Hidetoshi Matsuo 研究室

主宰者：Hidetoshi Matsuo

神戸大学

AI 要約（直近 5 年の研究成果）

松尾研究室は、医学画像の解析と診断支援を題材として、機械学習や深層学習の実装と応用に取り組んでいます。胸部X線写真や頭部CTなど多様な画像検査データから、肺がんや脳出血、感染症といった疾患の検出・分類を自動的に行うための人工知能モデルの開発が中心的なテーマです。これらのモデルは限られたデータセットの課題に対応するため、転移学習や生成モデルなど様々な手法を駆使して構築されています。同時に、医療現場での実用化を視野に入れ、複数施設からのデータを用いた外部検証や、放射線技師といった医療職の診断精度向上への貢献を重視しています。また近年は大規模言語モデルやマルチモーダル学習の導入により、画像データとテキスト形式の医療記録を統合した解析へと研究を拡張しており、放射線科レポートの自動構造化やがん分類の自動抽出といった臨床業務の効率化にも取り組んでいます。さらに、スーパーコンピュータを活用した大規模脳画像の並列処理など、計算効率の向上を図りながら、稀少疾患のプログレッション予測やPET/MRIにおける物理的課題への解決も進めています。こうした多角的なアプローチを通じて、医療者の判断を補助し、診断精度と効率の向上をもたらす実践的なAIシステムの構築を目指しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（28 件）

[2026] Artificial intelligence for chest radiography: an overview of techniques, challenges, and future directions
DOI: https://doi.org/10.1038/s44401-026-00087-y
[2026] Performance of Vision-Language Models for Zero-Shot Lung Nodule Detection on Chest Radiographs
DOI: https://doi.org/10.64898/2026.05.31.26354565
[2026] Development and evaluation of a deep learning-assisted diagnostic support system for radiographer preliminary clinical evaluation of intracranial hemorrhage
DOI: https://doi.org/10.7717/peerj.21414
[2026] Zero-TE MRI-based attenuation correction for bone components on chest [18F] FDG PET/MRI: accuracy, repeatability, and external validation of an unsupervised deep learning approach using unpaired PET/CT data
DOI: https://doi.org/10.1007/s12149-026-02213-0
[2025] RadVLM: A Multitask Conversational Vision-Language Model for Radiology
DOI: https://doi.org/10.3929/ethz-c-000792452
[2025] Identification of high-priority radiology reports with unexpected findings using fine-tuned large language models
DOI: https://doi.org/10.1007/s00330-025-12252-2
[2025] Deep Learning-Based Detection of Intracranial Hemorrhages in Postmortem Computed Tomography: Comparative Study of 15 Transfer-Learned Models
DOI: https://doi.org/10.3390/app151910513
[2024] Development and web deployment of prediction model for pulmonary arterial pressure in chronic thromboembolic pulmonary hypertension using machine learning
DOI: https://doi.org/10.1371/journal.pone.0300716
[2024] Fully automatic summarization of radiology reports using natural language processing with large language models
DOI: https://doi.org/10.1016/j.imu.2024.101465
[2024] Exploring Multilingual Large Language Models for Enhanced TNM Classification of Radiology Report in Lung Cancer Staging
DOI: https://doi.org/10.3390/cancers16213621

続きを表示（残り 18 件）

[2024] Automatic Structuring of Radiology Reports of Chest X-Ray Images Using Large Language Model
DOI: https://doi.org/10.1109/compsac61105.2024.00310
[2024] Clinical Impact Of Assessing Plaque Quantification And Local Hemodynamics Of Intermediate Lesions In The Prediction Of Acute Coronary Syndrome
DOI: https://doi.org/10.1016/j.jcct.2024.05.004
[2024] Clinical Impact Of Assessing Plaque Quantification And Local Hemodynamics Of Intermediate Lesions In The Prediction Of Acute Coronary Syndrome
DOI: https://doi.org/10.1016/j.jcct.2024.05.200
[2024] Sex Specific Analysis Of Artificial Intelligence-enabled Quantitative Coronary Plaque And Hemodynamic Analysis In Predicting Acute Coronary Syndrome
DOI: https://doi.org/10.1016/j.jcct.2024.05.036
[2024] [Applications] 11. Automatic Generation of Radiology Reports for Chest X-ray Images
DOI: https://doi.org/10.6009/jjrt.2024-2363
[2023] Zero-shot classification of TNM staging for Japanese radiology report using ChatGPT at RR-TNM subtask of NTCIR-17 MedNLP-SC
DOI: https://doi.org/10.20736/0002001283
[2023] Accelerated preprocessing of large numbers of brain images by parallel computing on supercomputers
DOI: https://doi.org/10.1038/s41598-023-46073-4
[2023] Development of Pericardial Fat Count Images Using a Combination of Three Different Deep-Learning Models: Image Translation Model From Chest Radiograph Image to Projection Image of Three-Dimensional Computed Tomography
DOI: https://doi.org/10.1016/j.acra.2023.09.014
[2023] Computer-aided diagnosis of chest X-ray for COVID-19 diagnosis in external validation study by radiologists with and without deep learning system
DOI: https://doi.org/10.1038/s41598-023-44818-9
[2023] Comparison between pystan and numpyro in Bayesian item response theory: evaluation of agreement of estimated latent parameters and sampling performance
DOI: https://doi.org/10.7717/peerj-cs.1620
[2023] Prognosis prediction of patients with malignant pleural mesothelioma using conditional variational autoencoder on 3D PET images and clinical data
DOI: https://doi.org/10.1002/mp.16694
[2023] Label Distribution Learning for Automatic Cancer Grading of Histopathological Images of Prostate Cancer
DOI: https://doi.org/10.3390/cancers15051535
[2022] Bayesian multidimensional nominal response model for observer study of radiologists
DOI: https://doi.org/10.1007/s11604-022-01366-y
[2022] Unsupervised-learning-based method for chest MRI–CT transformation using structure constrained unsupervised generative attention networks
DOI: https://doi.org/10.1038/s41598-022-14677-x
[2022] Deep learning model for the automatic classification of COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy: a multi-center retrospective study
DOI: https://doi.org/10.1038/s41598-022-11990-3
[2021] Lung Cancer Segmentation With Transfer Learning: Usefulness of a Pretrained Model Constructed From an Artificial Dataset Generated Using a Generative Adversarial Network
DOI: https://doi.org/10.3389/frai.2021.694815
[2021] Deep learning with deep convolutional neural network using FDG-PET/CT for malignant pleural mesothelioma diagnosis
DOI: https://doi.org/10.18632/oncotarget.27979
[2021] Deep learning model for predicting gestational age after the first trimester using fetal MRI
DOI: https://doi.org/10.1007/s00330-021-07915-9

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（28 件）

科研費（0 件）

所属学会・役職（0 件）