Search

Your search keyword '"Yukunori Korogi"' showing total 4 results
Start Over Author "Yukunori Korogi" Publication Year Range Last 3 years
4 results on '"Yukunori Korogi"'

1. Optic radiation atrophy in Lewy body disease with visual hallucination on phase difference enhanced magnetic resonance images

Author

Mari Miyata, Shingo Kakeda, Tetsuya Yoneda, Satoru Ide, Kazumasa Okada, Hiroaki Adachi, and Yukunori Korogi

Subjects
Medicine, Science
Abstract

Abstract Visual hallucinations (VH) occur commonly in Lewy body disease (LBD), including Parkinson’s disease (PD), PD with dementia, and dementia with Lewy bodies. We aimed to use phase difference enhanced imaging (PADRE) to assess structural abnormalities of optic radiation (OR) in patients with Lewy body disease (LBD) concomitant with VH. Firstly, two radiologists reviewed the OR appearances in healthy subjects (HS) on PADRE. Next, based on the OR abnormalities, two reviewers assessed the PADRE images from 18 HS and 38 and 110 patients with LBD, with and without VH, respectively, in a blinded manner. Finally, all patients with LBD without VH were eventually followed up for at least 5 years after magnetic resonance imaging to determine the appearance of VH. The radiologists identified three layers, namely external sagittal stratum, internal sagittal stratum, and tapetum, in OR on the PADRE in HS. Moreover, they were able to consensually define the OR as abnormal when the layers were obscured and the disappearance of the cranial side. The sensitivity/specificity of abnormal OR for each case was 68%/81% (LBD with VH vs. LBD without VH). Furthermore, VH appeared in 12 of the 21 (57%) patients with LBD and abnormal OR during the follow-up period. However, no patients without abnormal OR reported VH. Patients with LBD and VH demonstrated the abnormal OR. This, in turn, might be a useful marker to distinguish the patients with VH from those without VH and HS. Moreover, abnormal OR on PADRE may precede the appearance of VH in LBD.

Published
2022
Full Text
View/download PDF

2. The effect of CT texture-based analysis using machine learning approaches on radiologists' performance in differentiating focal-type autoimmune pancreatitis and pancreatic duct carcinoma

Author

Kenta Anai, Yoshiko Hayashida, Issei Ueda, Eri Hozuki, Yuuta Yoshimatsu, Jun Tsukamoto, Toshihiko Hamamura, Norihiro Onari, Takatoshi Aoki, and Yukunori Korogi

Subjects
Diagnosis, Differential, Pancreatic Neoplasms, Machine Learning, Autoimmune Pancreatitis, Radiologists, Pancreatic Ducts, Humans, Radiology, Nuclear Medicine and imaging, Tomography, X-Ray Computed, Retrospective Studies, Carcinoma, Pancreatic Ductal
Abstract

Purpose To develop a support vector machine (SVM) classifier using CT texture-based analysis in differentiating focal-type autoimmune pancreatitis (AIP) and pancreatic duct carcinoma (PD), and to assess the radiologists’ diagnostic performance with or without SVM. Materials and methods This retrospective study included 50 patients (20 patients with focal-type AIP and 30 patients with PD) who underwent dynamic contrast-enhanced CT. Sixty-two CT texture-based features were extracted from 2D images of the arterial and portal phase CTs. We conducted data compression and feature selections using principal component analysis (PCA) and produced the SVM classifier. Four readers participated in this observer performance study and the statistical significance of differences with and without the SVM was assessed by receiver operating characteristic (ROC) analysis. Results The SVM performance indicated a high performance in differentiating focal-type AIP and PD (AUC = 0.920). The AUC for all 4 readers increased significantly from 0.827 to 0.911 when using the SVM outputs (p = 0.010). The AUC for inexperienced readers increased significantly from 0.781 to 0.905 when using the SVM outputs (p = 0.310). The AUC for experienced readers increased from 0.875 to 0.912 when using the SVM outputs, however, there was no significant difference (p = 0.018). Conclusion The use of SVM classifier using CT texture-based features improved the diagnostic performance for differentiating focal-type AIP and PD on CT.

Published
2022

3. [Accuracy of VSRAD Analysis Using Scout Images: Comparison with Conventional 3D-T

Author

Tatsuya, Katayama, Keita, Watanabe, Hidekuni, Narimatsu, Shingo, Kakeda, and Yukunori, Korogi

Abstract

The voxel-based specific regional analysis system for Alzheimer's disease (VSRAD), which targets volume loss in medial temporal lobe, was developed as a sensitive diagnostic tool to detect early stages of Alzheimer's disease. However, conventional three-dimensional T

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results