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

Purpose: To improve reconstruction fidelity of fine structures and texturesin deep learning (DL) based reconstructions.  Methods: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposedand incorporated into the training of DL-based reconstruction frameworks inorder to preserve perceptual similarity and high-order statistics. The UFLossprovides instance-level discrimination by mapping similar instances to similarlow-dimensional feature vectors and is trained without any human annotation. Byadding an additional loss function on the low-dimensional feature space duringtraining, the reconstruction frameworks from under-sampled or corrupted datacan reproduce more realistic images that are closer to the original with finertextures, sharper edges, and improved overall image quality. The performance ofthe proposed UFLoss is demonstrated on unrolled networks for accelerated 2D and3D knee MRI reconstruction with retrospective under-sampling. Quantitativemetrics including NRMSE, SSIM, and our proposed UFLoss were used to evaluatethe performance of the proposed method and compare it with others.  Results: In-vivo experiments indicate that adding the UFLoss encouragessharper edges and more faithful contrasts compared to traditional andlearning-based methods with pure l2 loss. More detailed textures can be seen inboth 2D and 3D knee MR images. Quantitative results indicate thatreconstruction with UFLoss can provide comparable NRMSE and a higher SSIM whileachieving a much lower UFLoss value.  Conclusion: We present UFLoss, a patch-based unsupervised learned featureloss, which allows the training of DL-based reconstruction to obtain moredetailed texture, finer features, and sharper edges with higher overall imagequality under DL-based reconstruction frameworks.

High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Loss