Norio Hayashi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Norio Hayashi has a total of 120 co-authors. Here are the top co-authors by number of shared publications:
Akio Ogura
Department of Radiological Technology, Gunma Prefectural College of Health Sciences, Maebashi, Gunma, Japan
4 shared publicationsNobukazu Yuki
Osaka, Japan
4 shared publicationsTakenobu Kamada
Osaka, Japan
4 shared publicationsToshihiro Ogura
School of Radiological Technology, Gunma Prefectural College of Health Sciences, Maebashi, Japan
4 shared publicationsAkinori Kasahara
Department of Gastroenterology and Hepatology, Osaka University Graduate School of Medicine, Suita, Japan
3 shared publicationsHideyuki Fusamoto
Osaka, Japan
3 shared publications
Latest Publications
- Open Access
- 10 September 2026
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 19 (4) , 1816-1823
Evaluation-design effects and reference-CT-defined HU-class errors in brain MRI-to-CT synthesis on SynthRAD2023: a technical note
To quantify how evaluation design affects brain MRI-to-CT synthesis performance, we analyzed 180 MRI/CT pairs from three centers in the SynthRAD2023 Task 1 dataset. A lightweight 2D U-Net was trained with a common validation-based stopping rule under slice-random, patient-random, center-stratified size-matched patient-random, and three center-held-out designs. Comparisons were descriptive. The primary outcome was whole-mask mean absolute error (MAE), supplemented by MAE within reference-CT-defined Hounsfield unit (HU) classes. MAE (mean ± standard deviation) was 94.4 ± 3.0, 100.8 ± 1.3, and 105.2 ± 2.8 HU for the random designs and 187.4 ± 6.0, 160.6 ± 7.1, and 137.4 ± 5.1 HU for centers A, B, and C held out. Slice-random testing yielded lower MAE than patient-random testing. Center-held-out testing yielded higher MAE than the center-stratified comparator, although institutional and acquisition-domain effects could not be separated. Bone errors were high across designs; adipose-range and air errors were elevated in specific center-held-out tests.
- 10 September 2026
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 19 (4) , 1816-1823
Open AccessEvaluation-design effects and reference-CT-defined HU-class errors in brain MRI-to-CT synthesis on SynthRAD2023: a technical note
To quantify how evaluation design affects brain MRI-to-CT synthesis performance, we analyzed 180 MRI/CT pairs from three centers in the SynthRAD2023 Task 1 dataset. A lightweight 2D U-Net was trained with a common validation-based stopping rule under slice-random, patient-random, center-stratified size-matched patient-random, and three center-held-out designs. Comparisons were descriptive. The primary outcome was whole-mask mean absolute error (MAE), supplemented by MAE within reference-CT-defined Hounsfield unit (HU) classes. MAE (mean ± standard deviation) was 94.4 ± 3.0, 100.8 ± 1.3, and 105.2 ± 2.8 HU for the random designs and 187.4 ± 6.0, 160.6 ± 7.1, and 137.4 ± 5.1 HU for centers A, B, and C held out. Slice-random testing yielded lower MAE than patient-random testing. Center-held-out testing yielded higher MAE than the center-stratified comparator, although institutional and acquisition-domain effects could not be separated. Bone errors were high across designs; adipose-range and air errors were elevated in specific center-held-out tests.
- 17 May 2024
- Published by Elsevier in Journal of Stroke and Cerebrovascular Diseases
- Vol. 33 (8) , 107772
Comparison of qualitative and fully automated quantitative tools for classifying severity of white matter hyperintensity
- 17 May 2024
- Published by Elsevier in Journal of Stroke and Cerebrovascular Diseases
- Vol. 33 (8) , 107772
Comparison of qualitative and fully automated quantitative tools for classifying severity of white matter hyperintensity
- 28 December 2023
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 17 (1) , 186-194
Evaluation of deep learning reconstruction on diffusion-weighted imaging quality and apparent diffusion coefficient using an ice-water phantom
This study assessed the influence of deep learning reconstruction (DLR) on the quality of diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) using an ice-water phantom. An ice-water phantom with known diffusion properties (true ADC = 1.1 × 10–3 mm2/s at 0 °C) was imaged at various b-values (0, 1000, 2000, and 4000 s/mm2) using a 3 T magnetic resonance imaging scanner with slice thicknesses of 1.5 and 3.0 mm. All DWIs were reconstructed with or without DLR. ADC maps were generated using combinations of b-values 0 and 1000, 0 and 2000, and 0 and 4000 s/mm2. Based on the quantitative imaging biomarker alliance profile, the signal-to-noise ratio (SNRs) in DWIs was calculated, and the accuracy, precision, and within-subject parameter variance (wCV) of the ADCs were evaluated. DLR improved the SNR in DWIs with b-values ranging from 0 to 2000s/mm2; however, its effectiveness was diminished at 4000 s/mm2. There was no noticeable difference in the ADCs of images generated with or without implementing DLR. For a slice thickness of 1.5 mm and combined b-values of 0 and 4000 s/mm2, the ADC values were 0.97 × 10–3and 0.98 × 10–3mm2/s with and without DLR, respectively, both being lower than the true ADC value. Furthermore, DLR enhanced the precision and wCV of the ADC measurements. DLR can enhance the SNR, repeatability, and precision of ADC measurements; however, it does not improve their accuracies.
- 28 December 2023
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 17 (1) , 186-194
Evaluation of deep learning reconstruction on diffusion-weighted imaging quality and apparent diffusion coefficient using an ice-water phantom
This study assessed the influence of deep learning reconstruction (DLR) on the quality of diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) using an ice-water phantom. An ice-water phantom with known diffusion properties (true ADC = 1.1 × 10–3 mm2/s at 0 °C) was imaged at various b-values (0, 1000, 2000, and 4000 s/mm2) using a 3 T magnetic resonance imaging scanner with slice thicknesses of 1.5 and 3.0 mm. All DWIs were reconstructed with or without DLR. ADC maps were generated using combinations of b-values 0 and 1000, 0 and 2000, and 0 and 4000 s/mm2. Based on the quantitative imaging biomarker alliance profile, the signal-to-noise ratio (SNRs) in DWIs was calculated, and the accuracy, precision, and within-subject parameter variance (wCV) of the ADCs were evaluated. DLR improved the SNR in DWIs with b-values ranging from 0 to 2000s/mm2; however, its effectiveness was diminished at 4000 s/mm2. There was no noticeable difference in the ADCs of images generated with or without implementing DLR. For a slice thickness of 1.5 mm and combined b-values of 0 and 4000 s/mm2, the ADC values were 0.97 × 10–3and 0.98 × 10–3mm2/s with and without DLR, respectively, both being lower than the true ADC value. Furthermore, DLR enhanced the precision and wCV of the ADC measurements. DLR can enhance the SNR, repeatability, and precision of ADC measurements; however, it does not improve their accuracies.
- 10 May 2023
- Published by Springer Nature in Applied Magnetic Resonance
- Vol. 54 (7) , 687-697
Suitability of Latebra as a Skin Marker for Magnetic Resonance Imaging
- 10 May 2023
- Published by Springer Nature in Applied Magnetic Resonance
- Vol. 54 (7) , 687-697
Suitability of Latebra as a Skin Marker for Magnetic Resonance Imaging
- Open Access
- 1 May 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-8
Quality control system for mammographic breast positioning using deep learning
This study proposes a deep convolutional neural network (DCNN) classification for the quality control and validation of breast positioning criteria in mammography. A total of 1631 mediolateral oblique mammographic views were collected from an open database. We designed two main steps for mammographic verification: automated detection of the positioning part and classification of three scales that determine the positioning quality using DCNNs. After acquiring labeled mammograms with three scales visually evaluated based on guidelines, the first step was automatically detecting the region of interest of the subject part by image processing. The next step was classifying mammographic positioning accuracy into three scales using four representative DCNNs. The experimental results showed that the DCNN model achieved the best positioning classification accuracy of 0.7836 using VGG16 in the inframammary fold and a classification accuracy of 0.7278 using Xception in the nipple profile. Furthermore, using the softmax function, the breast positioning criteria could be evaluated quantitatively by presenting the predicted value, which is the probability of determining positioning accuracy. The proposed method can be quantitatively evaluated without the need for an individual qualitative evaluation and has the potential to improve the quality control and validation of breast positioning criteria in mammography.
- 1 May 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-8
Open AccessQuality control system for mammographic breast positioning using deep learning
This study proposes a deep convolutional neural network (DCNN) classification for the quality control and validation of breast positioning criteria in mammography. A total of 1631 mediolateral oblique mammographic views were collected from an open database. We designed two main steps for mammographic verification: automated detection of the positioning part and classification of three scales that determine the positioning quality using DCNNs. After acquiring labeled mammograms with three scales visually evaluated based on guidelines, the first step was automatically detecting the region of interest of the subject part by image processing. The next step was classifying mammographic positioning accuracy into three scales using four representative DCNNs. The experimental results showed that the DCNN model achieved the best positioning classification accuracy of 0.7836 using VGG16 in the inframammary fold and a classification accuracy of 0.7278 using Xception in the nipple profile. Furthermore, using the softmax function, the breast positioning criteria could be evaluated quantitatively by presenting the predicted value, which is the probability of determining positioning accuracy. The proposed method can be quantitatively evaluated without the need for an individual qualitative evaluation and has the potential to improve the quality control and validation of breast positioning criteria in mammography.
- 1 May 2020
- Published by SAGE Publications in Technology and Health Care
- Vol. 28 (3) , 241-248
Development of a quantitative statistical analysis system for double inversion recovery (DIR) MRI: A preliminary clinical study
BACKGROUND: Gray matter (GM) imaging is important in the investigation of many neurological diseases, including schizophrenia, multiple sclerosis, stroke, Alzheimer’s disease, tuberous sclerosis, and epilepsy, which are all associated with changes in cortical GM. OBJECTIVE: The aim of this study was to develop a quantitative statistical analysis system for double inversion recovery (DIR) MRI and to evaluate the new system using preliminary clinical data. METHODS: The study population comprised of 10 healthy volunteers and six patients with or without brain degeneration. A quantitative statistical analysis system for DIR images was developed using the following steps: 1) brain spatial normalization, 2) mean and standard deviation (SD) map creation, and 3) Z-score map creation. To evaluate the new voxel-based morphometry system, Z-scores of lesions in patients with brain degeneration were measured and then compared with Z-scores of normal regions. RESULTS: All DIR images were adequately spatially normalized to Montreal Neurological Institute MNI coordinate. Lesions in each patient were indicated by high Z-score values on a Z-score map, which were significantly higher than Z-scores of normal regions ( p < 0.05). CONCLUSIONS: In this study, we developed a quantitative statistical analysis system for DIR MRI. Using our system, clinicians might accurately diagnose early brain degeneration.
- 1 May 2020
- Published by SAGE Publications in Technology and Health Care
- Vol. 28 (3) , 241-248
Development of a quantitative statistical analysis system for double inversion recovery (DIR) MRI: A preliminary clinical study
BACKGROUND: Gray matter (GM) imaging is important in the investigation of many neurological diseases, including schizophrenia, multiple sclerosis, stroke, Alzheimer’s disease, tuberous sclerosis, and epilepsy, which are all associated with changes in cortical GM. OBJECTIVE: The aim of this study was to develop a quantitative statistical analysis system for double inversion recovery (DIR) MRI and to evaluate the new system using preliminary clinical data. METHODS: The study population comprised of 10 healthy volunteers and six patients with or without brain degeneration. A quantitative statistical analysis system for DIR images was developed using the following steps: 1) brain spatial normalization, 2) mean and standard deviation (SD) map creation, and 3) Z-score map creation. To evaluate the new voxel-based morphometry system, Z-scores of lesions in patients with brain degeneration were measured and then compared with Z-scores of normal regions. RESULTS: All DIR images were adequately spatially normalized to Montreal Neurological Institute MNI coordinate. Lesions in each patient were indicated by high Z-score values on a Z-score map, which were significantly higher than Z-scores of normal regions ( p < 0.05). CONCLUSIONS: In this study, we developed a quantitative statistical analysis system for DIR MRI. Using our system, clinicians might accurately diagnose early brain degeneration.
- 20 March 2020
- Published by SAGE Publications in Technology and Health Care
- Vol. 28 (2) , 113-120
Evaluating medical images using deep convolutional neural networks: A simulated CT phantom image study
BACKGROUND: Applied research on artificial intelligence, mainly in deep learning, is widely performed. If medical images can be evaluated using artificial intelligence, this could substantially improve examination efficiency. OBJECTIVE: We investigat
- 20 March 2020
- Published by SAGE Publications in Technology and Health Care
- Vol. 28 (2) , 113-120
Evaluating medical images using deep convolutional neural networks: A simulated CT phantom image study
BACKGROUND: Applied research on artificial intelligence, mainly in deep learning, is widely performed. If medical images can be evaluated using artificial intelligence, this could substantially improve examination efficiency. OBJECTIVE: We investigat
- 6 May 2017
- Published by SAGE Publications in Journal of X-Ray Science and Technology
- Vol. 25 (5) , 803-812
Optimization method of MRI scan parameters of a double inversion recovery sequence using a T1 map and a developed analysis algorithm
BACKGROUND: Optimizing scan parameters for double inversion recovery (DIR) sequences remains difficult. OBJECTIVE: To evaluate a new method for optimizing DIR sequence scan parameters using T1 mapping and a newly developed analysis algorithm. METHODS: Twelve healthy volunteers underwent T1 mapping and DIR magnetic resonance imaging. The following steps were used for image optimization including: 1) measurement of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) T1 values to create a T1 map; 2) calculation of optimized scan parameters by using a developed analysis algorithm; 3) performance assessment of DIR magnetic resonance imaging by using the calculated optimized imaging parameters. Additionally, we used scan parameters from previous studies to obtain DIR images in order to evaluate our new method. The contrast between GM and suppressed tissues was compared between these images and those obtained using the optimized parameters. RESULTS: Using our optimization method, WM and CSF regions were suppressed uniformly for all scan conditions. The contrast was significantly higher in images obtained using this optimization method compared to those obtained using previously published parameters ( p < 0.01). CONCLUSIONS: It is possible to obtain superior DIR images by using an optimization method that involves T1 mapping and a newly developed analysis algorithm.
- 6 May 2017
- Published by SAGE Publications in Journal of X-Ray Science and Technology
- Vol. 25 (5) , 803-812
Optimization method of MRI scan parameters of a double inversion recovery sequence using a T1 map and a developed analysis algorithm
BACKGROUND: Optimizing scan parameters for double inversion recovery (DIR) sequences remains difficult. OBJECTIVE: To evaluate a new method for optimizing DIR sequence scan parameters using T1 mapping and a newly developed analysis algorithm. METHODS: Twelve healthy volunteers underwent T1 mapping and DIR magnetic resonance imaging. The following steps were used for image optimization including: 1) measurement of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) T1 values to create a T1 map; 2) calculation of optimized scan parameters by using a developed analysis algorithm; 3) performance assessment of DIR magnetic resonance imaging by using the calculated optimized imaging parameters. Additionally, we used scan parameters from previous studies to obtain DIR images in order to evaluate our new method. The contrast between GM and suppressed tissues was compared between these images and those obtained using the optimized parameters. RESULTS: Using our optimization method, WM and CSF regions were suppressed uniformly for all scan conditions. The contrast was significantly higher in images obtained using this optimization method compared to those obtained using previously published parameters ( p < 0.01). CONCLUSIONS: It is possible to obtain superior DIR images by using an optimization method that involves T1 mapping and a newly developed analysis algorithm.
- 27 April 2017
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 10 (3) , 294-300
Magnetization and demagnetization of magnetic dental attachments in a 3-T MRI system
The purpose of this study was to evaluate the magnetization and demagnetization of magnetic dental attachments in a 3.0-T magnetic resonance imaging (MRI) scanner. A high-field-strength (3.0 T) MRI scanner (Achieva 3.0 T, Philips, Amsterdam, Netherlands) was used. Magnetic flux leakage was measured using a gaussmeter. To evaluate the magnetization and demagnetization of the magnetic assemblies and keepers caused by the moving in and out of the MRI scanner, the magnetic force of the attachments was measured before and after the table was moved in and out. Two settings were used wherein the magnetic assemblies and keepers were positioned on the table at angles of 0° or 90° with respect to the magnetic flux of the static magnetic field. The movement of the table was repeated 15 times. In addition, the retentive force of the magnetic dental attachments was measured after magnetic field exposure. The magnetic force of the magnetic attachments positioned at 0° decreased significantly after moving in and out of the MRI scanner (p < 0.05). In contrast, the magnetic force of the magnetic attachments positioned at 90° was stable after the movement of the table. The magnetic force of the keepers placed at both 0° and 90° was slightly increased after the movement of the table. At 0°, the retentive force of the magnet-keeper combinations decreased when the magnetic assembly was exposed to the strong magnetic flux of the MRI scanner. Therefore, the removal of all removable magnetic dentures is recommended before an MRI examination.
- 27 April 2017
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 10 (3) , 294-300
Magnetization and demagnetization of magnetic dental attachments in a 3-T MRI system
The purpose of this study was to evaluate the magnetization and demagnetization of magnetic dental attachments in a 3.0-T magnetic resonance imaging (MRI) scanner. A high-field-strength (3.0 T) MRI scanner (Achieva 3.0 T, Philips, Amsterdam, Netherlands) was used. Magnetic flux leakage was measured using a gaussmeter. To evaluate the magnetization and demagnetization of the magnetic assemblies and keepers caused by the moving in and out of the MRI scanner, the magnetic force of the attachments was measured before and after the table was moved in and out. Two settings were used wherein the magnetic assemblies and keepers were positioned on the table at angles of 0° or 90° with respect to the magnetic flux of the static magnetic field. The movement of the table was repeated 15 times. In addition, the retentive force of the magnetic dental attachments was measured after magnetic field exposure. The magnetic force of the magnetic attachments positioned at 0° decreased significantly after moving in and out of the MRI scanner (p < 0.05). In contrast, the magnetic force of the magnetic attachments positioned at 90° was stable after the movement of the table. The magnetic force of the keepers placed at both 0° and 90° was slightly increased after the movement of the table. At 0°, the retentive force of the magnet-keeper combinations decreased when the magnetic assembly was exposed to the strong magnetic flux of the MRI scanner. Therefore, the removal of all removable magnetic dentures is recommended before an MRI examination.
- 9 April 2017
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 10 (3) , 364-375
Double inversion recovery imaging of the brain: deriving the most relevant sequence through real images
We propose a practical method for setting the optimal inversion times (TI) for double inversion recovery (DIR) sequences. Our method used the measurement of signal intensity (SI) from real images to set the optimal TI for white-matter (WM) and gray-matter (GM)-attenuated inversion recovery (WAIR and GAIR, respectively) images. 3D-DIR images of healthy volunteers were obtained on 1.5- and 3.0-T magnetic resonance (MR) scanners and the SIs of GM, WM, and cerebrospinal fluid (CSF) were evaluated on real images. We found TI2s at which the SI of WM or GM was null. Then, we found TI1+2 (=TI1 + TI2) at which the SI of CSF was null. We defined the two TIs as optimal TIs. We assessed the utility of these TIs with additional volunteers and patients, and similar images were obtained with the determined TIs. Optimal TIs for DIR images could be efficiently determined using this method.
- 9 April 2017
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 10 (3) , 364-375
Double inversion recovery imaging of the brain: deriving the most relevant sequence through real images
We propose a practical method for setting the optimal inversion times (TI) for double inversion recovery (DIR) sequences. Our method used the measurement of signal intensity (SI) from real images to set the optimal TI for white-matter (WM) and gray-matter (GM)-attenuated inversion recovery (WAIR and GAIR, respectively) images. 3D-DIR images of healthy volunteers were obtained on 1.5- and 3.0-T magnetic resonance (MR) scanners and the SIs of GM, WM, and cerebrospinal fluid (CSF) were evaluated on real images. We found TI2s at which the SI of WM or GM was null. Then, we found TI1+2 (=TI1 + TI2) at which the SI of CSF was null. We defined the two TIs as optimal TIs. We assessed the utility of these TIs with additional volunteers and patients, and similar images were obtained with the determined TIs. Optimal TIs for DIR images could be efficiently determined using this method.