Dynamic recurrent inference machines for accelerated MRI-guided radiotherapy of the liver.

Autor: Lønning K; Netherlands Cancer Institute, Department of Radiotherapy, Plesmanlaan 121, 1066 CX Amsterdam, The Netherlands; Spinoza Centre for Neuroimaging, Meibergdreef 75, 1105 BK Amsterdam, The Netherlands., Caan MWA; Amsterdam UMC location University of Amsterdam, Department of Biomedical Engineering and Physics, Meibergdreef 9, 1105 AZ Amsterdam, The Netherlands., Nowee ME; Netherlands Cancer Institute, Department of Radiotherapy, Plesmanlaan 121, 1066 CX Amsterdam, The Netherlands., Sonke JJ; Netherlands Cancer Institute, Department of Radiotherapy, Plesmanlaan 121, 1066 CX Amsterdam, The Netherlands. Electronic address: j.sonke@nki.nl.
Jazyk: angličtina
Zdroj: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society [Comput Med Imaging Graph] 2024 Apr; Vol. 113, pp. 102348. Date of Electronic Publication: 2024 Feb 08.
DOI: 10.1016/j.compmedimag.2024.102348
Abstrakt: Recurrent inference machines (RIM), a deep learning model that learns an iterative scheme for reconstructing sparsely sampled MRI, has been shown able to perform well on accelerated 2D and 3D MRI scans, learn from small datasets and generalize well to unseen types of data. Here we propose the dynamic recurrent inference machine (DRIM) for reconstructing sparsely sampled 4D MRI by exploiting correlations between respiratory states. The DRIM was applied to a 4D protocol for MR-guided radiotherapy of liver lesions based on repetitive interleaved coronal 2D multi-slice T 2 -weighted acquisitions. We demonstrate with an ablation study that the DRIM outperforms the RIM, increasing the SSIM score from about 0.89 to 0.95. The DRIM allowed for an approximately 2.7 times faster scan time than the current clinical protocol with only a slight loss in image sharpness. Correlations between slice locations can also be used, but were found to be of less importance, as were a majority of tested variations in network architecture, as long as the respiratory states are processed by the network. Through cross-validation, the DRIM is also shown to be robust in terms of training data. We further demonstrate a good performance across a large range of subsampling factors, and conclude through an evaluation by a radiation oncologist that reconstructed images of the liver contour and inner structures are of a clinically acceptable standard at acceleration factors 10x and 8x, respectively. Finally, we show that binning the data with respect to respiratory states prior to reconstruction comes at a slight cost to reconstruction quality, but at greater speed of the overall protocol.
Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Jan-Jakob Sonke reports a relationship with Elekta AB that includes: funding grants. Jan-Jakob Sonke reports a relationship with Dutch Cancer Society that includes: funding grants. Jan-Jakob Sonke reports a relationship with Netherlands Enterprise Agency that includes: funding grants. Matthan W.A. Caan reports a relationship with Nicolab International Ltd. that includes: equity or stocks. Our department is a member of the Elekta ML Linac consortium. Our department received royalties for imaged radiotherapy software from Elekta AB.
(Copyright © 2024 Elsevier Ltd. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: