Super-resolution application of GAN on brain time-of-flight MR angiography

This study aimed to develop a generative adversarial network (GAN) model to improve the image resolution of brain time-of-flight MR angiography (TOF-MRA), as well as evaluate the image quality and diagnostic utility of the reconstructed images. The results showed that an optimized GAN could significantly improve the image quality and vessel visibility of low-resolution 3D TOF-MRA while maintaining equivalent sensitivity and specificity in detecting aneurysms, stenoses, and occlusions of brain arteries.

Key points

• GAN could significantly improve the image quality and vessel visualization of low-resolution brain MR angiography (MRA).
• With optimally adjusted training parameters, the GAN model did not degrade diagnostic performance by generating substantial false positives or false negatives.
• GAN could be a promising approach for obtaining higher resolution TOF-MRA from images scanned in a fraction of time.

Article: Super-resolution application of generative adversarial network on brain time-of-flight MR angiography: image quality and diagnostic utility evaluation

Authors: Krishna Pandu Wicaksono, Koji Fujimoto, Yasutaka Fushimi, Akihiko Sakata, Sachi Okuchi, Takuya Hinoda, Satoshi Nakajima, Yukihiro Yamao, Kazumichi Yoshida, Kanae Kawai Miyake, Hitomi Numamoto, Tsuneo Saga & Yuji Nakamoto