Radiology Alchemy: GAN We Do It?

Yi, Paul H.; Fritz, Jan

doi:10.1148/ryai.2021210125

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generated images often appear oversmoothed and thus visually differ substantially from conventional MR images, which can contribute to lower reader acceptance and diagnostic confidence. A potential solution to address this difference is using a GAN 83 . Generative adversarial networks use a second discriminator CNN, which is trained to distinguish between predicted and fully sampled reference images.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

“…A potential solution to address this difference is using a GAN. 83 Generative adversarial networks use a second discriminator CNN, which is trained to distinguish between predicted and fully sampled reference images. For example, as part of the SANTIS (sampling-augmented neural network with incoherent structure) model, Liu et al 84 use a GAN that enforces data consistency and features 3 loss components in contrast to other image-space methods with a single pixel-wise loss function.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence–Driven Ultra-Fast Superresolution MRI

2022

Self Cite

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is the keystone of modern musculoskeletal imaging; however, long pulse sequence acquisition times may restrict patient tolerability and access. Advances in MRI scanners, coil technology, and innovative pulse sequence acceleration methods enable 4-fold turbo spin echo pulse sequence acceleration in clinical practice; however, at this speed, conventional image reconstruction approaches the signal-to-noise limits of temporal, spatial, and contrast resolution. Novel deep learning image reconstruction methods can minimize signal-to-noise interdependencies to better advantage than conventional image reconstruction, leading to unparalleled gains in image speed and quality when combined with parallel imaging and simultaneous multislice acquisition. The enormous potential of deep learning-based image reconstruction promises to facilitate the 10-fold acceleration of the turbo spin echo pulse sequence, equating to a total acquisition time of 2-3 minutes for entire MRI examinations of joints without sacrificing spatial resolution or image quality. Current investigations aim for a better understanding of stability and failure modes of image reconstruction networks, validation of network reconstruction performance with external data sets, determination of diagnostic performances with independent reference standards, establishing generalizability to other centers, scanners, field strengths, coils, and anatomy, and building publicly available benchmark data sets to compare methods and foster innovation and collaboration between the clinical and image processing community. In this article, we review basic concepts of deep learning-based acquisition and image reconstruction techniques for accelerating and improving the quality of musculoskeletal MRI, commercially available and developing deep learning-based MRI solutions, superresolution, denoising, generative adversarial networks, and combined strategies for deep learning-driven ultra-fast superresolution musculoskeletal MRI. This article aims to equip radiologists and imaging scientists with the necessary practical knowledge and enthusiasm to meet this exciting new era of musculoskeletal MRI.

show abstract

Section: Generative Adversarial Networkmentioning

confidence: 99%

Section: Generative Adversarial Networkmentioning

confidence: 99%