T and 3T scanners with an optimized MRF EPI and MRF fast imaging with steady state precession (FISP) sequences with spiral readout. The utility of the method is demonstrated in a healthy subject in vivo at 1.5T.Network training required 10 to 74 minutes; once trained, data reconstruction required approximately 10 ms for the MRF EPI and 76 ms for the MRF FISP sequence. Reconstruction of simulated, noiseless brain data using the NN resulted in a RMS error (RMSE) of 2.6 ms for T1 and 1.9 ms for T2 . The reconstruction error in the presence of noise was less than 10% for both T1 and T2 for SNR greater than 25 dB. Phantom measurements yielded good agreement (R2  = 0.99/0.99 for MRF EPI T1 /T2 and 0.94/0.98 for MRF FISP T1 /T2 ) between the T1 and T2 estimated by the NN and reference values from the International Society for Magnetic Resonance in Medicine/National Institute of Standards and Technology phantom.Reconstruction of MRF data with a NN is accurate, 300- to 5000-fold faster, and more robust to noise and dictionary undersampling than conventional MRF dictionary-matching.

MR fingerprinting Deep RecOnstruction NEtwork (DRONE)

A rapid technique for quantitative abdominal imaging was developed by using a fast imaging with steady-state free precession MR fingerprinting acquisition in combination with the Bloch-Siegert B1 mapping method, allowing simultaneous quantification of T1 and T2 in the abdomen within a 19-second breath hold.

https://pubs.rsna.org/pb-assets/Radiology/podcasts/transcripts/2016/2016-04-transcript.pdf

MR Fingerprinting for Rapid Quantitative Abdominal Imaging

PURPOSE The goal of this study is to characterize and improve the accuracy of 2D magnetic resonance fingerprinting (MRF) scans in the presence of slice profile (SP) and B1 imperfections, which are two main factors that affect quantitative results in MRF. METHODS The SP and B1 imperfections are characterized and corrected separately. The SP effect is corrected by simulating the radiofrequency pulse in the dictionary, and the B1 is corrected by acquiring a B1 map using the Bloch-Siegert method before each scan. The accuracy, precision, and repeatability of the proposed method are evaluated in phantom studies. The effects of both SP and B1 imperfections are also illustrated and corrected in the in vivo studies. RESULTS The SP and B1 corrections improve the accuracy of the T1 and T2 values, independent of the shape of the radiofrequency pulse. The T1 and T2 values obtained from different excitation patterns become more consistent after corrections, which leads to an improvement of the robustness of the MRF design. CONCLUSION This study demonstrates that MRF is sensitive to both SP and B1 effects, and that corrections can be made to improve the accuracy of MRF with only a 2-s increase in acquisition time. Magn Reson Med 78:1781-1789, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

Slice profile and B1 corrections in 2D magnetic resonance fingerprinting

Purpose The purpose of this study was to accelerate the acquisition and reconstruction time of 3D magnetic resonance fingerprinting scans. Methods A 3D magnetic resonance fingerprinting scan was accelerated by using a single-shot spiral trajectory with an undersampling factor of 48 in the x-y plane, and an interleaved sampling pattern with an undersampling factor of 3 through plane. Further acceleration came from reducing the waiting time between neighboring partitions. The reconstruction time was accelerated by applying singular value decomposition compression in k-space. Finally, a 3D premeasured B1 map was used to correct for the B1 inhomogeneity. Results The T1 and T2 values of the International Society for Magnetic Resonance in Medicine/National Institute of Standards and Technology MRI phantom showed a good agreement with the standard values, with an average concordance correlation coefficient of 0.99, and coefficient of variation of 7% in the repeatability scans. The results from in vivo scans also showed high image quality in both transverse and coronal views. Conclusions This study applied a fast acquisition scheme for a fully quantitative 3D magnetic resonance fingerprinting scan with a total acceleration factor of 144 as compared with the Nyquist rate, such that 3D T1 , T2 , and proton density maps can be acquired with whole-brain coverage at clinical resolution in less than 5 min. Magn Reson Med 79:2190-2197, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Fast 3D magnetic resonance fingerprinting for a whole-brain coverage.

Purpose To reduce the acquisition time needed to obtain reliable parametric maps with Magnetic Resonance Fingerprinting. Methods An iterative-denoising algorithm is initialized by reconstructing the MRF image series at low image resolution. For subsequent iterations, the method enforces pixel-wise fidelity to the best-matching dictionary template then enforces fidelity to the acquired data at slightly higher spatial resolution. After convergence, parametric maps with desirable spatial resolution are obtained through template matching of the final image series. The proposed method was evaluated on phantom and in vivo data using the highly undersampled, variable-density spiral trajectory and compared with the original MRF method. The benefits of additional sparsity constraints were also evaluated. When available, gold standard parameter maps were used to quantify the performance of each method. Results The proposed approach allowed convergence to accurate parametric maps with as few as 300 time points of acquisition, as compared to 1000 in the original MRF work. Simultaneous quantification of T1, T2, proton density (PD), and B0 field variations in the brain was achieved in vivo for a 256 × 256 matrix for a total acquisition time of 10.2 s, representing a three-fold reduction in acquisition time. Conclusion The proposed iterative multiscale reconstruction reliably increases MRF acquisition speed and accuracy. Magn Reson Med 75:2481-2492, 2016. © 2015 Wiley Periodicals, Inc.

/pdf/multiscale-reconstruction-for-mr-fingerprinting-lx3eohrguw.pdf

Multiscale reconstruction for MR fingerprinting.

Magnetic resonance fingerprinting (MRF) is a quantitative imaging technique that can simultaneously measure multiple important tissue properties of human body. Although MRF has demonstrated improved scan efficiency as compared to conventional techniques, further acceleration is still desired for translation into routine clinical practice. The purpose of this paper is to accelerate MRF acquisition by developing a new tissue quantification method for MRF that allows accurate quantification with fewer sampling data. Most of the existing approaches use the MRF signal evolution at each individual pixel to estimate tissue properties, without considering the spatial association among neighboring pixels. In this paper, we propose a spatially constrained quantification method that uses the signals at multiple neighboring pixels to better estimate tissue properties at the central pixel. Specifically, we design a unique two-step deep learning model that learns the mapping from the observed signals to the desired properties for tissue quantification, i.e.: 1) with a feature extraction module for reducing the dimension of signals by extracting a low-dimensional feature vector from the high-dimensional signal evolution and 2) a spatially constrained quantification module for exploiting the spatial information from the extracted feature maps to generate the final tissue property map. A corresponding two-step training strategy is developed for network training. The proposed method is tested on highly undersampled MRF data acquired from human brains. Experimental results demonstrate that our method can achieve accurate quantification for T1 and T2 relaxation times by using only 1/4 time points of the original sequence (i.e., four times of acceleration for MRF acquisition).

/pdf/erratum-to-deep-learning-for-fast-and-spatially-constrained-586vfabv7a.pdf

Yong Chen

Papers

MR Fingerprinting for Rapid Quantitative Abdominal Imaging

Slice profile and B1 corrections in 2D magnetic resonance fingerprinting

Fast 3D magnetic resonance fingerprinting for a whole-brain coverage.

Multiscale reconstruction for MR fingerprinting.

Erratum to “Deep Learning for Fast and Spatially Constrained Tissue Quantification From Highly Accelerated Data in Magnetic Resonance Fingerprinting”