Improving the Quality of Synthetic FLAIR Images with Deep Learning Using a Conditional Generative Adversarial Network for Pixel-by-Pixel Image Translation

Abstract

BACKGROUND AND PURPOSE: Synthetic FLAIR images are of lower quality than conventional FLAIR images. Here, we aimed to improve the synthetic FLAIR image quality using deep learning with pixel-by-pixel translation through conditional generative adversarial network training. MATERIALS AND METHODS:Forty patients with MS were prospectively included and scanned (3T) to acquire synthetic MR imaging and conventional FLAIR images. Synthetic FLAIR images were created with the SyMRI software. Acquired data were divided into 30 training and 10 test datasets. A conditional generative adversarial network was trained to generate improved FLAIR images from raw synthetic MR imaging data using conventional FLAIR images as targets. The peak signal-to-noise ratio, normalized root mean square error, and the Dice index of MS lesion maps were calculated for synthetic and deep learning FLAIR images against conventional FLAIR images, respectively. Lesion conspicuity and the existence of artifacts were visually assessed. RESULTS:The peak signal-to-noise ratio and normalized root mean square error were significantly higher and lower, respectively, in generated-versus-synthetic FLAIR images in aggregate intracranial tissues and all tissue segments (all P Ͻ .001). The Dice index of lesion maps and visual lesion conspicuity were comparable between generated and synthetic FLAIR images (P ϭ 1 and .59, respectively). Generated FLAIR images showed fewer granular artifacts (P ϭ .003) and swelling artifacts (in all cases) than synthetic FLAIR images. CONCLUSIONS:Using deep learning, we improved the synthetic FLAIR image quality by generating FLAIR images that have contrast closer to that of conventional FLAIR images and fewer granular and swelling artifacts, while preserving the lesion contrast.ABBREVIATIONS: cGAN ϭ conditional generative adversarial network; DL ϭ deep learning; GAN ϭ generative adversarial network; NRMSE ϭ normalized root mean square error; PSNR ϭ peak signal-to-noise ratio Indicates open access to non-subscribers at www.ajnr.org http://dx.

Validation of Deep Learning-Based Artifact Correction on Synthetic FLAIR Images in a Different Scanning Environment

“…The results of the current study also revealed that the DL algorithm using CNN improved the image quality of the synthetic FLAIR images by correcting the typical artifacts in both quantitative and qualitative analyses, and it is consistent with the results of two recent studies [10,11]. In the current study, both NRMSE and PSNR values in the DL-FLAIR image were more distinctive in GM and CSF regions than in WM in the region-wise analyses, which is consistent with the quantitative analysis of the recent study [10].…”

“…Thus, recent studies have developed DL algorithms using variants of CNN to remove synthetic FLAIR artifacts and have thus demonstrated the feasibility of this method. However, two studies presented limitations because they were conducted using the same 3T MR scanner provided by a single vendor, although the institutions were different [10,11]. Therefore, our results are promising for generalizing the application of the DL method for improving synthetic FLAIR image quality because overfitted DL models only work for internal datasets and exhibit poor performance for external datasets [20].…”

“…Second, the quantitative analyses were performed only for 19 patients owing to the mentioned heterogeneity of the conventional FLAIR images. Third, we obtained all data by using a different MR scanner with different scan parameters in a single institution; however, previous studies used scanners from the same vendor [10,11]. Therefore, we expect that future studies with different scanners from other vendors in multiple institutions will be conducted to validate and generalize our results.…”

“…Two recent studies using deep learning (DL) have introduced the improvement of the synthetic FLAIR image quality [10,11]. Although those studies employed different methodological approaches-convolutional neural network with perceptual loss function (CNN) vs. pixel-wise neural network with conditional generative adversarial network (GAN) loss function-both of them showed remarkable potential to solve this issue [10,11]. However, the studies used DL-based correction for a synthetic FLAIR image employed a limited number of study participants at each institution; therefore, these new approaches should be validated in a different scan environment to establish their clinical utility.…”

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation

“…Further, up-and downsampling, scale aggregation, and preclassification with a multicolumn approach could also be used to increase the accuracy of crowd counting. On the other hand, deconvolution [65] and Generative Adversarial Networks (GANs) [66] can be employed to enhance the quality of a density map for medical applications.…”