Name
Abstract | ||
|---|---|---|
This paper presents a fast, high-precision, and fully automatic windowing method based on deep convolutional neural network (CNN) for magnetic resonance imaging (MRI). Displaying a magnetic resonance (MR) image with a data depth of 12/16 bits on regular 8-bit monitors usually needs a windowing process to remap the full range of pixel intensity to a subrange. However, adaptively and automatically adjusting the windowing parameters of MR images under various viewing conditions is a challenging problem in medical image processing due to the low contrast and high grayscale range. We present a novel method based on the deep CNN's to estimate the windowing parameters that can match the adjustment of human experts precisely and quickly. The network acts as a typical end-to-end mapping function that takes the raw pixels of the MR images as input and directly outputs the corresponding estimation of the optimal windowing parameters. To speed up the inference, we utilize a space-to-depth (STD) conversion to reduce the spatial resolution of input images, and thus the computing burden of the inference process. The extensive experiments on the dataset annotated by clinicians show that the proposed method can accurately predict the optimal windowing parameters of an MR image with a size of 1024 x 1024 in less than 0.01 s. Due to the high effectiveness and efficiency of the proposed method, it is highly applicable for various clinical and research purposes. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ACCESS.2019.2918814 | IEEE ACCESS |
Keywords | Field | DocType |
Automatic windowing, convolutional neural network, deep learning, window width and window level, magnetic resonance imaging | Pattern recognition,Computer science,Convolutional neural network,Inference,Image processing,Artificial intelligence,Pixel,Image resolution,Grayscale,Speedup,Distributed computing | Journal |
Volume | ISSN | Citations |
7 | 2169-3536 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaole Zhao | 1 | 14 | 2.38 |
| Tao Zhang | 2 | 220 | 69.03 |
| Hangfei Liu | 3 | 0 | 0.34 |
| Gaiyan Zhu | 4 | 0 | 0.34 |
| Xueming Zou | 5 | 7 | 2.19 |