Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution
| Autor: | Dmitry V. Dylov, Joël Valentin Stadelmann, Sergey Kastryulin, Aleksandr Belov |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 ISBN: 9783030872304 MICCAI (6) |
| DOI: | 10.1007/978-3-030-87231-1_25 |
| Popis: | We went below the MRI acceleration factors (a.k.a., k-space undersampling) reported by all published papers that reference the original fastMRI challenge [29], and then used deep learning based image enhancement methods to compensate for the underresolved images. We thoroughly study the influence of the sampling patterns, the undersampling and the downscaling factors, as well as the recovery models on the final image quality for both the brain and the knee fastMRI benchmarks. The quality of the reconstructed images compares favorably against other methods, yielding an MSE of \(11.4 \cdot 10^{-4}\), a PSNR of 29.6 dB, and an SSIM of 0.956 at \(\times 16\) acceleration factor. More extreme undersampling factors of \(\times 32\) and \(\times 64\) are also investigated, holding promise for certain clinical applications such as computer-assisted surgery or radiation planning. We survey 5 expert radiologists to assess 100 pairs of images and show that the recovered undersampled images statistically preserve their diagnostic value. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|