English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Denoising of magnetic resonance images is beneficial in improving the qualityof low signal-to-noise ratio images. Recently, denoising using deep neuralnetworks has demonstrated promising results. Most of these networks, however,utilize supervised learning, which requires large training images ofnoise-corrupted and clean image pairs. Obtaining training images, particularlyclean images, is expensive and time-consuming. Hence, methods such asNoise2Noise (N2N) that require only pairs of noise-corrupted images have beendeveloped to reduce the burden of obtaining training datasets. In this study,we propose a new self-supervised denoising method, Coil2Coil (C2C), that doesnot require the acquisition of clean images or paired noise-corrupted imagesfor training. Instead, the method utilizes multichannel data from phased-arraycoils to generate training images. First, it divides and combines multichannelcoil images into two images, one for input and the other for label. Then, theyare processed to impose noise independence and sensitivity normalization suchthat they can be used for the training images of N2N. For inference, the methodinputs a coil-combined image (e.g., DICOM image), enabling a wide applicationof the method. When evaluated using synthetic noise-added images, C2C shows thebest performance against several self-supervised methods, reporting comparableoutcomes to supervised methods. When testing the DICOM images, C2C successfullydenoised real noise without showing structure-dependent residuals in the errormaps. Because of the significant advantage of not requiring additional scansfor clean or paired images, the method can be easily utilized for variousclinical applications.

Coil2Coil: Self-supervised MR image denoising using phased-array coil images