研究者詳細 - 岡本　昌士

論文 - 岡本　昌士

分割表示 58 件中 1 - 20 件目／全件表示 >>

Development and Validation of Transformer- and Convolutional Neural Network-Based Deep Learning Models to Predict Curve Progression in Adolescent Idiopathic Scoliosis 査読

Shinji Takahashi, Shota Ichikawa, Kei Watanabe, Haruki Ueda, Hideyuki Arima, Yu Yamato, Takumi Takeuchi, Naobumi Hosogane, Masashi Okamoto, Manami Umezu, Hiroki Oba, Yohan Kondo, Shoji Seki

Journal of Clinical Medicine 14 ( 20 ) 7216 - 7216 2025年10月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：MDPI AG

Background/Objectives: The clinical management of adolescent idiopathic scoliosis (AIS) is hindered by the inability to accurately predict curve progression. Although skeletal maturity and the initial Cobb angle are established predictors of progression, their combined predictive accuracy remains limited. This study aimed to develop a robust and interpretable artificial intelligence (AI) system using deep learning (DL) models to predict the progression of scoliosis using only standing frontal radiographs. Methods: We conducted a multicenter study involving 542 patients with AIS. After excluding 52 borderline progression cases (6–9° progression in the Cobb angle), 294 and 196 patients were assigned to progression (≥10° increase) and non-progression (≤5° increase) groups, respectively, considering a 2-year follow-up. Frontal whole spinal radiographs were preprocessed using histogram equalization and divided into two regions of interest (ROIs) (ROI 1, skull base–femoral head; ROI 2, C7–iliac crest). Six pretrained DL models, including convolutional neural networks (CNNs) and transformer-based models, were trained on the radiograph images. Gradient-weighted class activation mapping (Grad-CAM) was further performed for model interpretation. Results: Ensemble models outperformed individual ones, with the average ensemble model achieving area under the curve (AUC) values of 0.769 for ROI 1 and 0.755 for ROI 2. Grad-CAM revealed that the CNNs tended to focus on the local curve apex, whereas the transformer-based models demonstrated global attention across the spine, ribs, and pelvis. Models trained on ROI 2 performed comparably with respect to those using ROI 1, supporting the feasibility of image standardization without a loss of accuracy. Conclusions: This study establishes the clinical potential of transformer-based DL models for predicting the progression of scoliosis using only plain radiographs. Our multicenter approach, high AUC values, and interpretable architectures support the integration of AI into clinical decision-making for the early treatment of AIS.

DOI： 10.3390/jcm14207216

researchmap

主観型画像解析システムのための実空間内に存在する医療画像を対象とした物体検出モデルの開発；初期検討査読

梅室愛華, 佐藤充, 小倉敏裕, 近藤世範, 岡本昌士

医用画像情報学会雑誌 42 ( 4 ) 2025年9月

Radiomic Fingerprints: Automated Personal Identification in Mass Disasters Using Shape-Based Features of Thoracic Vertebral Bodies on CT 査読

Shota Ichikawa, Yohan Kondo, Masashi Okamoto, Tatsuya Kondo, Naoya Takahashi

Journal of Imaging Informatics in Medicine 2025年6月

深層学習を用いた領域抽出および脊椎パラメータ計測自動化の検討

木俣太一, 岡本昌士, 小林桜子, 近藤達也, 市川翔太, 佐藤充, 近藤世範

医用画像情報学会雑誌 42 ( 1 ) xli - xlii 2025年3月

Development of a Patient-Radiopharmaceutical Matching Verification System for Preventing Misadministration of Radioactive Drugs Using Mixed Reality ―Development of a deep-learning model based on video acquired by a camera mounted on a mixed reality device― 査読

Mitsuru SATO, Hiromitsu HOSHINO, Masataka SHIMIZU, Hiromitsu DAISAKI, Toshihiro OGURA, Shota ICHIKAWA, Tatsuya KONDO, Masashi OKAMOTO

RADIOISOTOPES 74 ( 1 ) 25 - 37 2025年3月

Pilot Study on Using Large Language Models for Educational Resource Development in Japanese Radiological Technologist Exams 査読

Tatsuya Kondo, Masashi Okamoto, Yohan Kondo

Medical Science Educator 2025年1月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Springer Science and Business Media LLC

Abstract

In this study, we explored the potential application of large language models (LLMs) to the development of educational resources for medical licensure exams in non-English-speaking contexts, focusing on the Japanese Radiological Technologist National Exam. We categorized multiple-choice questions into image-based, calculation, and textual types. We generated explanatory texts using Copilot, an LLM integrated with Microsoft Bing, and assessed their quality on a 0–4-point scale. LLMs achieved high performance for textual questions, which demonstrated their strong capability to process specialized content. However, we identified challenges in generating accurate formulas and performing calculations for calculation questions, as well as in interpreting complex medical images in image-based questions. To address these issues, we suggest using LLMs with programming functionalities for calculations and using keyword-based prompts for medical image interpretation. The findings highlight the active role of educators in managing LLM-supported learning environments, particularly by validating outputs and providing supplementary guidance to ensure accuracy. Furthermore, the rapid evolution of LLM technology necessitates continuous adaptation of utilization strategies to align with their advancing capabilities. In this study, we underscored the potential of LLMs to enhance educational practices in non-English-speaking regions, while addressing critical challenges to improve their reliability and utility.

DOI： 10.1007/s40670-024-02251-1

researchmap

その他リンク： https://link.springer.com/article/10.1007/s40670-024-02251-1/fulltext.html

A noncontact operating system using motion sensors for image display to avoid communication errors in gastrointestinal fluoroscopy 査読

Mitsuru SATO, Zen HAYAMA, Chihiro TSUCHIDA, Yohan KONDO, Masashi OKAMOTO, Toshihiro OGURA, Hiromitsu DAISAKI

The Japanese Journal of Ergonomics 2024年12月

Automated Prediction of Thoracic Vertebral Body Diameters from Computed Tomography Scans Using Deep Learning 査読

Shota Ichikawa, Yohan Kondo, Masashi Okamoto, Tatsuya Kondo, Naoya Takahashi

Journal of Health Sciences of Niigata University 21 2024年10月

低線量画像診断装置(EOSイメージングシステム)を用いた骨密度・筋肉量推定の精度検証

末原和樹, 谷懿, 大竹義人, 上村圭亮, 岡本昌士, 徳永邦彦, 政木勇人, 崇風まあぜん, 佐藤嘉伸

日本コンピュータ外科学会誌 26 ( 2 ) 208 - 208 2024年10月

Assessment of spinal alignment in standing position using Biplanar X-ray images and three-dimensional vertebral models 査読

Koichi Kobayashi, Makoto Sakamoto, Keisuke Sasagawa, Masaaki Nakai, Masashi Okamoto, Kazuhiro Hasegawa, Kengo Narita

Porto Biomedical Journal 9 ( 3 ) 2024年5月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Ovid Technologies (Wolters Kluwer Health)

Abstract

We developed two methods for three-dimensional (3D) evaluation of spinal alignment in standing position by image matching between biplanar x-ray images and 3D vertebral models. One used a Slot-Scanning 3D x-ray Imager (sterEOS) to obtain biplanar x-ray images, and the other used a conventional x-ray system and a rotating table. The 3D vertebral model was constructed from the CT scan data. The spatial position of the vertebral model was determined by minimizing the contour difference between the projected image of the model and the biplanar x-ray images. Verification experiments were conducted using a torso phantom. The relative positions of the upper vertebrae to the lowest vertebrae of the cervical, thoracic, and lumbar vertebrae were evaluated. The mean, standard deviation, and mean square error of the relative position were less than 1° and 1 mm in all cases for sterEOS. The maximum mean squared errors of the conventional x-ray system and the rotating table were 0.7° and 0.4 mm for the cervical spine, 1.0° and 1.2 mm for the thoracic spine, and 1.1° and 1.2 mm for the lumbar spine. Therefore, both methods could be useful for evaluating the spinal alignment in standing position.

DOI： 10.1097/j.pbj.0000000000000256

researchmap

Contactless operation system development for radiographic consoles using a motion controller to prevent unknown viruses: proof of concept 査読

Mitsuru Sato, Chihiro Tsuchida, Zen Hayama, Yohan Kondo, Masashi Okamoto, Toshihiro Ogura, Hiromitsu Daisaki

Medical Imaging and Information Sciences 41 ( 1 ) 15 - 21 2024年3月

Development of a Patient–Radiopharmaceutical Matching System Using Smartphone to Prevent Misadministration: Feasibility Study 査読

Mitsuru Sato, Hiromitsu Hoshino, Masataka Shimizu, Hiromitsu Daisaki, Shota Ichikawa, Tatsuya Kondo, Masashi Okamoto

RADIOISOTOPES 73 ( 1 ) 69 - 80 2024年3月

Racial differences in whole‑body sagittal alignment between Asians and Caucasians based on international multicenter data 査読

Jun Ouchida, Hiroaki Nakashima, Tokumi Kanemura, Masashi Okamoto, Shun Hatsushikano, Shiro Imagama, Jean Charles Le Huec, Kazuhiro Hasegawa

European Spine Journal 32 ( 10 ) 3608 - 3615 2023年6月

Improvement of teaching materials for anatomy by use of virtual reality system 査読

Mitsuru Sato, Naoya Takahashi, Masashi Okamoto

The Japan Association of Radiological Technologists 13 2023年3月

Deep learning-based classification of adequate sonographic images for self-diagnosing deep vein thrombosis 査読

Yusuke Nakayama, Mitsuru Sato, Masashi Okamoto, Yohan Kondo, Manami Tamura, Yasuko Minagawa, Mieko Uchiyama, Yosuke Horii

PLOS ONE 18 ( 3 ) e0282747 - e0282747 2023年3月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Public Library of Science (PLoS)

Background

Pulmonary thromboembolism is a serious disease that often occurs in disaster victims evacuated to shelters. Deep vein thrombosis is the most common reason for pulmonary thromboembolism, and early prevention is important. Medical technicians often perform ultrasonography as part of mobile medical screenings of disaster victims but reaching all isolated and scattered shelters is difficult. Therefore, deep vein thrombosis medical screening methods that can be easily performed by anyone are needed. The purpose of this study was to develop a method to automatically identify cross-sectional images suitable for deep vein thrombosis diagnosis so disaster victims can self-assess their risk of deep vein thrombosis.

Methods

Ultrasonographic images of the popliteal vein were acquired in 20 subjects using stationary and portable ultrasound diagnostic equipment. Images were obtained by frame split from video. Images were classified as “Satisfactory,” “Moderately satisfactory,” and “Unsatisfactory” according to the level of popliteal vein visualization. Fine-tuning and classification were performed using ResNet101, a deep learning model.

Results

Acquiring images with portable ultrasound diagnostic equipment resulted in a classification accuracy of 0.76 and an area under the receiver operating characteristic curve of 0.89. Acquiring images with stationary ultrasound diagnostic equipment resulted in a classification accuracy of 0.73 and an area under the receiver operating characteristic curve of 0.88.

Conclusion

A method for automatically identifying appropriate diagnostic cross-sectional ultrasonographic images of the popliteal vein was developed. This elemental technology is sufficiently accurate to automatically self-assess the risk of deep vein thrombosis by disaster victims.

DOI： 10.1371/journal.pone.0282747

researchmap

The age-specific normative values of standing whole-body sagittal alignment parameters in healthy adults: based on international multicenter data 査読

Jun Ouchida, Hiroaki Nakashima, Tokumi Kanemura, Masashi Okamoto, Shun Hatsushikano, Shiro Imagama, Jean Charles Le Huec, Kazuhiro Hasegawa

European Spine Journal 2022年11月

Development of individual identification method using thoracic vertebral features as biometric fingerprints 査読国際誌

Mitsuru Sato, Yohan Kondo, Masashi Okamoto, Naoya Takahashi

Scientific Reports 12 ( 1 ) 16274 - 16274 2022年9月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Springer Science and Business Media LLC

Abstract

Identification of individuals is performed when a corpse is found after a natural disaster, incident, or accident. DNA and dental records are frequently used as biometric fingerprints; however, identification may be difficult in some cases due to decomposition or damage to the corpse. The present study aimed to develop an individual identification method using thoracic vertebral features as a biological fingerprint. In this method, the shortest diameter in height, width, and depth of the thoracic vertebrae in the postmortem image and a control antemortem were recorded and a database was compiled using this information. The Euclidean distance or the modified Hausdorff distance was calculated as the distance between two points on the three-dimensional feature space of these measurement data. The thoracic vertebrae T1-12 were measured and the pair with the smallest distance was considered to be from the same person. The accuracy of this method for identifying individuals was evaluated by matching images of 82 cases from a total of 702 antemortem images and showed a hit ratio of 100%. Therefore, this method may be used to identify individuals with high accuracy.

DOI： 10.1038/s41598-022-20748-w

PubMed

researchmap

その他リンク： https://www.nature.com/articles/s41598-022-20748-w

Development of a computer‑aided quality assurance support system for identifying hand X‑ray image direction using deep convolutional neural network 査読

Mitsuru Sato, Yohan Kondo, Masashi Okamoto

Radiological Physics and Technology 2022年8月

Development of a contactless operation system for radiographic consoles using an eye tracker for severe acute respiratory syndrome coronavirus 2 infection control: a feasibility study 査読

Mitsuru Sato, Mizuki Narita, Naoya Takahashi, Yohan Kondo, Masashi Okamoto, Toshihiro Ogura

ACTA IMEKO 11 ( 2 ) 1 - 8 2022年6月

Implications of the uncertainty of postoperative functional parameters for the preoperative planning of total hip arthroplasty 査読

Maximilian C. M. Fischer, Kunihiko Tokunaga, Masashi Okamoto, Juliana Habor, Klaus Radermacher

Journal of Orthopaedic Research 2022年3月

　前のページ - 次のページ　

<岡本 昌士>

論文 - 岡本 昌士

<岡本　昌士>

論文 - 岡本　昌士