The University of Tokyo · Medicine
Professor Ryusuke Irie's research lab specializes in advanced neuroimaging and quantitative MRI techniques, focusing on the development and application of innovative magnetic resonance imaging methods for neurological disorders. The lab pioneers deep learning-based approaches to enhance image reconstruction and diagnosis, particularly in intracranial aneurysms, neurodegenerative diseases like Alzheimer’s and iNPH, and cerebrovascular interventions. By integrating quantitative synthetic MRI, silent MRA, and diffusion kurtosis imaging, the lab aims to improve diagnostic accuracy, reproducibility, and patient follow-up with minimal additional scan time.
Figures are computed from collected data and may differ slightly.
Silent MRA was able to visualize flow in an intracranial stent more effectively than TOF MRA. Silent MRA might be useful for follow-up imaging after stent-assisted coil embolization, though these study results may be only preliminary due to some limitations.
Our study showed changes according to age in tissue characteristic values and brain volumes using quantitative synthetic MRI. The reference values for age demonstrated in this study may be useful to discriminate brain disorders from healthy brains.
Magnetic resonance angiography generated by deep learning from 3D synthetic MRI data visualized major intracranial arteries as effectively as TOF-MRA, with inherently aligned quantitative maps and multiple contrast-weighted images. Our proposed algorithm may be useful as a screening tool for intracranial aneurysms without requiring additional scanning time.
Residual extraction approach in a deep learning method achieved a high accuracy for the differential diagnosis of iNPH, AD, and healthy controls trained with a small number of cases.
Objective The aim of this study was to evaluate the reproducibility of computed tomography (CT)–derived fractional flow reserve (FFR) determined on site by inexperienced observers using a postprocessing software based on structural and fluid analysis. Methods Using 21 coronary vessels in 7 patients who underwent 320-row coronary CT angiography and catheter-FFR, 2 independent inexperienced observers (A: a student radiation technologist; B: a nonmedical staff) determined the CT-FFR using a postpro
DKI accurately reflected neurite density in the area with crossing fibers, potentially allowing evaluation of complex microstructures.
This pilot study tests the feasibility of rapid carotid MR angiography using the liver acquisition with volume acceleration-flex technique (LAVA MRA). Seven healthy volunteers and 21 consecutive patients suspected of carotid stenosis underwent LAVA and conventional time-of-flight (cTOF) MRAs. Artery-to-fat and artery-to-muscle signal intensity ratios were manually measured. LAVA MRA exhibited a significantly larger artery-to-fat signal intensity ratio compared with cTOF MRA in all slices (P < 0.
Liver acquisition with volume acceleration-flex (LAVA-Flex) acquires out-of-phase and in-phase echo images and automatically generates water-only and fat-only images from one single acquisition. The scan time of carotid MR angiography (MRA) using LAVA-Flex (LAVA MRA) is about one-fifth that of conventional time-of-flight MRA (cTOF MRA). We aimed to investigate whether LAVA MRA could provide useful information for the diagnosis of carotid plaque by utilizing the ability to acquire multiple sequen
Purpose: The Prostate Imaging Reporting and Data System (PI-RADS) was introduced to standardize prostate cancer diagnosis by MRI. However, the inter-reader agreement by PI-RADS scoring is not always high. The purpose of this study was to validate a deep-learning-based diagnostic algorithm of PI-RADS. Methods: We applied a Siemens Healthineers Prostate Artificial Intelligence (AI) prototype (work in progress) for fully automated prostate lesion detection, classification and reporting. More than 2
Open papers in the app to read, cite, and organize with AI.
