Generative adversarial network-based post-processed image super-resolution technology for accelerating brain MRI: comparison with compressed sensing
Generative adversarial network-based post-processed image super-resolution technology for accelerating brain MRI: comparison with compressed sensing
复制标题
DOI：
10.1177/02841851221076330
复制
发表时间：
2022-02
期刊：
影响因子：
1.3
通讯作者：
Wataru Ueki;Tatsuya Nishii;Kensuke Umehara;Junko Ota;Satoshi Higuchi;Y. Ohta;Yasuhiro Nagai
中科院分区：
文献类型：
--
作者：
Wataru Ueki;Tatsuya Nishii;Kensuke Umehara;Junko Ota;Satoshi Higuchi;Y. Ohta;Yasuhiro Nagai
目前尚不清楚基于深度学习的超分辨率技术（SR）或压缩传感技术（CS）是否可以加速磁共振成像（MRI）。目的比较SR加速图像与CS图像与参考2D和3D梯度回波序列（GRE）脑MRI的图像相似性。材料与方法通过减小矩阵大小或增加CS因子，我们前瞻性地获得了20名志愿者的2D和3D GRE图像，其速度比参考时间快1.3倍和2.0倍。对于SR，我们训练了生成对抗网络（GAN），通过双重交叉验证将低分辨率图像提升到参考图像。我们比较了加速图像与参考图像的结构相似性（SSIM）指数。将放射科医师快速鉴别参考图像的错误回答率用作主观图像相似性（ISM）指标。结果SR的SSIM明显高于CS（SSIM=0.9993-0.999 vs.0.9947 -0.9986; P < 0.001）。在2D GRE中，与CS相比，区分SR图像与参考图像具有挑战性（1.3×中ISM指数为40% vs. 17.5%; P = 0.039; 2.0×中ISM指数为17.5% vs. 2.5%; P = 0.034）。在3D GRE中，在2.0倍速度的图像中，CS显示的ISM指数显著高于SR（22.5% vs. 2.5%; P = 0.011）。然而，2.0× CS和1.3× SR的ISM指数相同（22.5% vs. 27.5%; P = 0.62），时间成本相当。结论基于GAN的SR在MRI加速中与2D GRE的图像相似性优于CS。此外，CS在3D GRE中比SR更有优势。
Background It is unclear whether deep-learning–based super-resolution technology (SR) or compressed sensing technology (CS) can accelerate magnetic resonance imaging (MRI) . Purpose To compare SR accelerated images with CS images regarding the image similarity to reference 2D- and 3D gradient-echo sequence (GRE) brain MRI. Material and Methods We prospectively acquired 1.3× and 2.0× faster 2D and 3D GRE images of 20 volunteers from the reference time by reducing the matrix size or increasing the CS factor. For SR, we trained the generative adversarial network (GAN), upscaling the low-resolution images to the reference images with twofold cross-validation. We compared the structural similarity (SSIM) index of accelerated images to the reference image. The rate of incorrect answers of a radiologist discriminating faster and reference image was used as a subjective image similarity (ISM) index. Results The SR demonstrated significantly higher SSIM than the CS (SSIM=0.9993–0.999 vs. 0.9947–0.9986; P < 0.001). In 2D GRE, it was challenging to discriminate the SR image from the reference image, compared to the CS (ISM index 40% vs. 17.5% in 1.3×; P = 0.039 and 17.5% vs. 2.5% in 2.0×; P = 0.034). In 3D GRE, the CS revealed a significantly higher ISM index than the SR (22.5% vs. 2.5%; P = 0.011) in 2.0 × faster images. However, the ISM index was identical for the 2.0× CS and 1.3× SR (22.5% vs. 27.5%; P = 0.62) with comparable time costs. Conclusion The GAN-based SR outperformed CS in image similarity with 2D GRE for MRI acceleration. In addition, CS was more advantageous in 3D GRE than SR.