Super-resolution musculoskeletal MRI using deep learning.
Citations
991 citations
590 citations
Cites methods from "Super-resolution musculoskeletal MR..."
...generating super-resolution single (no reference information) and multi-contrast (applying a high-resolution image of another modality as reference) brain MR images using CNNs [196]; constructing superresolution brain MRI by a CNN stacked by multi-scale fusion units [197]; and super-resolution musculoskeletal MRI (“DeepResolve”) [198]....
[...]
246 citations
242 citations
201 citations
References
111,197 citations
"Super-resolution musculoskeletal MR..." refers methods in this paper
...DeepResolve training was performed on 124 data sets using stochastic gradient descent using Keras and a Tensorflow backend (Google, Mountain View, CA).(34,35) Hyperparameter optimization was performed by minimizing L2 loss on the 35 validation data sets with a learning rate of 0....
[...]
73,978 citations
64,109 citations
"Super-resolution musculoskeletal MR..." refers methods in this paper
...99).(41) FIGURE 5 Example coronal ground-truth, DeepResolve, and TCI images are shown (A-C) in addition to the generated DeepResolve residual map (D) in comparison with the actual residual between the ground truth and TCI (E)....
[...]
...A linearly-weighted Cohen’s kappa (j) and its confidence interval were calculated to evaluate interreader variability for the image quality ratings and the image rankings.(41,42) All numerical analysis and data preprocessing were performed using MATLAB....
[...]
55,235 citations
"Super-resolution musculoskeletal MR..." refers background in this paper
...It has been shown that filters with larger supports can be effectively decomposed into several smaller filters, introducing unnecessary redundancy during the network training process.(50) As a result, a small convolution kernel efficiently maximized high-resolution feature extraction....
[...]
49,914 citations