Updated on 2025/04/24

写真a

 
FUKUI Ryouhei
 
Organization
Faculty of Health Sciences Assistant Professor
Position
Assistant Professor
External link

Degree

  • 博士（保健学） ( 2018.9   熊本大学 )

  • 学士（保健学） ( 2008.3   岡山大学 )

Research Interests

  • tomosynthesis

  • x-ray image

  • deep learning

Research Areas

  • Life Science / Radiological sciences  / Radiological Technology

Education

  • Kumamoto University   大学院保健学教育部   博士後期課程

    2015.4 - 2018.9

    　 More details

    Country： Japan

    researchmap

  • Okayama University   医学部   保健学科放射線技術科学専攻

    2004.4 - 2008.3

    　 More details

    Country： Japan

    researchmap

 

Papers

  • Deep learning-based approach for acquisition time reduction in ventilation SPECT in patients after lung transplantation. Reviewed

    Masahiro Nakashima, Ryohei Fukui, Seiichiro Sugimoto, Toshihiro Iguchi

    Radiological physics and technology   18 ( 1 )   47 - 57   2025.3

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    We aimed to evaluate the image quality and diagnostic performance of chronic lung allograft dysfunction (CLAD) with lung ventilation single-photon emission computed tomography (SPECT) images acquired briefly using a convolutional neural network (CNN) in patients after lung transplantation and to explore the feasibility of short acquisition times. We retrospectively identified 93 consecutive lung-transplant recipients who underwent ventilation SPECT/computed tomography (CT). We employed a CNN to distinguish the images acquired in full time from those acquired in a short time. The image quality was evaluated using the structural similarity index (SSIM) loss and normalized mean square error (NMSE). The correlation between functional volume/morphological volume (F/M) ratios of full-time SPECT images and predicted SPECT images was evaluated. Differences in the F/M ratio were evaluated using Bland-Altman plots, and the diagnostic performance was compared using the area under the curve (AUC). The learning curve, obtained using MSE, converged within 100 epochs. The NMSE was significantly lower (P < 0.001) and the SSIM was significantly higher (P < 0.001) for the CNN-predicted SPECT images compared to the short-time SPECT images. The F/M ratio of full-time SPECT images and predicted SPECT images showed a significant correlation (r = 0.955, P < 0.0001). The Bland-Altman plot revealed a bias of -7.90% in the F/M ratio. The AUC values were 0.942 for full-time SPECT images, 0.934 for predicted SPECT images and 0.872 for short-time SPECT images. Our findings suggest that a deep-learning-based approach can significantly curtail the acquisition time of ventilation SPECT, while preserving the image quality and diagnostic accuracy for CLAD.

    DOI： 10.1007/s12194-024-00853-3

    PubMed

    researchmap

  • Accuracy of deep learning-based attenuation correction in 99mTc-GSA SPECT/CT hepatic imaging Reviewed

    M. Miyai, R. Fukui, M. Nakashima, D. Hasegawa, S. Goto

    Radiography   31 ( 1 )   112 - 117   2025.1

    　More details

    Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier BV  

    DOI： 10.1016/j.radi.2024.11.002

    researchmap

  • Investigating the Effects of Reconstruction Conditions on Image Quality and Radiomic Analysis in Photon-counting Computed Tomography. International journal

    Miyu Ohata, Ryohei Fukui, Yusuke Morimitsu, Daichi Kobayashi, Takatsugu Yamauchi, Noriaki Akagi, Mitsugi Honda, Aiko Hayashi, Koshi Hasegawa, Katsuhiro Kida, Sachiko Goto, Takao Hiraki

    Journal of medical physics   50 ( 1 )   100 - 107   2025

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    INTRODUCTION: Photon-counting computed tomography (CT) is equipped with an adaptive iterative reconstruction method called quantum iterative reconstruction (QIR), which allows the intensity to be changed during image reconstruction. It is known that the reconstruction conditions of CT images affect the analysis results when performing radiomic analysis. The aim of this study is to investigate the effect of QIR intensity on image quality and radiomic analysis of renal cell carcinoma (RCC). MATERIALS AND METHODS: The QIR intensities were selected as off, 2 and 4. The image quality evaluation items considered were task-based transfer function (TTF), noise power spectrum (NPS), and low-contrast object specific contrast-to-noise ratio (CNRLO). The influence on radiomic analysis was assessed using the discrimination accuracy of clear cell RCC. RESULTS: For image quality evaluation, TTF and NPS values were lower and CNRLO values were higher with increasing QIR intensity; for radiomic analysis, sensitivity, specificity, and accuracy were higher with increasing QIR intensity. Principal component analysis and receiver operating characteristics analysis also showed higher values with increasing QIR intensity. CONCLUSION: It was confirmed that the intensity of the QIR intensity affects both the image quality and the radiomic analysis.

    DOI： 10.4103/jmp.jmp_114_24

    PubMed

    researchmap

  • Effect of segmentation dimension on radiomics analysis for MGMT promoter methylation status in gliomas Reviewed

    Ryohei Fukui, Masataka Onishi, Koshi Hasegawa, Miyu Ohata, Katsuhiro Kida, Sachiko Goto

    Current Neurology   24 ( 1 )   8 - 14   2024.7

    　More details

    Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Medical Communications Sp. z.o.o.  

    Introduction and objective: We investigated the impact of 2D (2D_seg) and 3D (3D_seg) segmentation on the accuracy of prediction models in the radiomics analysis to determine the presence or absence of methylation in the O6-methylguanine DNA methyltransferase (MGMT) gene promoter region of gliomas. Materials and methods: Magnetic resonance imaging images of gliomas were obtained from the Cancer Imaging Archive for 50 methylated and 50 unmethylated cases respectively. For each case, 2D_seg and 3D_seg were performed, and 788 radiomics features, including wavelet transform, were obtained. Ten features were selected by LASSO regression. The coefficients of determination (R2) and root mean squared error (RMSE) were calculated by multiple regression analysis. Discriminant boundaries to discriminate methylation were created by linear discriminant analysis, and the sensitivity and specificity of each method were calculated. The discriminant accuracy of both methods was evaluated by receiver operating characteristics (ROC) analysis. Results: The R2 value and RMSE were 0.72/0.28 and 0.73/0.33 for 2D_seg and 3D_seg, respectively. Similarly, sensitivity and specificity were 82.5/67.5% and 85/62.5%, respectively. The area under the curve determined by ROC analysis was 0.80 and 0.79, respectively, i.e. slightly larger for 2D_seg. The p-value by the DeLong method was 0.73. Conclusions: In the radiomics analysis using 2D_seg and 3D_seg, no difference in discriminant accuracy was observed between them. Therefore, 2D segmentation should be chosen because it is easier to segment.

    DOI： 10.15557/an.2024.0002

    researchmap

  • Native myocardial T1 mapping using inversion recovery T1-weighted turbo field echo sequence. Reviewed

    Katsuhiro Kida, Takamasa Kurosaki, Ryohei Fukui, Ryutaro Matsuura, Sachiko Goto

    Radiological Physics and Technology   17 ( 2 )   425 - 432   2024.3

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    This study proposes the use of the inversion recovery T1-weighted turbo field echo (IR-T1TFE) sequence for myocardial T1 mapping and compares the results obtained with those of the modified Look-Locker inversion recovery (MOLLI) method for accuracy, precision, and reproducibility. A phantom containing seven vials with different T1 values was imaged, thereby comparing the T1 measurements between the inversion recovery spin-echo (IR-SE) technique, MOLLI, and the IR-T1TFE. The accuracy, precision, and reproducibility of the T1-mapping sequences were analyzed in a phantom study. Fifteen healthy subjects were recruited for the in vivo comparison of native myocardial T1 mapping using MOLLI and IR-T1TFE sequences. After myocardium segmentation, the T1 value of the entire myocardium was calculated. In the phantom study, excellent accuracy was achieved using IR-T1TFE for all T1 ranges. MOLLI displayed lower accuracy than IR-T1TFE (p =0.016), substantially underestimating T1 at large T1 values (> 1000 ms). In the in vivo study, the first mean myocardial T1 values ± SD using MOLLI and IR-T1TFE were 1306 ± 70 ms and 1484 ± 28 ms, respectively, and the second were 1297 ± 68 ms and 1474 ± 43 ms, respectively. The native myocardial T1 obtained with MOLLI was lower than that of IR-T1TFE (p < 0.001). The reproducibility of native myocardial T1 mapping within the same sequence was not statistically significant (p = 0.11). This study demonstrates the utility and validity of myocardial T1 mapping using IR-T1TFE, which is a common sequence. This method was found to have high accuracy and reproducibility.

    DOI： 10.1007/s12194-024-00795-w

    PubMed

    researchmap

  • Task-based assessment of resolution properties of CT images with a new index using deep convolutional neural network Reviewed

    Aiko Hayashi, Ryohei Fukui, Shogo Kamioka, Kazushi Yokomachi, Chikako Fujioka, Eiji Nishimaru, Masao Kiguchi, Junji Shiraishi

    Radiological Physics and Technology   17 ( 1 )   83 - 92   2024.3

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    researchmap

  • Deep learning-based attenuation correction method in 99mTc-GSA SPECT/CT hepatic imaging: A phantom study Reviewed

    Masahiro Miyai, Ryohei Fukui, Masahiro Nakashima, Sachiko Goto

    Radiological Physics and Technology   17 ( 1 )   165 - 175   2024.3

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    researchmap

  • Assessment of a New Elbow Joint Positioning Method Using Area Detector Computed Tomography Reviewed

    Takuya Akagawa, Sachiko Goto, Ryohei Fukui, Katsuhiro Kida, Ryutaro Matsuura, Makoto Shimada, Mitsuhiro Kinoshita, Yoko Akagawa

    Acta Medica Okayama   78 ( 3 )   215 - 225   2024.3

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    researchmap

  • Characteristics of the Z-resolution measurement in the digital breast tomosynthesis Reviewed

    Saki Nishioka, Miho Numata, Natsuko Taniguchi, Ryohei Fukui, Mitsugi Honda

    Japanese Journal of Radiological Technology   79 ( 11 )   1241 - 1248   2023.11

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society of Radiological Technology  

    File： 共著_ディジタルブレストトモシンセシスのZ軸分解能測定における諸特性.pdf

    DOI： 10.6009/jjrt.2023-1395

    researchmap

  • Proposal for diagnosis using FLAIR image aimed for pediatric MELAS with recurrent stroke-like episodes on MRI system cannot take ASL imaging Reviewed

    Makoto Shimada, Tae Ikeda, Ryohei Fukui, Katsuhiro Kida, Ryutaro Matsuura, Takuya Akagawa, Sachiko Goto

    Egyptian Pediatric Association Gazette   71 ( 85 )   2023.11

    　More details

  • Influence of Two-Dimensional and Three-Dimensional Acquisitions of Radiomic Features for Prediction Accuracy Reviewed

    Ryohei Fukui, Ryutarou Matsuura, Katsuhiro Kida, Sachiko Goto

    Progress in Medical Physics   34 ( 3 )   23 - 32   2023.9

    　More details

    Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Korean Society of Medical Physics  

    File： PMP_福井論文.pdf

    DOI： 10.14316/pmp.2023.34.3.23

    researchmap

  • Effect of Bead Device Diameter on Z-Resolution Measurement in Tomosynthesis Images: A Simulation Study Reviewed

    Ryohei Fukui, Miho Numata, Saki Nishioka, Ryutarou Matsuura, Katsuhiro Kida, Sachiko Goto

    Progress in Medical Physics   33 ( 4 )   63 - 71   2022.12

    　More details

    Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Korean Society of Medical Physics  

    File： pmp-33-4-63.pdf

    DOI： 10.14316/pmp.2022.33.4.63

    researchmap

  • Effect of the center of rotation setting of the X-ray tube for the resolution characteristics of the tomosynthesis projection image Reviewed

    Yudai Ota, Ryohei Fukui

    38 ( 2 )   108 - 113   2021.7

    　More details

    Authorship：Corresponding author   Language：Japanese   Publishing type：Research paper (scientific journal)  

    File： 共著_トモシンセシス撮影におけるX線管回転中心の高さ設定が投影画像解像特性に及ぼす影響.pdf

    researchmap

  • Effect of the Number of Projected Images on the Noise Characteristics in Tomosynthesis Imaging Reviewed

    Ryohei Fukui, Ryutaro Matsuura, Katsuhiro Kida, Sachiko Goto

    Progress in Medical Physics   32 ( 2 )   50 - 58   2021.6

    　More details

    Authorship：Lead author   Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：Korean Society of Medical Physics  

    File： 論文_PMP_福井.pdf

    DOI： 10.14316/pmp.2021.32.2.50

    researchmap

  • Generation of the Pseudo CT Image Based on the Deep Learning Technique Aimed for the Attenuation Correction of the PET Image Reviewed

    Ryohei Fukui, Susumu Fujii, Hiroki Ninomiya, Yasuhiro Fujiwara, Tomonobu Ida

    Japanese Journal of Radiological Technology   76 ( 11 )   1152 - 1162   2020.11

    　More details

    Authorship：Lead author   Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society of Radiological Technology  

    File： 筆頭_深層学習を用いたPET画像の減弱補正を目的とした疑似CT画像の作成.pdf

    DOI： 10.6009/jjrt.2020_jsrt_76.11.1152

    researchmap

  • Effect of DCNN Super-Resolution Processing on Dynamic Processing in Digital Radiography (DR) Reviewed

    HAYASHI Aiko, SHIRAISHI Junji, HIRATA Sarasa, MAEKAWA Kento, YAMADA Tamaki, MIYAKE Kumiko, NAKATSUKASA Hiroaki, MORIHIRO Masashi, FUKUI Ryohei, KAWASHITA Ikuo

    Medical Imaging and Information Sciences   37 ( 2 )   21 - 27   2020

    　More details

    Authorship：Last author   Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：MEDICAL IMAGING AND INFORMATION SCIENCES  

    <p>In this study, we evaluated the effect of a newly developed super-resolution processing using Deep Convolutional Neural Network (DCNN) on the images processed with the conventional dynamic processing in digital radiography (DR). We used human phantom images to obtain case samples of which each image included a lateral view of thoracolumbar junction. All case samples were processed without and with dynamic processing, which were ranging from 1 to 4 steps of image enhancement processing. Deep Denoising Super Resolution (DDSR) were trained and assessed using the supervised image (the original image) and the low-resolution image degraded to 1/3 of matrix size by binning from the original image. The effects of the DDSR on the conventional dynamic processing were assessed using the modified Ura method of Scheffe's paired comparison. The average psychological measures for interpreting vertebral body of thoracolumbar junction tended to increase as the enhancement of dynamic processing increased, regardless of the application of DDSR. The correlation between the average psychological measures without and with DDSR was very high with a correlation coefficient of 0.98. We conclude that the effect of the DDSR on the conventional dynamic processing would be neglected on the observation of a diagnosis object in DR.</p>

    File： 共著_DRのダイナミック処理におけるDCNN超解像処理の影響.pdf

    DOI： 10.11318/mii.37.21

    CiNii Article

    researchmap

  • Application of a pixel-shifted linear interpolation technique for reducing the projection number in tomosynthesis imaging. Reviewed

    Ryohei Fukui, Junji Shiraishi

    Radiological physics and technology   12 ( 1 )   30 - 39   2019.3

    　More details

    Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

    Tomosynthesis images are reconstructed from several projections. However, the number of projections is proportional to the exposure dose, and a reduction in the number of projections would result in a reduction of radiation dose to the patient but also degradation of image quality. The purpose of this study was to propose a new computerized method to supply interpolation images instead of real projection images for maintaining the number of projection images and image quality of reconstructed tomosynthesis images. A set of images comprising one-half the number of projection images [37 projections (Half set)], selected from the original full set of projection images [73 projections (Full set)], was used at an interval of one by one. In this study, the authors used a new linear interpolation technique (Shift-Linear method), which takes into account shifted distances between two corresponding pixels on two projection images. The image quality of tomosynthesis images reconstructed from the full set and the quasi-full projection images, which were produced from the Half set using the Shift-Linear method, was compared. Image quality was assessed in terms of modulation transfer function, noise power spectrum, contrast-to-noise ratio, and the detective quantum efficiency. Using this proposed method, the image quality of reconstructed tomosynthesis images could be maintained with the reduction of approximately 50% exposure dose.

    DOI： 10.1007/s12194-018-0488-8

    PubMed

    researchmap

  • Effect of a cathepsin K inhibitor on arthritis and bone mineral density in ovariectomized rats with collagen-induced arthritis. Reviewed International journal

    Takahiro Yamashita, Hiroshi Hagino, Ikuta Hayashi, Masako Hayashibara, Atsushi Tanida, Keita Nagira, Ryohei Fukui, Hideki Nagashima

    Bone reports   9   1 - 10   2018.12

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    Objectives: Cathepsin K is expressed by osteoclasts and synovial fibroblasts and degrades key components of bone and cartilage. Inhibition of cathepsin K protease activity may be beneficial for the prevention of bone erosion and cartilage degradation in rheumatoid arthritis (RA). The collagen-induced arthritis (CIA) rat model is well established for studying the pathology and treatment of RA. We investigated the effect of ONO-KK1-300-01, a cathepsin K inhibitor (CKI), on arthritis and bone mineral density (BMD) in rats with CIA. Methods: Seven-month-old female Sprague Dawley rats were divided into 5 groups: rats without CIA (CNT); CIA rats that underwent ovariectomy (OVX) and were treated with CKI; CIA rats that underwent OVX and were treated with vehicle (Veh); CIA rats that underwent sham surgery and were treated with CKI; and CIA rats that underwent sham surgery and were treated with Veh. CKI was orally administered at a dose of 15 mg/kg, thus initiating collagen sensitization, until death at 4 weeks. We evaluated hind paw thickness and the arthritis score every week until death. Radiographs of the resected left foot were obtained with a soft X-ray apparatus. Destruction of bone and cartilage was classified and scored as previously described by Engelhardt et al. BMD was measured by bone densitometry at the halfway point between the distal metaphysis and the diaphysis of the resected right femur. We also performed histomorphometry of the proximal left tibia, histological evaluation of arthritis, and a bone strength test. Results: CKI administration significantly reduced hind paw thickness and the arthritis score, and prevented a decrease in BMD. The radiographic score was significantly lower in the CKI group than in the Veh group. In the histomorphometric analysis, bone-resorption parameters were significantly lower in the CKI groups than in the Veh groups. CKI significantly inhibited synovial proliferation in the CIA rats. In the bone strength test, the ultimate stress was significantly higher in the CKI groups than in the Veh groups. Conclusion: Our findings indicate that cathepsin K inhibitors may inhibit systemic and local bone loss, ameliorate arthritis, and attenuate the decrease of bone strength in an animal model of arthritis.

    File： 共著_Effect of a cathepsin K inhibitor on arthritis and bone mineral density in ovariectomized rats with collagen-induced arthritis.pdf

    DOI： 10.1016/j.bonr.2018.05.006

    PubMed

    researchmap

  • Proposal of the Modified Radial Frequency Method Aimed for the Measuring Noise Property of the Digital Tomosynthesis Image Reviewed

    FUKUI Ryohei, SHIRAISHI Junji

    Medical Imaging and Information Sciences   35 ( 1 )   6 - 11   2018

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：MEDICAL IMAGING AND INFORMATION SCIENCES  

    <p>The measurement method for the noise property of the digital tomosynthesis image has not been standardized in any guidelines or papers. Currently, a noise in a digital tomosynthesis image has been commonly measured using a 2-D fast Fourier transform（2D-FFT）method. The purpose of this paper is to propose a new method for measuring the noise property of a digital tomosynthesis image, which applies the radial frequency（Radial）method with a limited angular range （LAR）for data acquisition. Although the Radial method was used to obtain the power spectrum from all angles（360°）around the origin, the LAR method acquired the power spectrum in the limited angle regions. When the noise properties acquired by the LAR method with the limited angles of 3°, 5° and 15° were compared to those obtained through the Radial method and the 2D-FFT method. The results of the LAR method had the large differences compared to those of the Radial method in the u-axis direction. Further, the noise property of the LAR method and the 2D-FFT method showed a higher correlation in both axis directions. In conclusion, we believe that the noise properties of the digital tomosynthesis image can be measured by using the LAR method with a limited angle of 5°.</p>

    File： 筆頭_ディジタルトモシンセシス画像のノイズ特性測定を目的としたRadial Frequency法の変則法の提案.pdf

    DOI： 10.11318/mii.35.6

    CiNii Article

    researchmap

  • Evaluation of the effect of geometry for measuring section thickness in tomosynthesis. Reviewed

    Ryohei Fukui, Rie Ishii, Junichi Kishimoto, Shinichiro Yamato, Akira Takahata, Chiyuki Kohama

    Radiological physics and technology   7 ( 1 )   141 - 7   2014.1

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    Our aim in this study was to evaluate the effect of geometry for measuring section thickness in tomosynthesis by using a metal bead device (bead method). Tomosynthesis images were obtained from two types of tomosynthesis equipment, Safire17 (ST, Shimadzu, Kyoto, Japan) and XR650 (GT, GE Healthcare, Milwaukee, WI). After tomosynthesis radiography with each device, the bead tomosynthesis images were obtained by image reconstruction. The digital profile was obtained from the digital value of the bead central coordinate in the perpendicular direction, and we acquired the slice sensitivity profile (SSP). The section thickness was defined with the full width at half maximum obtained from the SSP. We investigated the change in section thickness under different evaluation conditions: the angular range, the height of the bead position, the source-image receptor distance (SID), and image processing. The section thickness decreased when the angular range and height of the bead position increased. Also, the section thickness varied with a change in the SID. The section thickness differed according to the geometry for measuring the section thickness. Thus, the effect of the geometry used for measurement should be considered when the section thickness in tomosynthesis is measured by the bead method.

    DOI： 10.1007/s12194-013-0243-0

    PubMed

    researchmap

  • Evaluation of a noise reduction procedure for chest radiography. Reviewed

    Ryohei Fukui, Rie Ishii, Kazuhiko Kodani, Yoshiko Kanasaki, Hisashi Suyama, Masanari Watanabe, Masaki Nakamoto, Yasushi Fukuoka

    Yonago acta medica   56 ( 4 )   85 - 91   2013.12

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    BACKGROUND: The aim of this study was to evaluate the usefulness of noise reduction procedure (NRP), a function in the new image processing for chest radiography. METHODS: A CXDI-50G Portable Digital Radiography System (Canon) was used for X-ray detection. Image noise was analyzed with a noise power spectrum (NPS) and a burger phantom was used for evaluation of density resolution. The usefulness of NRP was evaluated by chest phantom images and clinical chest radiography. We employed the Bureau of Radiological Health Method for scoring chest images while carrying out our observations. RESULTS: NPS through the use of NRP was improved compared with conventional image processing (CIP). The results in image quality showed high-density resolution through the use of NRP, so that chest radiography examination can be performed with a low dose of radiation. Scores were significantly higher than for CIP. CONCLUSION: In this study, use of NRP led to a high evaluation in these so we are able to confirm the usefulness of NRP for clinical chest radiography.

    File： 筆頭_Evaluation of a Noise Reduction Procedure for Chest Radiography.pdf

    PubMed

    researchmap

▼display all

Presentations

  • X線画像系モダリティにおける空間分解能の理解 Invited

    福井亮平

    第1回日本放射線技術学術大会(JCRTM2024)  2024.11.1 

    　More details

    Event date： 2024.10.31 - 2024.11.3

    Language：Japanese   Presentation type：Oral presentation (invited, special)  

    File： JCRTM2024_福井.pdf

    researchmap

  • 逐次近似再構成を用いたDigital Breast Tomosynthesisの低コントラスト分解能評価方法の検討

    藤田紗也加, 谷口菜摘子, 沼田美保, 木村優里, 福井亮平, 本田貢

    第20回中四国放射線医療技術フォーラム(CSFRT2024)  2024.10.20 

    　More details

    Event date： 2024.10.19 - 2024.10.20

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 1011_藤田スライド.pdf

    researchmap

  • Digital Breast Tomosynthesisにおける視覚評価を用いた最適な撮影条件の検討

    木村優里, 谷口菜摘子, 沼田美保, 藤田紗也加, 福井亮平, 本田貢

    第20回中四国放射線医療技術フォーラム(CSFRT2023)  2024.10.20 

    　More details

    Event date： 2024.10.19 - 2024.10.20

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 木村スライド1008.pdf

    researchmap

  • Proposal of a new index of resolution characteristics using DCNN in CT images

    Hayashi A, Fukui R, Kamioka S, Yakomachi K, Fujioka C, Nishimaru E, Kiguchi M, Shiraishi J

    Korean Society of Radiological Science 2023  2023.6.2 

    　More details

    Event date： 2023.6.2 - 2023.6.3

    Language：English   Presentation type：Oral presentation (general)  

    File： KSRS2023本番用 aiko.pdf

    researchmap

  • CT画像におけるDCNNを利用した新たな解像特性の指標

    林藍子, 福井亮平, 横町和志, 藤岡知加子, 西丸英治, 木口雅夫, 白石順二

    第79回日本放射線技術学会総会学術大会  2023.4.16 

    　More details

    Event date： 2023.4.13 - 2023.4.16

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： JRC2023_hayashi.pdf

    researchmap

  • 深層学習を用いた99mTc-肝受容体シンチグラフィにおける疑似CT画像生成の試み

    宮井蔣宏, 福井亮平, 中嶋真大, 後藤佐知子

    第79回日本放射線技術学会総会学術大会  2023.4.14 

    　More details

    Event date： 2023.4.13 - 2023.4.16

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： JRC2023_miyai.pdf

    researchmap

  • Suggestion for the dose reduction of the tomosynthesis imaging by using the generated interpolation image based on the deep learning

    Ryohei Fukui, Ryutaro Matsuura, Katsuhiko Kida, Sachiko Goto

    Radiological Society of North America 108th Scientific Assembly and Annual Meeting (RSNA2022)  2022.11.27 

    　More details

    Event date： 2022.11.27 - 2022.12.1

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： RSNA2022_Education.pdf

    researchmap

  • 部位別アーチファクト除去処理がCT解像特性に及ぼす影響の基礎的検討

    林藍子, 白石順二, 福井亮平, 神岡尚吾, 横町和志, 藤岡知加子, 西丸英治, 木口雅夫, 粟井和夫

    第18回中四国放射線医療技術フォーラム(CSFRT2022)  2022.10.16 

    　More details

    Event date： 2022.10.15 - 2022.10.16

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 部位別アーチファクト除去処理がCT解像.pdf

    researchmap

  • ブレストトモシンセシス画像におけるZ軸分解能の諸特性

    西岡早紀, 沼田美保, 福井亮平, 本田貢

    第50回日本放射線技術学会秋季学術大会  2022.10.8 

    　More details

    Event date： 2022.10.7 - 2022.10.9

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 秋季スライド20220905.pdf

    researchmap

  • 各領域におけるファントムの活用事例（トモシンセシス） Invited

    福井亮平

    日本放射線技術学会中国四国支部 第23回夏季学術大会 画像情報研究会  2022.7.3 

    　More details

    Event date： 2022.7.3

    Language：Japanese   Presentation type：Symposium, workshop panel (nominated)  

    File： 令和4年度_夏季_画像情報研究会_福井担当.pdf

    researchmap

  • 核医学と人工知能

    福井亮平

    第16回MICCS  2022.5.28 

    　More details

    Event date： 2022.5.28

    Language：Japanese   Presentation type：Oral presentation (invited, special)  

    File： 第16回MICCS_核医学と人工知能.pdf

    researchmap

  • Effect of the high-density object for measuring image noise in tomosynthesis

    2021.12.18 

    　More details

    Event date： 2021.12.18 - 2022.1.19

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： CSFRT2021_音声なし_福井.pdf

    researchmap

  • 異なる撮影モードのディジタルブレストトモシンセシスにおけるZ軸分解能の比較

    西岡早紀, 谷口菜摘子, 沼田美保, 福井亮平, 本田貢

    第17回中四国放射線医療技術フォーラム(CSFRT2021)  2021.12.18 

    　More details

    Event date： 2021.12.18 - 2022.1.19

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： CSFRT2021_修正 1117_2.pdf

    researchmap

  • 畳み込みニューラルネットワークを用いた仮想散乱線除去処理の検討

    林藍子, 福井亮平, 白石順二

    第49回日本放射線技術学会秋季学術大会  2021.10.17 

    　More details

    Event date： 2021.10.15 - 2021.10.17

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 2021秋季学会スライド.pdf

    researchmap

  • 逐次近似再構成法による乳房トモシンセシス撮影条件の検討

    谷口菜摘子, 森千尋, 沼田美保, 西岡早紀, 福井亮平, 本田貢

    第49回日本放射線技術学会秋季学術大会  2021.10.15 

    　More details

    Event date： 2021.10.15 - 2021.10.17

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： JSRT2021_taniguchi.pdf

    researchmap

  • 研究事例1（AI技術の生成モデルを用いた患者被ばく低減） Invited

    福井亮平

    日本放射線技術学会中国四国支部 第22回夏季学術大会 画像情報研究会  2021.7.4 

    　More details

    Event date： 2021.7.3 - 2021.7.4

    Language：Japanese   Presentation type：Symposium, workshop panel (nominated)  

    File： 令和3年度_夏季学術大会_研究事例1.pdf

    researchmap

  • GANの核医学領域への応用(核医学領域) Invited

    福井亮平

    日本放射線技術学会中国四国支部 第22回夏季学術大会  2021.7.3 

    　More details

    Event date： 2021.7.3 - 2021.7.4

    Language：Japanese   Presentation type：Symposium, workshop panel (nominated)  

    File： 令和3年度_夏季学術大会_シンポジウム.pdf

    researchmap

  • Suggestion for Dose Reduction of the PET/CT Imaging by Using the Generated Pseudo CT Image Based on the Deep Learning

    Fukui R, Sakimoto S, Fujii S, Ninomiya H, Ida T, Fujiwata Y

    Radiological Society of North America 106th Scientific Assembly and Annual Meeting (RSNA2020)  2020.11.30 

    　More details

    Language：English   Presentation type：Oral presentation (general)  

    File： RSNA2020_education exibit.pdf

    researchmap

  • 深層学習により作成したPET-to-CT画像の減弱補正への適用

    福井亮平, 﨑本翔太, 藤井進, 二宮宏樹, 井田智延, 藤原泰裕

    第2回日本核医学会中国・四国支部会  2020.5.2 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 演題13_JSNM中四国支部会_oral_fukui.pdf

    researchmap

  • 深層学習をベースとしたPET-to-CT画像生成の試み

    福井亮平, 﨑本翔太, 藤井進, 二宮宏樹, 井田智延, 藤原泰裕

    第30回山陰デジタル画像研究会  2020.2.22 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 山デジ_PETtoCT_福井.pdf

    researchmap

  • DCNNによる超解像処理におけるDR圧縮処理の影響

    林藍子, 平田更紗, 前川賢斗, 山田圭紀, 三宅久美子, 中務博章, 森広雅史, 福井亮平, 川下郁夫, 白石順二

    医用画像情報学会令和元年度春季(第186回)大会  2020.2.1 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： MII2020_poster.pdf

    researchmap

  • Influence of the Center of Rotation of the X-ray Tube in Tomosynthesis Imaging

    Ota Y, Fukui R

    Radiological Society of North America 105th Scientific Assembly and Annual Meeting (RSNA2019)  2019.12.6 

    　More details

    Language：English   Presentation type：Oral presentation (general)  

    File： RSNA2019_educational exhibit_1019.pdf

    researchmap

  • PET画像における深層学習を用いた疑似CT画像作成による減弱補正法の検討

    福井亮平, 﨑本翔太, 藤井進, 二宮宏樹, 井田智延, 藤原泰裕

    第47回日本放射線技術学会秋季学術大会  2019.10.19 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： JSRT_Autumn2019_oral.pdf

    researchmap

  • 深層学習によるPET画像を用いた疑似CT画像作成の試み

    福井亮平, 﨑本翔太, 藤井進, 二宮宏樹, 井田智延, 藤原泰裕

    第15回中四国放射線医療技術フォーラム(CSFRT2019)  2019.9.22 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： CSFRT2019_oral.pdf

    researchmap

  • AIの概要と医用分野への応用について Invited

    福井亮平

    第25回医用画像情報研究会サマースクール  2019.9.8 

    　More details

    Language：Japanese   Presentation type：Oral presentation (invited, special)  

    File： 第25回サマースクール_AI.pdf

    researchmap

  • PET/CTで指摘された肝膿瘍を疑わせる1例

    福井亮平

    日本放射線技術学会中国四国支部 第20回夏季学術大会 核医学研究会  2019.7.7 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： 令和1年度夏季_核医学_症例報告0706.pdf

    researchmap

  • トモシンセシスにおけるX線管回転中心の高さが解像特性に与える影響

    太田雄大, 福井亮平

    第75回日本放射線技術学会総会学術大会  2019.4.14 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： JRC2019_Cypos_0227.pdf

    researchmap

  • 深層学習による超解像技術を応用した顎関節トモシンセシス撮影の線量低減

    福井亮平, 白石順二

    第75回日本放射線技術学会総会学術大会  2019.4.13 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： JRC2019_Cypos_last.pdf

    researchmap

  • Flat Panel Detectorにおける斜め45度方向の解像特性

    石井里枝, 福井亮平, 石井美枝, 眞田泰三, 吉田彰

    第75回日本放射線技術学会総会学術大会  2019.4.11 

    　More details

    Language：Japanese   Presentation type：Oral presentation (general)  

    File： JRC2019_Cypos_20190222.pdf

    researchmap

▼display all

Research Projects

  • 人工知能を応用した疑似トモシンセシス画像によるマンモトーム生検精度向上技術の開発

    Grant number：23K17230  2023.04 - 2026.03

    日本学術振興会  科学研究費助成事業 若手研究  若手研究

    福井 亮平

    　 More details

    Authorship：Principal investigator 

    Grant amount：\4030000 （ Direct expense: \3100000 、 Indirect expense：\930000 ）

    researchmap

  • 人工知能技術を応用した患者被ばくを低減する新しいＰＥＴ検査法の提案

    Grant number：20H01129  2020.04 - 2021.03

    日本学術振興会  科学研究費助成事業 奨励研究  奨励研究

    福井 亮平

    　 More details

    Grant amount：\480000 （ Direct expense: \480000 ）

    本研究では，従来はCT画像により実施されるPET画像の減弱補正を，深層学習（CycleGAN）による疑似CT画像作成により達成することを目的とした．診療で撮影された約15,000枚のPET画像とCT画像により学習したCycleGANにより，PET画像から疑似CT画像を生成することは可能であった．また，疑似CT画像によりPET画像の減弱補正も達成された．画像の類似度を評価する指標により，疑似的なCT画像および減弱補正されたPET画像の類似度は高いことが確認された．しかし，臨床で用いるにはさらに疑似CT画像の生成精度を向上させる必要があり，学習モデルの改善や，学習データの増強が必須である．

    researchmap

  • X線画像評価用模型(ファントム)の試作と評価に関する研究

    Grant number：25931041  2013.04 - 2014.03

    日本学術振興会  科学研究費助成事業 奨励研究  奨励研究

    福井 亮平

    　 More details

    Grant amount：\300000 （ Direct expense: \300000 ）

    【プロジェクト等の成果】
    ○ファントム作製 : ファントムのスポンジに塗布する水性造影剤の量(xml)と, 最外部のワックスに混和する油性造影剤量(yml)を変化させて試作ファントムを作製した. 人体から得た手根骨のx線画像を基準とし, 最良となるx, yを決定した. 指標は骨梁やファントム全体のコントラストとした. その結果, x=0.2ml, y=0.1mlとなった.
    ○骨折線検出能の比較 : 単純X線撮影(radiography)による2方向(2R)および4方向撮影(4R), トモシンセシス(tomos)による2方向撮影画像の評価結果によりROC曲線を算出した. 曲線下面積(AUC)は2R, 4R, tomosでそれぞれ0.67, 0.75, 0.8となった. 2R-4R間, 4R-tomos間は有意水準5%のとき有意差があった. 従って, tomosの骨折線検出能がradiographyより有意に高いことが示された. また, 2R, 4R, tomosの感度-特異度は54-63%, 59-63%, 73-76%となった.
    【本研究の意義】
    本作成法は様々な骨折線を想定でき, モダリティの検出限界を引き出すことが可能である. また, CTなど他モダリティにも転用可能である.
    経験年数(1～3年および4～27年)で観察者を分けROC曲線を算出した. AUCの差は4Rとtomosでそれぞれ0.05, 0.03であった. 従って, tomosは読影能力の差を軽減する可能性が示唆された. しかし, 偽陽性率は4Rで37%, tomosで24%だった. radiographyとtomosで最も評価に差が生じた骨折方向は, 手根骨の水平面に並行な骨折線であった. これはtomosにより偽陰性を低下させたためである. しかし, tomosでもX線束軸に接線とならない骨折線は描出困難であった. 以上より, 試作ファントムの有用性, およびtomosの骨折線検出能を確認できた.

    researchmap

 

Class subject in charge

  • Exercise of Team Medical Activities （2024academic year） 1st and 2nd semester  - その他

  • Medical Image Processing Practice （2024academic year） Fourth semester  - 金4～5

  • Medical Informatics, Practice （2024academic year） 1st semester  - 木4～5

  • Graduation Thesis in Radiological Technology （2024academic year） 1-3 semesters  - その他

  • Practical Clinical Radiology Exercise （2024academic year） Second semester  - 金4～5

  • Experiments in Radiochemistry （2024academic year） 3rd and 4th semester  - 木4～6

  • Experiments in Radiation Safety Management （2024academic year） Second semester  - 月5～7,水5～7

  • Experiments in Radiation Safety Management （2024academic year） 1st and 2nd semester  - 水5～6

  • Experiment of Radiation Equipment Engineering （2024academic year） 3rd and 4th semester  - [第３学期]火7～8,金7～8, [第４学期]火7～8,水7～8

  • Human Macroscopic Anatomy of Radiology （2024academic year） 1st semester  - 月2～3

  • Experiments in Radiation Detection and Measurement （2024academic year） 3rd and 4th semester  - 月5～7

  • Clinical Practice (Special) （2024academic year） Fourth semester  - 月4～6,水4～6

  • Practice in Clincal RadiologyI （2024academic year） 3rd and 4th semester  - [第３学期]火3～6,金3～6, [第４学期]火3～6,水3～6

  • Practice in Clincal RadiologyⅡ （2024academic year） 1-3 semesters  - その他

  • Clinical Skills Practice （2024academic year） 1st and 2nd semester  - 金6～8

  • Clinical Skills Exercise （2024academic year） 1st semester  - 金6～8

  • Radiographic Technology Practices （2024academic year） 3rd and 4th semester  - [第３学期]火1～2,金1～2, [第４学期]火1～2,水1～2

  • Radiographic Technology （2024academic year） 1st semester  - 火2～3

  • Medical Image Processing Practice （2023academic year） Fourth semester  - 金4～6

  • Medical Informatics, Practice （2023academic year） 1st semester  - 水4～5

  • Graduation Thesis in Radiological Technology （2023academic year） 1-3 semesters  - その他

  • Experiments in Radiochemistry （2023academic year） 3rd and 4th semester  - 木4～6

  • Experiment of Radiographic Imaging （2023academic year） Second semester  - 月5～7,水5～7

  • Experiment of Radiation Equipment Engineering （2023academic year） 3rd and 4th semester  - [第３学期]火5～8,金5～8, [第４学期]火5～8,水5～8

  • Human Macroscopic Anatomy of Radiology （2023academic year） 1st semester  - 木1～2

  • Experiments in Radiation Detection and Measurement （2023academic year） 3rd and 4th semester  - 月5～7

  • Human Macroscopic Anatomy （2023academic year） 1st semester  - 木1～2

  • Clinical Practice (Special) （2023academic year） Fourth semester  - 月4～6,水4～6

  • Practice in Clincal RadiologyI （2023academic year） special  - その他

  • Clinical Skills Exercise （2023academic year） Second semester  - 金7～8

  • Radiographic Technology Practices （2023academic year） 3rd and 4th semester  - [第３学期]火1～4,金1～4, [第４学期]火1～4,水1～4

  • Graduation Thesis in Radiological Technology （2022academic year） 1-3 semesters  - その他

  • Experiments in Radiochemistry （2022academic year） 3rd and 4th semester  - 木5～7

  • Experiment of Radiographic Imaging （2022academic year） Second semester  - 月5～7,水5～7

  • Experiment of Radiation Equipment Engineering （2022academic year） 3rd and 4th semester  - [第３学期]火5～8,金5～8, [第４学期]火5～8,水5～8

  • Experiments of Dosimetry （2022academic year） Second semester  - 火1～6

  • Experiments in Radiation Detection and Measurement （2022academic year） 3rd and 4th semester  - 月5～7

  • Human Macroscopic Anatomy （2022academic year） 1st semester  - 木1～2

  • Clinical Practice (Special) （2022academic year） Fourth semester  - 月4～6,水4～6

  • Practice in Clincal RadiologyI （2022academic year） special  - その他

  • Simulation-based Clinical-Skills Examination （2022academic year） Second semester  - 金7～8

  • Radiographic Technology Practices （2022academic year） 3rd and 4th semester  - [第３学期]火1～4,金1～4, [第４学期]火1～4,水1～4

  • Medical Image Analysis and Diagnosis （2021academic year） Late  - 月7

  • Seminar in Medical Imaging （2021academic year） Late  - 水7

  • Experiments in Radiochemistry （2021academic year） 3rd and 4th semester  - 木5～7

  • Experiment of Radiographic Imaging （2021academic year） Second semester  - 月5～7,水5～7

  • Experiment of Radiation Equipment Engineering （2021academic year） 3rd and 4th semester  - [第３学期]火5～8,金5～8, [第４学期]火5～8,水5～8

  • Experiments of Dosimetry （2021academic year） Second semester  - 火1～6

  • Experiments in Radiation Detection and Measurement （2021academic year） 3rd and 4th semester  - 月5～7

  • Human Macroscopic Anatomy （2021academic year） 1st semester  - 木1～2

  • Clinical Practice (Special) （2021academic year） Fourth semester  - 月4～6,水4～6

  • Simulation-based Clinical-Skills Examination （2021academic year） Summer concentration  - その他

  • Radiographic Technology Practices （2021academic year） 3rd and 4th semester  - [第３学期]火1～4,金1～4, [第４学期]火1～4,水1～4

  • Medical Image Analysis and Diagnosis （2020academic year） Late  - 月7

  • Seminar in Medical Imaging （2020academic year） Late  - 水7

▼display all