Updated on 2025/11/10

All information, except for affiliations, is reprinted from the information registered on researchmap.

写真a

 
Akiyoshi Hizukuri
 
Organization
Graduate School of Data Science Department of Data Science Associate Professor
School of Data Science Department of Data Science
Title
Associate Professor
External link

Degree

  • Doctor of Engineering ( Mie University )

Research Interests

  • machine learning

  • medical image analysis

  • image processing

  • deep learning

Research Areas

  • Life Science / Medical systems

  • Informatics / Perceptual information processing

  • Informatics / Intelligent informatics

  • Informatics / Soft computing

  • Informatics / Life, health and medical informatics

Education

  • Mie University   Graduate School of Engineering   Division of Systems Engineering

    - 2014.3

    　 More details

  • Mie University   Graduate School of Engineering   Division of Electrical and Electronic Engineering

    - 2011.3

    　 More details

  • Mie University   Faculty of Engineering   Department of Electrical and Electronic Engineering

    - 2009.3

    　 More details

Research History

  • Yokohama City University   School of Data Science   Associate Professor

    2025.4

    　 More details

  • Ritsumeikan University   College of Science and Engineering Department of Electronic and Computer Engineering   Lecturer

    2023.4 - 2025.3

    　 More details

  • Ritsumeikan University   College of Science and Engineering Department of Electronic and Computer Engineering   Assistant Professor

    2018.4 - 2023.3

    　 More details

  • Mizuho Information & Research Institute, Inc.

    2014.4 - 2018.3

    　 More details

Professional Memberships

  • Japan Society of Medical Physics

    　 More details

  • The Institute of Electronics, Information and Communication Engineers

    　 More details

  • The Institute of Electrical Engineers of Japan

    　 More details

  • Technical Committee on Industrial Application of Image Processing

    　 More details

  • The Japanese Society of Medical Imaging Technology

    　 More details

Committee Memberships

  • ICIPRob2026 (International Conference on Image Processing and Robotics)   International Program Committee  

    2026.3   

    　 More details

    Committee type：Academic society

    researchmap

  • 精密工学会   春季・秋季大会 オーガナイザー  

    2025.4   

    　 More details

    Committee type：Academic society

    researchmap

  • 電子情報通信学会   英文論文誌D編集委員  

    2025.4   

    　 More details

    Committee type：Academic society

    researchmap

  • 動的画像処理実利用化ワークショップ2026（DIA2026）   幹事（プログラム委員会）  

    2025.4 - 2026.3   

    　 More details

    Committee type：Academic society

    researchmap

  • ビジョン技術の実利用ワークショップ2025（ViEW2025）   組織委員会委員  

    2025.4 - 2025.12   

    　 More details

    Committee type：Academic society

    researchmap

  • 令和7年電気学会全国大会グループ委員会   5グループ委員  

    2024.9 - 2025.3   

    　 More details

  • ATAIT 2024（International Symposium on Advanced Technologies and Applications in the Internet of Things）   Local Arrangement Chair  

    2024.8   

    　 More details

  • 電気学会 論文委員会（C2）   幹事  

    2024.4   

    　 More details

  • 画像応用技術専門委員会   運営委員  

    2024.4   

    　 More details

  • 動的画像処理実利用化ワークショップ2025（DIA2025）   幹事（プログラム委員会）  

    2024.4 - 2025.3   

    　 More details

  • ビジョン技術の実利用ワークショップ2024   委員（組織委員会）  

    2024.4 - 2024.12   

    　 More details

  • ICIPRob2024 (International Conference on Image Processing and Robotics)   International Program Committee  

    2024.3   

    　 More details

  • 電気学会 論文委員会（C2）   委員  

    2024.2 - 2024.3   

    　 More details

  • ATAIT2023（International Symposium on Advanced Technologies and Applications in the Internet of Things）   Local Arrangement Chair  

    2023.8   

    　 More details

  • SCIS&ISIS2022 (Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems)   Program Committee Members  

    2022.11 - 2022.12   

    　 More details

  • ICIPRob2022 (International Conference on Image Processing and Robotics)   International Program Committee  

    2022.3   

    　 More details

  • 電気関係学会関西連合大会実行委員会   委員（会場担当）  

    2020.11   

    　 More details

  • 電子情報通信学会関西支部   運営委員  

    2020.4 - 2022.3   

    　 More details

  • IEEE Kansai Section Young Professionals Affinity Group   Committee Member  

    2020.1 - 2021.12   

    　 More details

  • ICIPRob2020 (International Conference on Image Processing and Robotics)   International Program Committee  

    2019.4 - 2020.3   

    　 More details

▼display all

Papers

  • Unsupervised Video Anomaly Detection Using Video Vision Transformer and Adversarial Training Reviewed

    Kobayshi Shimpei, Akiyoshi Hizukuri, Ryohei Nakayama

    IEEE Access   2025.3

    　More details

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

    researchmap

  • Anomaly detection scheme for lung CT images using vector quantized variational auto-encoder with support vector data description. Reviewed

    Zhihui Gao, Ryohei Nakayama, Akiyoshi Hizukuri, Shoji Kido

    Radiological physics and technology   18 ( 1 )   17 - 26   2025.3

    　More details

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

    This study aims to develop an anomaly-detection scheme for lesions in CT images. Our database consists of lung CT images obtained from 1500 examinees. It includes 1200 normal and 300 abnormal cases. In this study, SVDD (Support Vector Data Description) mapping the normal latent variables into a hypersphere as small as possible on the latent space is introduced to VQ-VAE (Vector Quantized-Variational Auto-Encoder). VQ-VAE with SVDD is constructed from two encoders, two decoders, and an embedding space. The first encoder compresses the input image into the latent-variable map, whereas the second encoder maps the normal latent variables into a hypersphere as small as possible. The first decoder then up-samples the mapped latent variables into a latent-variable map with the original size. The second decoder finally reconstructs the input image from the latent-variable map replaced by the embedding representations. The data of each examinee is classified as abnormal or normal based on the anomaly score defined as the combination of the difference between the input image and the reconstructed image and the distance between the latent variables and the center of the hypersphere. The area under the ROC curve for VQ-VAE with SVDD was 0.76, showing an improvement when compared with the conventional VAE (0.63, p < .001). VQ-VAE with SVDD developed in this study can yield higher anomaly-detection accuracy than the conventional VAE. The proposed method is expected to be useful for identifying examinees with lesions and reducing interpretation time in CT screening.

    DOI： 10.1007/s12194-024-00851-5

    PubMed

    researchmap

  • Computerized classification method for significant coronary artery stenosis on whole-heart coronary MRA using 3D convolutional neural networks with attention mechanisms. Reviewed

    Takuma Shiomi, Ryohei Nakayama, Akiyoshi Hizukuri, Masafumi Takafuji, Masaki Ishida, Hajime Sakuma

    Radiological physics and technology   18 ( 1 )   219 - 226   2025.3

    　More details

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

    This study aims to develop a computerized classification method for significant coronary artery stenosis on whole-heart coronary magnetic resonance angiography (WHCMRA) images using a 3D convolutional neural network (3D-CNN) with attention mechanisms. The dataset included 951 segments from WHCMRA images of 75 patients who underwent both WHCMRA and invasive coronary angiography (ICA). Forty-two segments with significant stenosis (luminal diameter reduction ≥ 75%) on ICA were annotated on WHCMRA images by an experienced radiologist, whereas 909 segments without it were annotated at representative sites. Volumes of interest (VOIs) of 21 × 21 × 21 voxels centered on annotated points were extracted. The network comprises two feature extractors, two attention mechanisms (for the coronary artery and annotated points), and a classifier. The feature extractors first extracted the feature maps from the VOI. The two attention mechanisms weighted the feature maps of the coronary artery and those the neighborhood of the annotated point, respectively. The classifier finally classified the VOIs into those with and without significant coronary artery stenosis. Using fivefold cross-validation, the classification accuracy, sensitivity, specificity, and AUROC (area under the receiver operating characteristic curve) were 0.875, 0.905, 0.873, and 0.944, respectively. The proposed method showed high classification performance for significant coronary artery stenosis and appears to have a substantial impact on the interpretation of WHCMRA images.

    DOI： 10.1007/s12194-024-00875-x

    PubMed

    researchmap

  • Computerized Segmentation Method for Nonmasses on Breast DCE-MRI Images Using ResUNet++ with Slice Sequence Learning and Cross-Phase Convolution. Reviewed International journal

    Akiyoshi Hizukuri, Ryohei Nakayama, Mariko Goto, Koji Sakai

    Journal of imaging informatics in medicine   37 ( 4 )   1567 - 1578   2024.8

    　More details

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

    The purpose of this study was to develop a computerized segmentation method for nonmasses using ResUNet++ with a slice sequence learning and cross-phase convolution to analyze temporal information in breast dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI) images. The dataset consisted of a series of DCE-MRI examinations from 54 patients, each containing three-phase images, which included one image that was acquired before contrast injection and two images that were acquired after contrast injection. In the proposed method, the region of interest (ROI) slice images are first extracted from each phase image. The slice images at the same position in each ROI are stacked to generate a three-dimensional (3D) tensor. A cross-phase convolution generates feature maps with the 3D tensor to incorporate the temporal information. Subsequently, the feature maps are used as the input layers for ResUNet++. New feature maps are extracted from the input data using the ResUNet++ encoders, following which the nonmass regions are segmented by a decoder. A convolutional long short-term memory layer is introduced into the decoder to analyze a sequence of slice images. When using the proposed method, the average detection accuracy of nonmasses, number of false positives, Jaccard coefficient, Dice similarity coefficient, positive predictive value, and sensitivity were 90.5%, 1.91, 0.563, 0.712, 0.714, and 0.727, respectively, larger than those obtained using 3D U-Net, V-Net, and nnFormer. The proposed method achieves high detection and shape accuracies and will be useful in differential diagnoses of nonmasses.

    DOI： 10.1007/s10278-024-01053-6

    PubMed

    researchmap

  • Computerized Classification Method for Molecular Subtypes of Low-grade Gliomas on Brain MR Images Using Modified ArcFace with Gram–Schmidt Orthogonalization Invited Reviewed

    Akiyoshi Hizukuri, Daiki Tanaka, Ryohei Nakayama, Kaori Kusuda, Ken Masamune, Yoshihiro Muragaki

    IEEE Access   12   194540 - 194550   2024

    　More details

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

    researchmap

  • マルチシーケンス脳MRIを用いたMulti-scale 3D-Attention Branch Networksによるグリオーマ分子サブタイプ分類 Reviewed

    田中大貴, 檜作彰良, 中山良平, 楠田佳緒, 正宗賢, 村垣善浩

    電気学会論文誌C   143 ( 5 )   539 - 545   2023.5

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Two-Stream 3D Convolutional Neural Networks-v2を用いた万引き行動の自動検知手法の高速化 Reviewed

    山下裕之介, 檜作彰良, 中山良平

    情報処理学会論文誌   64 ( 1 )   229 - 235   2023.1

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Semantic Face Segmentation Using Convolutional Neural Networks with a Supervised Attention Module Reviewed

    Akiyoshi Hizukuri, Yuto Hirata, Ryohei Nakayama

    IEEE Access   11   116892 - 116902   2023

    　More details

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

    researchmap

  • Computerized Classification Method for 1p/19q Codeletion in Low Grade Gliomas from Brain MRI Images Using Three Dimensional Radiomics Features Reviewed

    The Journal of the Institute of Image Electronics Engineers of Japan (IIEEJ)   10 ( 1 )   120 - 126   2022.6

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Tooth detection for each tooth type by application of faster R-CNNs to divided analysis areas of dental panoramic X-ray images Reviewed

    Yuichi Mima, Ryohei Nakayama, Akiyoshi Hizukuri, Kan Murata

    Radiological Physics and Technology   15 ( 2 )   170 - 176   2022.5

    　More details

    Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    This study aimed to propose a computerized method for detecting the tooth region for each tooth type as the initial stage in the development of a computer-aided diagnosis (CAD) scheme for dental panoramic X-ray images. Our database consists of 160 panoramic dental X-ray images obtained from 160 adult patients. To reduce false positives (FPs), the proposed method first extracts a rectangular area including all teeth from a dental panoramic X-ray image with a faster region using a convolutional neural network (Faster R-CNN). From the rectangular area including all teeth, six divided areas are then extracted with Faster R-CNN: top left, top center, top right, bottom left, bottom center, and bottom right. Faster R-CNNs for detecting tooth regions for each tooth type were trained individually for each of the divided areas that narrowed down the target tooth types. By applying these Faster R-CNNs to each divided area, the bounding boxes of each tooth were detected and classified into 32 tooth types. A k-fold cross-validation method with k = 4 was used for training and testing the proposed method. The detection rate for each tooth, number of FPs per image, mean intersection over union for each tooth, and classification accuracy for the 32 tooth types were 98.9%, 0.415, 0.748, and 91.7%, respectively, showing an improvement compared to the application of the Faster R-CNN once to the entire image (98.0%, 1.194, 0.736, and 88.8%).

    DOI： 10.1007/s12194-022-00659-1

    PubMed

    researchmap

    Other Link： https://link.springer.com/article/10.1007/s12194-022-00659-1/fulltext.html

  • ROI Poolingを用いたCNNによる乳房超音波画像上の腫瘤病変の病理組織型分類 Reviewed

    檜作彰良, 國枝紳也, 中山良平

    電気学会論文誌C   142 ( 5 )   586 - 592   2022.5

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Attention Mechanismを導入したMulti-scale 3D-CNNsによる脳MRI画像の低悪性度グリオーマの1p/19q共欠損分類 Reviewed

    田中大貴, 檜作彰良, 中山良平

    電気学会論文誌C   142 ( 5 )   550 - 556   2022.5

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • 各顔パーツを対象とした複数CNNモデルによる顔画像の高解像度化 Reviewed

    丸井勇輝, 檜作彰良, 中山良平

    情報処理学会論文誌   63 ( 5 )   1216 - 1224   2022.5

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Generalized Dice Lossを用いたEncoder-Multiple Decoders U-Netによる顔パーツのセマンティックセグメンテーション Reviewed

    宮本旭, 檜作彰良, 中山良平

    画像電子学会誌   51 ( 2 )   150 - 156   2022.4

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Cross Modality Pre-Trainingを用いたTwo-Stream 3D Convolutional Neural Networksによる万引き行動の自動検知 Reviewed

    山下裕之介, 檜作彰良, 中山良平

    情報処理学会論文誌   62 ( 5 )   1193 - 1199   2021.5

    　More details

  • Segmentation of teeth in panoramic dental X-ray images using U-Net with a loss function weighted on the tooth edge Reviewed

    Yuya Nishitani, Ryohei Nakayama, Daisei Hayashi, Akiyoshi Hizukuri, Kan Murata

    Radiological Physics and Technology   14 ( 1 )   64 - 69   2021.1

    　More details

    Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    Panoramic dental X-ray imaging is an established method for the diagnosis of dental problems. However, the resolution of panoramic dental X-ray images is relatively low. Thus, early lesions are often overlooked. As the first step in the development of a computer-aided diagnosis scheme for panoramic dental X-ray images, we propose a computerized method for the segmentation of teeth using U-Net with a loss function weighted on the tooth edge. Our database consisted of 162 panoramic dental X-ray images. The training dataset consisted of 102 images, while the remaining 60 images were used as the test dataset. The loss function obtained by the cross entropy (CE) in the entire image is usually used in training U-Net. To improve the segmentation accuracy of the tooth edge, a loss function weighted on the tooth edge is proposed by adding the CE in the tooth edge region to the CE for the entire image. The mean Jaccard index and Dice index for U-Net with the loss function combining the CEs for the entire image and tooth edge were 0.864 and 0.927, respectively, which were significantly larger than those for U-Net with the CE for the entire image (0.802 and 0.890, p < 0.001) and U-Net with the CE for the tooth edge (0.826 and 0.905, p < 0.001). U-Net with the new loss function exhibited a higher segmentation accuracy of the tooth in panoramic dental X-ray images than that obtained by U-Net with the conventional loss function.

    DOI： 10.1007/s12194-020-00603-1

    PubMed

    researchmap

    Other Link： http://link.springer.com/article/10.1007/s12194-020-00603-1/fulltext.html

  • Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses on Breast DCE-MRI Images Using Deep Convolutional Neural Network with Bayesian Optimization Reviewed

    Akiyoshi Hizukuri, Ryohei Nakayama, Mayumi Nara, Megumi Suzuki, Kiyoshi Namba

    Journal of Digital Imaging   34 ( 1 )   116 - 123   2020.11

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    DOI： 10.1007/s10278-020-00394-2

    researchmap

    Other Link： http://link.springer.com/article/10.1007/s10278-020-00394-2/fulltext.html

  • 事例ベース超解像技術を用いた歯科パノラマX線画像の高画質化 Reviewed

    檜作 彰良, 中山 良平, 服部政幸

    医用画像情報学会雑誌   36 ( 4 )   162 - 172   2019.12

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Improving Image Resolution of Whole-Heart Coronary MRA Using Convolutional Neural Network Reviewed

    Hiroki Kobayashi, Ryohei Nakayama, Akiyoshi Hizukuri, Masaki Ishida, Kakuya Kitagawa, Hajime Sakuma

    Journal of Digital Imaging   33 ( 2 )   497 - 503   2019.8

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    DOI： 10.1007/s10278-019-00264-6

    researchmap

    Other Link： http://link.springer.com/article/10.1007/s10278-019-00264-6/fulltext.html

  • 病理組織画像解析の研究動向

    檜作 彰良, 中山 良平

    医用画像情報学会雑誌   36   53 - 58   2019

    　More details

    Publishing type：Research paper (scientific journal)  

    researchmap

  • Computer-Aided Diagnosis Scheme for Determining Histological Classification of Breast Lesions on Ultrasonographic Images Using Convolutional Neural Network Reviewed

    Akiyoshi Hizukuri, Ryohei Nakayama

    Diagnostics   8 ( 3 )   48 - 48   2018.7

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

    It can be difficult for clinicians to accurately discriminate among histological classifications of breast lesions on ultrasonographic images. The purpose of this study was to develop a computer-aided diagnosis (CADx) scheme for determining histological classifications of breast lesions using a convolutional neural network (CNN). Our database consisted of 578 breast ultrasonographic images. It included 287 malignant (217 invasive carcinomas and 70 noninvasive carcinomas) and 291 benign lesions (111 cysts and 180 fibroadenomas). In this study, the CNN constructed from four convolutional layers, three batch-normalization layers, four pooling layers, and two fully connected layers was employed for distinguishing between the four different types of histological classifications for lesions. The classification accuracies for histological classifications with our CNN model were 83.9–87.6%, which were substantially higher than those with our previous method (55.7–79.3%) using hand-crafted features and a classifier. The area under the curve with our CNN model was 0.976, whereas that with our previous method was 0.939 (p = 0.0001). Our CNN model would be useful in differential diagnoses of breast lesions as a diagnostic aid.

    DOI： 10.3390/diagnostics8030048

    researchmap

  • Segmentation Method of Breast Masses on Ultrasonographic Images Using Level Set Method Based on Statistical Model Reviewed

    Akiyoshi Hizukuri, Ryohei Nakayama, Hiroshi Ashiba

    Journal of Biomedical Science and Engineering   10 ( 04 )   149 - 162   2017

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Scientific Research Publishing, Inc.  

    DOI： 10.4236/jbise.2017.104012

    researchmap

    Other Link： http://file.scirp.org/xml/75815.xml

  • Computerized Scheme for Histological Classification of Masses with Architectural Distortions in Ultrasonographic Images Reviewed

    Akiyoshi Hizukuri, Ryohei Nakayama, Emi Honda, Yumi Kashikura, Tomoko Ogawa

    Journal of Biomedical Science and Engineering   09 ( 08 )   399 - 409   2016

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Scientific Research Publishing, Inc.  

    DOI： 10.4236/jbise.2016.98035

    researchmap

    Other Link： http://file.scirp.org/xml/68096.xml

  • Computerized Determination Scheme for Histological Classification of Breast Mass Using Objective Features Corresponding to Clinicians’ Subjective Impressions on Ultrasonographic Images Reviewed

    Akiyoshi Hizukuri, Ryohei Nakayama, Yumi Kashikura, Haruhiko Takase, Hiroharu Kawanaka, Tomoko Ogawa, Shinji Tsuruoka

    Journal of Digital Imaging   26 ( 5 )   958 - 970   2013.4

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    DOI： 10.1007/s10278-013-9594-7

    researchmap

    Other Link： http://link.springer.com/article/10.1007/s10278-013-9594-7/fulltext.html

  • Improved Differential Diagnosis of Breast Masses on Ultrasonographic Images with a Computer-Aided Diagnosis Scheme for Determining Histological Classifications Reviewed

    Yumi Kashikura, Ryohei Nakayama, Akiyoshi Hizukuri, Aya Noro, Yuki Nohara, Takashi Nakamura, Minori Ito, Hiroko Kimura, Masako Yamashita, Noriko Hanamura, Tomoko Ogawa

    Academic Radiology   20 ( 4 )   471 - 477   2013.4

    　More details

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

    DOI： 10.1016/j.acra.2012.11.007

    researchmap

  • Computerized Segmentation Method for Individual Calcifications Within Clustered Microcalcifications While Maintaining Their Shapes on Magnification Mammograms Reviewed

    Akiyoshi Hizukuri, Ryohei Nakayama, Nobuo Nakako, Hiroharu Kawanaka, Haruhiko Takase, Koji Yamamoto, Shinji Tsuruoka

    Journal of Digital Imaging   25 ( 3 )   377 - 386   2011.10

    　More details

    Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

    DOI： 10.1007/s10278-011-9420-z

    researchmap

    Other Link： http://link.springer.com/article/10.1007/s10278-011-9420-z/fulltext.html

  • Computer-Aided Detection Scheme for Sentinel Lymph Nodes in Lymphoscintigrams using Symmetrical Property Around Mapped Injection Point Reviewed

    Ryohei Nakayama, Akiyoshi Hizukuri, Koji Yamamoto, Nobuo Nakako, Naoki Nagasawa, Kan Takeda

    Journal of Digital Imaging   25 ( 1 )   148 - 154   2011.7

    　More details

▼display all

Books

  • 深層学習を用いた防犯カメラ映像からの異常行動検知

    檜作彰良,小林慎平,中山良平

    画像ラボ  2025.5 

    　More details

  • 推定

    檜作彰良（ Role： Sole author）

    画像通信  2021.10 

    　More details

  • 深層学習を用いた医用画像上の病変分類

    檜作彰良（ Role： Sole author）

    画像通信  2020.4 

    　More details

  • CAD・AIの未来

    檜作彰良（ Role： Sole author）

    京都府立医科大学雑誌  2020.2 

    　More details

  • 機械学習・人工知能業務活用の手引き～導入の判断・具体的応用とその運用設計事例集～

    檜作彰良（第5 章第1 節第3 項・4 項/第 5 章第7 節第1 項）

    株式会社情報機構,  2017.11  （ ISBN:9784865021424 ）

    　More details

Presentations

  • 外観検査におけるAIの活用

    第32回エレクトロニクス実装学術講演大会講演論文集  2018.3 

    　More details

  • 畳み込みニューラルネットワーク（CNN）を用いた超低線量CT（Computed Tomography）画像の高画質化

    第36回日本医用画像工学会大会  2017.7 

    　More details

  • CNNによる冠動脈MRA画像の高解像度化

    第19回医用画像認知研究会  2017.7 

    　More details

  • Detection and Tracking Method for Cells Using Adaptive Thresholding

    International Symposium on Imaging Frontier (ISIF2017)  2017.7 

    　More details

  • カップリング学習による顔超解像

    第21回日本顔学会大会  2016 

    　More details

  • Tablet PCによるARナビゲーションシステムの開発 ～カップリング学習によるレジストレーションの基礎検討 ～

    第25回日本コンピュータ外科学会大会特集号  2016 

    　More details

  • 局所ヒストグラム情報を用いた欠陥検出手法

    ViEW2015 ビジョン技術の実利用ワークショップ  2015.12 

    　More details

  • HOG特徴量を用いたReal AdaBoostによる欠陥検出～機械学習を用いた欠陥検出～

    ViEW2014 ビジョン技術の実利用ワークショップ  2014.12 

    　More details

  • Computerized Classification Method for Histological Classification of Masses using Objective Features Based on Clinicians' Subjective Impresions

    Proc. of International Conference The 6th International Conference on Soft Computing and Intelligent Systems, The 13th International Symposium on Advanced Intelligent Systems (SCIS-ISIS 2012)  2012.11 

    　More details

  • Computer-aided Diagnosis Scheme for Determining Histological Classification of Breast Masses using Clinical Features and Texture Features,”

    Proc. of the four-international workshop on regional innovation studies  2012.10 

    　More details

  • 乳房超音波画像における構築の乱れの定量化とその病理組織型の分類への応用

    医用画像研究会(MI)  2014.1 

    　More details

  • レベルセット法を用いた乳房超音波画像における腫瘤病変のセグメンテーション法の開発

    電気関係学会東海支部連合大会  2013 

    　More details

  • Improved Differential Diagnosis of Breast Masses on Ultrasonographic Images with CAD Scheme for Determining Histological Classifications

    Radiological Society of North America, 97st Scientific Assembly and Annual Meeting (RSNA2012)  2012.12 

    　More details

  • Usefulness of Computer-aided Diagnosis Scheme for Determining Histological Classifications of Breast Masses on Ultrasonographic Images

    Radiological Society of North America 2012 97st Scientific Assembly and Annual Meeting (RSNA2012)  2012.12 

    　More details

  • Improvement of Computer-aided Diagnosis (CAD) Scheme for Histological Classification of Masses on Ultrasonographic Images by Using Objective Features Based on Clinicians’ Subjective Impressions

    Proc. of Computer Assisted Radiology and Surgery (CARS2012)  2012 

    　More details

  • Computer-aided detection scheme for clustered microcalcifications in telediagnostic system via telemedicine network

    Proc. of Computer Assisted Radiology and Surgery (CARS2012)  2012 

    　More details

  • Computer-aided Diagnosis Scheme for Determining Histological Classifications of Breast Masses Using Objective Features Based on Clinicians’ Subjective Impressions on Ultrasonographic Images

    Radiological Society of North America 2011 96st Scientific Assembly and Annual Meeting (RSNA2011)  2011.12 

    　More details

  • Construction of Telediagnostic System via Telemedicine Network with Computer-aided Diagnosis (CAD) Scheme for Determining Histological Classification of Clustered Microcalcifications in Mammograms

    Radiological Society of North America 2011 96st Scientific Assembly and Annual Meeting (RSNA2011)  2011.12 

    　More details

  • 教育用電子カルテを用いた電子カルテ実習の一考察

    第16回 日本医療情報学会春季学術大会  2012 

    　More details

  • Computer-aided diagnosis scheme based on histological classifications of breast masses on ultrasonographic images

    Proc. of Computer Assisted Radiology and Surgery (CARS2011)  2011.6 

    　More details

  • Introduction of Computer-aided Detection (CAD) Scheme for Clustered Microcalcifications in Mammograms to Telediagnostic System via Telemedicine Network

    Radiological Society of North America 2011 96st Scientific Assembly and Annual Meeting (RSNA2011)  2011.12 

    　More details

  • 乳房超音波画像上の腫瘤病変に対する医師の主観的印象に基づいた画像特徴の定量化法

    日本生体医工学会東海支部大会  2011.10 

    　More details

  • Computerized Quantification Method for Objective Features based on Clinicians’ Subjective Ratings of Breast Masses on Ultrasonographic Images

    Proc. of the Third International Workshop on Regional Innovation Studies  2011.10 

    　More details

  • 同じ位置で撮影された過去と現在の歯科口内法X線画像の同定法

    Mテクノロジー学会大会講演論文集  2011.8 

    　More details

  • Introduction of Computerized Detection Method to Breast Cancer Screening in Mie Prefecture

    Proc. of the Second International Workshop on Regional Innovation Studies  2010.10 

    　More details

  • Computerized identification method for current dental intraoral radiographs based on the arranged previous dental intraoral radiographs

    Proc. of the Second International Workshop on Regional Innovation Studies  2010.10 

    　More details

  • Computerized segmentation method of calcifications within clustered microcalcifications on mammograms using multiresolution analysis

    Proc. of Computer Assisted Radiology and Surgery (CARS2010)  2010.6 

    　More details

  • Computer-Aided diagnosis (CAD) scheme for detection of sentinel lymph nodes on lymphoscintigrams based on symmetry of mapped injection site

    Proc. of Computer Assisted Radiology and Surgery (CARS2010)  2010.6 

    　More details

  • 乳房超音波画像における腫瘤像の病理組織型の分類法

    医用画像研究会(MI)  2011.5 

    　More details

  • Computer-aided Diagnosis Scheme for Determing Histological Classifications of Breast Masses on Ultrasonographic Image

    Radiological Society of North America 2010 95th Scientific Assembly and Annual Metting (RSNA2010)  2010.12 

    　More details

  • 遠隔画像診断ネットワークへのCADシステム導入の可能性

    日本乳癌検診学会誌  2010 

    　More details

  • 超高速回線を用いたマンモグラフィ遠隔画像診断システムの実用化

    日本乳癌検診学会誌  2010 

    　More details

  • 腹部3次元CT画像における肝臓領域内血管の抽出法

    日本生体医工学会東海支部大会  2009.10 

    　More details

  • Computerized Segmentation Method of Calcifications within Clustered Microcalcifications on Mammograms

    Proc. of the First International Workshop on Regional Innovation Studies - Biomedical Engineering  2009.10 

    　More details

  • 形状を維持した個々の石灰化陰影の抽出法

    三重地区計測制御研究講演会  2008.12 

    　More details

  • 差分技術を用いたリンパシンチグラムにおけるセンチネルリンパ節のコンピュータ同定システム

    三重地区計測制御研究講演会  2008.12 

    　More details

  • リンパシンチグラムにおける注射部位の対称性に基づくセンチネルリンパ節の同定法

    三重地区計測制御研究講演会  2008.12 

    　More details

  • 乳房X線画像（MLO画像）を対象とした乳頭領域検出法の開発

    第28回医療情報学連合大会  2008.11 

    　More details

  • Computer-aided Detection Scheme for Sentinel Lymph Nodes

    Proc. of the First International Workshop on Regional Innovation Studies  2009.10 

    　More details

  • Computerized Extraction Method of Hepatic Vessels in Contrasted Abdominal X-ray CT Images

    Proc. of the First International Workshop on Regional Innovation Studies  2009.10 

    　More details

  • 対称性に基づいた差分処理によるセンチネルリンパ節の同定法

    電気関係学会東海支部連合大会  2009.9 

    　More details

  • リンパシンチグラムにおけるセンチネルリンパ節部位のコンピュータ同定支援システムの開発

    第28回医療情報学連合大会  2008.11 

    　More details

  • One Class Support Vector Machine(OC-SVM)を用いたグリオーマ病 理組織像からの非破壊的遺伝子異常評価法

    日本病理学会総会  2019.5 

    　More details

  • 人工知能を用いた病理組織標本の採取臓器の自動分類法

    日本病理学会総会  2019.5 

    　More details

  • 人工知能を用いた病理組織画像における正常組織の自動同定法

    日本病理学会総会  2019.5 

    　More details

  • 深層学習を用いたグリオーマ病理組織像からの遺伝子発現同定法

    医用画像研究会(MI)  2019.1 

    　More details

  • Improvement of frame rate in cine MRI using deep learning

    第18回情報科学技術フォーラム  2019.9 

    　More details

  • Determination of hyper-parameters in convolutional neural network for medical image applications using Bayesian optimization method

    第18回情報科学技術フォーラム  2019.9 

    　More details

  • GANを用いた病理組織画像における異常組織の自動同定法

    第38回日本医用画像工学会大会  2019.7 

    　More details

  • 肺野／肺野以外に異なる畳み込みニューラルネットワーク (CNN)を用いた超低線量CT画像の高画質化

    医用画像研究会(MI)  2019.1 

    　More details

  • Application of Artificial Intelligence to Medical Imaging（招待講演）

    Asia Pacific Society for Computing and Information Technology 2018 Annual Meeting  2018.7 

    　More details

  • 畳み込みニューラルネットワークを用いたシネMRI（Magnetic Resonance Imaging）の高フレームレート化

    第37回日本医用画像工学会大会  2018.7 

    　More details

  • 深層学習による病理組織標本の採取臓器の同定

    医用画像研究会(MI)  2019.1 

    　More details

  • Orthogonalized coupled learning and application for face hallucination

    Proc. of IEEE Mechatronics (MECATRONICS) /17th International Conference on Research and Education in Mechatronics (REM), 2016 11th France-Japan & 9th Europe-Asia Congress  2016.6 

    　More details

  • Optimization Method of Hyper-Parameters in Convolutional Neural Network for Medical Image Application

    104th RSNA Scientific Assembly and Annual Meeting (RSNA2018)  2018.12 

    　More details

  • 冠動脈MRA(Magnetic Resonance Angiography)画像を対象とした超解像技術の高速化

    第17回情報科学技術フォーラム  2018.9 

    　More details

  • 畳み込みニューラルネットワーク(CNN)を用いた病理組織標本の採取臓器の同定

    第17回情報科学技術フォーラム  2018.9 

    　More details

  • 複数シーケンス乳房MRI(Magnetic Resonance Imaging)画像における腫瘤病変の良悪性分類アルゴリズム

    第37回日本医用画像工学会大会  2018.7 

    　More details

  • ベイズ最適化法に基づく冠動脈MRA高解像度化のためのConvolutional Neural Networkの最適化

    第37回日本医用画像工学会大会  2018.7 

    　More details

  • 深層学習を用いた冠動脈MRAの高解像度化

    医用画像情報学会（平成30年度秋季（第182回））  2018.10 

    　More details

  • 超低線量CT高画質化技術の高速化

    医用画像情報学会（平成30年度秋季（第182回））  2018.10 

    　More details

  • 学習型超解像技術による超低線量CT画像の高画質化の検討

    医用画像情報学会（平成30年度秋季（第182回））  2018.10 

    　More details

  • 超低線量Computed Tomography画像高画質化のための畳み込みニューラルネットワーク(CNN)の構築

    第17回情報科学技術フォーラム  2018.9 

    　More details

  • Improving image resolution of whole heart coronary magnetic resonance angiography using 3-dimentional super-resolution technique

    International journal of computer asisted radiology and surgery (CARS2018)  2018.6 

    　More details

  • Development of a classification method for a crack on a pavement surface images using machine learning

    Proc. of SPIE Thirteenth International Conference on Quality Control by Artificial Vision (QCAV2017)  2017.5 

    　More details

  • 2段階の機械学習を用いた細胞の検出・状態分類 ～複数の識別器を用いた細胞の高精度検出

    ViEW2016 ビジョン技術の実利用ワークショップ  2016.12 

    　More details

▼display all

Industrial property rights

  • 画像処理システム、画像処理方法及び画像処理プログラム

    　More details

    Application no：特願2017-5786 

    Announcement no：特開2018-116391 

    researchmap

  • 画像処理システム、画像処理方法及び画像処理プログラム

    　More details

    Application no：特願2016-197815 

    Patent/Registration no：特許第6292682号 

    researchmap

  • 情報予測システム、情報予測方法及び情報予測プログラム

    　More details

    Application no：特願2016-99737 

    Announcement no：特開2016-177829 

    researchmap

  • 情報予測システム、情報予測方法及び情報予測プログラム

    　More details

    Application no：特願2014-231089 

    Announcement no：特開2016-95651 

    researchmap

Awards

  • Award for Certificate of Merit(Optimization Method of Hyper-Parameters in Convolutional Neural Network for Medical Image Application)

    2018.11   Radiological Society of North America 2018 (RSNA2018)  

    　More details

  • Outstanding Research Achievement and Contribution

    2018.7   Asia Pacific Society for Computing and Information Technology  

    　More details

  • 奨励賞

    2017.7   第36回日本医用画像工学会大会奨励賞  

    　More details

  • 優秀賞

    2016.12   精密工学会 外観検査アルゴリズムコンテスト  

    　More details

  • レゾナンスバイオ賞

    2016.12   精密工学会 外観検査アルゴリズムコンテスト  

    　More details

  • 特別賞

    2015.12   精密工学会 外観検査アルゴリズムコンテスト  

    　More details

  • 最優秀賞

    2014.12   精密工学会 外観検査アルゴリズムコンテスト  

    　More details

  • Outstanding Paper Award

    2012.10   Fourth International Workshop on Regional Innovation Studies - Biomedical Engineering -  

    　More details

▼display all

Research Projects

  • Prognostic Prediction of Breast Cancer Using Artificial Intelligence with Radiomics Features

    Grant number：19K20719  2019.4 - 2022.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Early-Career Scientists

    HIZUKURI AKIYOSHI

    　 More details

    Grant amount：\2990000 （ Direct Cost: \2300000 、 Indirect Cost：\690000 ）

    The purpose of this study was to develop a computerized classification method for triple negative breast cancer from breast MRI (magnetic resonance imaging) images using support vector machine (SVM) with radiomics features. We also conducted the prognostic prediction from breast MRI images using a cox proportional hazard model with radiomics features. Our database consisted of T1 weighted images, T2 weighted images, and dynamic MRI images obtained from 66 patients. The classification accuracy, sensitivity, specificity and area under the ROC curve of the proposed method using SVM with radiomics features were 84.8%, 81.3%, 86.0%, and 0.874, respectively.

    researchmap

  • 深層生成モデルによる異常検知を基盤としたコンピュータ支援診断システムの構築

    Grant number：24K15776  2024.4 - 2027.3

    日本学術振興会  科学研究費助成事業  基盤研究(C)

    中山 良平, 檜作 彰良, 木戸 尚治

    　 More details

    Grant amount：\4550000 （ Direct Cost: \3500000 、 Indirect Cost：\1050000 ）

    researchmap

  • 距離学習とデータ拡張による深層学習の汎化能力改善とそのディープフェイク検出応用

    2024.4 - 2025.3

    公益財団法人 電気通信普及財団  研究調査助成

    　 More details

    Authorship：Principal investigator 

    researchmap

  • Computerized classification method for molecular subtypes of gliomas in brain MRI images using deep learning with a limited number of training data

    Grant number：23K11909  2023.4 - 2026.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    　 More details

    Grant amount：\4160000 （ Direct Cost: \3200000 、 Indirect Cost：\960000 ）

    researchmap