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

被引：19

作者：

Oshima, Sonoko ^{[1
]}

Fushimi, Yasutaka ^{[1
]}

Miyake, Kanae Kawai ^{[2
]}

Nakajima, Satoshi ^{[1
]}

Sakata, Akihiko ^{[1
]}

Okuchi, Sachi ^{[1
]}

Hinoda, Takuya ^{[1
]}

Otani, Sayo ^{[1
]}

Numamoto, Hitomi ^{[2
]}

Fujimoto, Koji ^{[3
]}

Shima, Atsushi ^{[4
]}

Nambu, Masahito ^{[5
]}

Sawamoto, Nobukatsu ^{[6
]}

Takahashi, Ryosuke ^{[7
]}

Ueno, Kentaro ^{[8
]}

Saga, Tsuneo ^{[2
]}

Nakamoto, Yuji ^{[1
]}

机构：

[1] Kyoto Univ, Grad Sch Med, Dept Diagnost Imaging & Nucl Med, 54 Shogoin Kawahara Cho,Sakyo Ku, Kyoto 6068507, Japan

[2] Kyoto Univ, Grad Sch Med, Dept Adv Med Imaging Res, 54 Shogoin Kawahara Cho,Sakyo Ku, Kyoto 6068507, Japan

[3] Kyoto Univ, Grad Sch Med, Dept Real World Data Res & Dev, 54 Shogoin Kawahara Cho,Sakyo Ku, Kyoto 6068507, Japan

[4] Kyoto Univ, Human Brain Res Ctr, Grad Sch Med, Dept Regenerat Syst Neurosci, 54 Shogoin Kawahara Cho,Sakyo Ku, Kyoto 6068507, Japan

[5] Canon Med Syst Corp, MRI Syst Div, 1385 Shimoishigami, Otawara, Tochigi 3240036, Japan

[6] Kyoto Univ, Grad Sch Med, Dept Human Hlth Sci, 53 Shogoin Kawahara Cho,Sakyo Ku, Kyoto 6068507, Japan

[7] Kyoto Univ, Grad Sch Med, Dept Neurol, 54 Shogoin Kawahara-Cho,Sakyo Ku, Kyoto 6068507, Japan

[8] Kyoto Univ, Grad Sch Med, Dept Biomed Stat & Bioinformat, 54 Shogoin Kawahara Cho,Sakyo Ku, Kyoto 6068507, Japan

来源：

JAPANESE JOURNAL OF RADIOLOGY | 2023年 / 41卷 / 11期

关键词：

Deep learning; Denoising; Neuromelanin; Magnetic resonance imaging; Parkinson's disease; SUBSTANTIA-NIGRA; PARKINSONS-DISEASE; LOCUS-COERULEUS; SYSTEM;

D O I：

10.1007/s11604-023-01452-9

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

PurposeNeuromelanin-sensitive MRI (NM-MRI) has proven useful for diagnosing Parkinson's disease (PD) by showing reduced signals in the substantia nigra (SN) and locus coeruleus (LC), but requires a long scan time. The aim of this study was to assess the image quality and diagnostic performance of NM-MRI with a shortened scan time using a denoising approach with deep learning-based reconstruction (dDLR).Materials and methodsWe enrolled 22 healthy volunteers, 22 non-PD patients and 22 patients with PD who underwent NM-MRI, and performed manual ROI-based analysis. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in ten healthy volunteers were compared among images with a number of excitations (NEX) of 1 (NEX1), NEX1 images with dDLR (NEX1 + dDLR) and 5-NEX images (NEX5). Acquisition times for NEX1 and NEX5 were 3 min 12 s and 15 min 58 s, respectively. Diagnostic performances using the contrast ratio (CR) of the SN (CR_SN) and LC (CR_LC) and those by visual assessment for differentiating PD from non-PD were also compared between NEX1 and NEX1 + dDLR.ResultsImage quality analyses revealed that SNRs and CNRs of the SN and LC in NEX1 + dDLR were significantly higher than in NEX1, and comparable to those in NEX5. In diagnostic performance analysis, areas under the receiver operating characteristic curve (AUC) using CR_SN and CR_LC of NEX1 + dDLR were 0.87 and 0.75, respectively, which had no significant difference with those of NEX1. Visual assessment showed improvement of diagnostic performance by applying dDLR.ConclusionImage 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.

引用

页码：1216 / 1225

页数：10

共 38 条

[31] Contrast Mechanisms Associated With Neuromelanin-MRI [J].