A Densely Interconnected Network for Deep Learning Accelerated MRI

Autor: Jon André Ottesen, Matthan W. A. Caan, Inge Rasmus Groote, Atle Bjørnerud
Přispěvatelé: Biomedical Engineering and Physics, ANS - Brain Imaging
Rok vydání: 2022
Předmět:
Zdroj: Magma (New York, N.Y.). Springer Verlag
ISSN: 0968-5243
DOI: 10.48550/arxiv.2207.02073
Popis: Objective To improve accelerated MRI reconstruction through a densely connected cascading deep learning reconstruction framework. Materials and methods A cascading deep learning reconstruction framework (reference model) was modified by applying three architectural modifications: input-level dense connections between cascade inputs and outputs, an improved deep learning sub-network, and long-range skip-connections between subsequent deep learning networks. An ablation study was performed, where five model configurations were trained on the NYU fastMRI neuro dataset with an end-to-end scheme conjunct on four- and eightfold acceleration. The trained models were evaluated by comparing their respective structural similarity index measure (SSIM), normalized mean square error (NMSE), and peak signal to noise ratio (PSNR). Results The proposed densely interconnected residual cascading network (DIRCN), utilizing all three suggested modifications achieved a SSIM improvement of 8% and 11%, a NMSE improvement of 14% and 23%, and a PSNR improvement of 2% and 3% for four- and eightfold acceleration, respectively. In an ablation study, the individual architectural modifications all contributed to this improvement for both acceleration factors, by improving the SSIM, NMSE, and PSNR with approximately 2–4%, 4–9%, and 0.5–1%, respectively. Conclusion The proposed architectural modifications allow for simple adjustments on an already existing cascading framework to further improve the resulting reconstructions.
Databáze: OpenAIRE
Externí odkaz: