MR electrical properties mapping using vision transformers and canny edge detectors

• Published in: Magnetic resonance in medicine Vol. 93; no. 3; pp. 1117 - 1131
• Main Authors: Giannakopoulos, Ilias I., Carluccio, Giuseppe, Keerthivasan, Mahesh B., Koerzdoerfer, Gregor, Lakshmanan, Karthik, De Moura, Hector L., Cruz Serrallés, José E., Lattanzi, Riccardo
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.03.2025
• Subjects: Algorithms; Brain - diagnostic imaging; Coils; Datasets; Electric Conductivity; Electrical properties; Head - diagnostic imaging; Humans; Image Processing, Computer-Assisted - methods; Imaging, Three-Dimensional; Lesions; Magnetic properties; Magnetic resonance; Magnetic Resonance Imaging - instrumentation; Neural networks; Neural Networks, Computer; Permittivity; Phantoms, Imaging; Reconstruction; vision transformers; transfer learning; electrical properties mapping; electromagnetic simulations
• ISSN: 0740-3194; 1522-2594; 1522-2594
• DOI: 10.1002/mrm.30338

We developed a 3D vision transformer-based neural network to reconstruct electrical properties (EP) from magnetic resonance measurements. Our network uses the magnitude of the transmit magnetic field of a birdcage coil, the associated transceive phase, and a Canny edge mask that identifies the object boundaries as inputs to compute the EP maps. We trained our network on a dataset of 10 000 synthetic tissue-mimicking phantoms and fine-tuned it on a dataset of 11 000 realistic head models. We assessed performance in-distribution simulated data and out-of-distribution head models, with and without synthetic lesions. We further evaluated our network in experiments for an inhomogeneous phantom and a volunteer. The conductivity and permittivity maps had an average peak normalized absolute error (PNAE) of 1.3% and 1.7% for the synthetic phantoms, respectively. For the realistic heads, the average PNAE for the conductivity and permittivity was 1.8% and 2.7%, respectively. The location of synthetic lesions was accurately identified, with reconstructed conductivity and permittivity values within 15% and 25% of the ground-truth, respectively. The conductivity and permittivity for the phantom experiment yielded 2.7% and 2.1% average PNAEs with respect to probe-measured values, respectively. The in vivo EP reconstruction truthfully preserved the subject's anatomy with average values over the entire head similar to the expected literature values. We introduced a new learning-based approach for reconstructing EP from MR measurements obtained with a birdcage coil, marking an important step towards the development of clinically-usable in vivo EP reconstruction protocols.