1 code implementation • 30 Apr 2024 • Dimitrios Karkalousos, Ivana Išgum, Henk A. Marquering, Matthan W. A. Caan
We benchmark 25 DL models on eight publicly available datasets to present distinct applications of ATOMMIC on accelerated MRI reconstruction, image segmentation, quantitative parameter map estimation, and joint accelerated MRI reconstruction and image segmentation utilizing MTL.
no code implementations • 23 Jan 2024 • Jon André Ottesen, Tryggve Storas, Svein Are Sirirud Vatnehol, Grethe Løvland, Einar O. Vik-Mo, Till Schellhorn, Karoline Skogen, Christopher Larsson, Atle Bjørnerud, Inge Rasmus Groote-Eindbaas, Matthan W. A. Caan
Results: The DL reconstruction was strongly favored or favored over the CS reconstruction for 33/40, 39/40, and 8/40 of cases for reader 1, 2, and 3, respectively.
no code implementations • 5 Jul 2022 • Jon Andre Ottesen, Matthan W. A. Caan, Inge Rasmus Groote, Atle Bjørnerud
In an ablation study, the individual architectural modifications all contributed to this improvement, by reducing the SSIM and NMSE with approximately 3% and 5% for four-fold acceleration, respectively.
1 code implementation • 14 Dec 2020 • Dimitrios Karkalousos, Kai Lønning, Hanneke E. Hulst, Serge O. Dumoulin, Jan-Jakob Sonke, Frans M. Vos, Matthan W. A. Caan
The IndRNN is an efficient recurrent unit, reducing inference time by 68\% compared to CS, whereas maintaining performance.