Denoising approach with deep learning-based reconstruction for neuromelanin-sensitive MRI: image quality and diagnostic performance.

Sonoko OshimaYasutaka FushimiKanae Kawai MiyakeSatoshi NakajimaAkihiko SakataSachi OkuchiTakuya HinodaSayo OtaniHitomi NumamotoKoji FujimotoAtsushi ShimaMasahito NambuNobukatsu SawamotoRyosuke TakahashiKentaro UenoTsuneo SagaYuji Nakamoto

Published in: Japanese journal of radiology (2023)

Image quality for NEX1 + dDLR was comparable to that of NEX5. dDLR has the potential to reduce scan time of NM-MRI without degrading image quality. Both 1-NEX NM-MRI with and without dDLR showed high AUCs for diagnosing PD by CR. The results of visual assessment suggest advantages of dDLR. Further tuning of dDLR would be expected to provide clinical merits in diagnosing PD.

Keyphrases

image quality
computed tomography
contrast enhanced
magnetic resonance imaging
dual energy
deep learning
diffusion weighted imaging
photodynamic therapy
magnetic resonance
convolutional neural network
machine learning
human health
risk assessment
artificial intelligence