• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Radiation dose reduction in medical imaging exams by means of deep-learning-based virtual imaging technology

Research Project

Project/Area Number 18H02761
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 52040:Radiological sciences-related
Research InstitutionTokyo Institute of Technology

Principal Investigator

鈴木 賢治  東京工業大学, 科学技術創成研究院, 教授 (00295578)

Co-Investigator(Kenkyū-buntansha) 粟井 和夫  広島大学, 医系科学研究科(医), 教授 (30294573)
小尾 高史  東京工業大学, 科学技術創成研究院, 准教授 (40280995)
Project Period (FY) 2018-04-01 – 2022-03-31
Project Status Granted (Fiscal Year 2021)
Budget Amount *help
¥17,290,000 (Direct Cost: ¥13,300,000、Indirect Cost: ¥3,990,000)
Fiscal Year 2021: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2020: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2019: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2018: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Keywords機械学習 / CT / 被曝低減 / 深層学習 / 雑音除去
Outline of Annual Research Achievements

1)3次元胸部ファントムによる被曝低減技術の性能検証
昨年度は、2次元の深層学習(ディープラーニング)モデルを3次元に拡張し、臨床Computed Tomography (CT)で得られる3次元データを扱えるモデルにした。同時に、演算量削減手法の開発により、1回のCT検査のデータを高速に処理できるようにした。本年度は、精巧な胸部ファントム(京都科学社製)のCT像を、最低線量から最高線量まで(0.05-35 mSv)変化させて撮像した。次に、超低線量CT像(0.05, 0.1, 0.2 mSv)を入力画像、それに対応する最高線量CT像(35 mSv)を教師画像とし、3次元の深層学習モデルを学習した3次元の深層学習モデルは、3次元のカーネルを有し、カーネル内の3次元画素情報をニューラルネット回帰モデルの入力とする。入力は超低線量CTの3次元局所領域(カーネルと一致)の画素値、出力はそれに対応する高線量CT中の1画素の推定値である。学習は、教師画素と出力画素の二乗誤差が小さくなるよう、ニューラルネットの層間の重み係数を調整することにより行われた。すなわち、出力画像が教師画像として使われた高線量CT画像に近くなるように、学習が進んだ。学習後の深層学習モデルの性能を評価するため、学習後のモデルの出力画像(仮想高線量CT像)と本物の高線量CT像の画質を定量的に比較し、線量低減率を算出した。仮想高線量CT像と本物のCT像の画質の関係を調べることにより、本手法で低減できる被曝線量を定量的に明らかにした。以上のように、本年度は、3次元胸部ファントムを用いて、3次元深層学習モデルによる被曝低減技術の性能検証を行った。

Current Status of Research Progress
Current Status of Research Progress

2: Research has progressed on the whole more than it was originally planned.

Reason

研究計画にて、計画したように、3次元胸部ファントムによる実験データを取得、3次元深層学習モデルによる被曝低減技術の性能を検証した。以上のように、本研究は、おおむね計画通りに進捗している。

Strategy for Future Research Activity

当初の研究計画に沿って、がん検診で得られた臨床CT像を取得・収集し、データベース化する。取得したデータを用いて深層学習モデルを学習し、機能・性能の評価を行う。臨床CT像のデータは、本研究の共同研究機関である、広島大学病院で行う。本病院では、CTによる肺がん検診において、被曝低減手法評価のためのデータ収集が行われてきた。これらの症例から肺腫瘍患者(“充実性結節”と検出が難しく淡い“すりガラス陰影“)を後ろ向き(レトロスペクティブ・スタディ)に選択し、手法の開発、検証、評価に用いることで、本手法で低減できる線量を定量的に明らかにする。

Report

(2 results)
  • 2019 Annual Research Report
  • 2018 Annual Research Report

Research Products

(51 results)

All 2020 2019 2018 Other

All Int'l Joint Research (2 results) Journal Article (6 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results) Presentation (38 results) (of which Int'l Joint Research: 22 results,  Invited: 23 results) Book (5 results)

  • [Int'l Joint Research] Illinois Institute of Technology(米国)

    • Related Report
      2019 Annual Research Report
  • [Int'l Joint Research] Illinois Institute of Technology/University of Chicago(米国)

    • Related Report
      2018 Annual Research Report
  • [Journal Article] 医用画像システム2020

    • Author(s)
      鈴木賢治
    • Journal Title

      JMAI Letter

      Volume: 2 Pages: 53-54

    • Related Report
      2019 Annual Research Report
  • [Journal Article] Separation of bones from soft tissue in chest radiographs: Anatomy‐specific orientation‐frequency‐specific deep neural network convolution2019

    • Author(s)
      Zarshenas Amin、Liu Junchi、Forti Paul、Suzuki Kenji
    • Journal Title

      Medical Physics

      Volume: 46 Pages: 2232-2242

    • DOI

      10.1002/mp.13468

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] 大腸CTにおけるAI支援画像診断2019

    • Author(s)
      鈴木賢治
    • Journal Title

      月刊インナービジョン

      Volume: 34 Pages: 47-50

    • Related Report
      2018 Annual Research Report
  • [Journal Article] 人工知能(AI)最新動向 ー 画像処理2019

    • Author(s)
      鈴木賢治
    • Journal Title

      月刊インナービジョン

      Volume: 34 Pages: 35-36

    • Related Report
      2018 Annual Research Report
  • [Journal Article] 画像診断領域における深層学習の最先端技術とAI支援画像診断2018

    • Author(s)
      鈴木賢治
    • Journal Title

      Multislice CT 2018 Book (映像情報メディカル増刊号)

      Volume: 50 Pages: 36-46

    • Related Report
      2018 Annual Research Report
  • [Journal Article] ディープラーニングによる画像処理・認識技術の最前線2018

    • Author(s)
      鈴木賢治
    • Journal Title

      月刊インナービジョン

      Volume: 33 Pages: 30-35

    • Related Report
      2018 Annual Research Report
  • [Presentation] Neural Network Convolution (NNC) Deep Learning for Radiation Dose Reduction in Digital Breast Tomosynthesis (DBT)2020

    • Author(s)
      Y. Onai, Z. Jin, T. Obi and K. Suzuki
    • Organizer
      Proceedings of Annual Meeting of Research Center for Biomedical Engineering 2019
    • Related Report
      2019 Annual Research Report
  • [Presentation] Medical Imaging & AI - Fundamentals2020

    • Author(s)
      Suzuki K.
    • Organizer
      46th Winter School of Optical Society of Japan
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] AI in Medical Image Processing and Diagnosis of Chest2020

    • Author(s)
      Suzuki K.
    • Organizer
      The 12th Annual Meeting of Japanese Society of Pulmonary Functional Imaging
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] Cutting-edge and Translational Research in Medical Image Processing with Deep Learning and AI-aided Diagnosis2020

    • Author(s)
      Suzuki K.
    • Organizer
      3rd Annual Meeting of Japanese Gastrointestinal Virtual Reality Association
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] Translational Research in Medical Image Processing with Deep Learning and AI-aided Diagnosis2020

    • Author(s)
      Suzuki K.
    • Organizer
      2nd Annual Meeting of Japanese Association for Medical Artificial Intelligence
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] Measuring System Entropy with a Deep Recurrent Neural Network Model2019

    • Author(s)
      Martinez-Garcia M., Zhang Y., Suzuki K., and Zhang Y.
    • Organizer
      Proc. 2019 IEEE 17th International Conference on Industrial Informatics (INDIN)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Development of Deep-learning Segmentation for Breast Cancer in MR Images based on Neural Network Convolution2019

    • Author(s)
      Wang Y., Jin Z., Tokuda Y., Naoi Y., Tomiyama N., and Suzuki K.
    • Organizer
      International Conference on Computing and Pattern Recognition (ICCPR 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Neural Network Convolution Deep Learning for Semantic Segmentation of Breast Tumor in MRI2019

    • Author(s)
      Wang Y., Jin Z., Tokuda Y., Naoi Y., Tomiyama N., Suzuki K.
    • Organizer
      Proc. of 4th International Symposium on Biomedical Engineering (ISBE2019)
    • Related Report
      2019 Annual Research Report
  • [Presentation] Radiation dose reduction in chest CT at a micro-dose (mD) level by noise simulation and noise-specific anatomic neural network convolution (NNC) deep-learning (DL) with K-means clustering2019

    • Author(s)
      Zhao Y., Zarshenas A., Higaki T., Awai K., and Suzuki K.
    • Organizer
      Program of Scientific Assembly and Annual Meeting of Radiological Society of North America (RSNA)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] AI Doctor and Smart Medical Imaging with Deep Learning2019

    • Author(s)
      Suzuki K.
    • Organizer
      2019 3rd International Conference on Artificial Intelligence, Automation and Control Technologies (AIACT 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Virtual Dual-Energy Chest Imaging2019

    • Author(s)
      Suzuki K.
    • Organizer
      2019 AAPM Summer School - Practical Medical Image Analysis
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Introduction to Machine Learning I - Traditional Methods2019

    • Author(s)
      Suzuki K.
    • Organizer
      2019 AAPM Summer School - Practical Medical Image Analysis
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] 世間の流行に左右されない深層学習所感2019

    • Author(s)
      鈴木賢治
    • Organizer
      第38回日本医用画像工学会大会 (JAMIT 2019)
    • Related Report
      2019 Annual Research Report
    • Invited
  • [Presentation] AI Doctor and Smart Medical Imaging with Deep Learning2019

    • Author(s)
      Suzuki K.
    • Organizer
      2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Deep Learning-based AI in Medical Image Processing and Computer-aided Diagnosis2019

    • Author(s)
      Suzuki K.
    • Organizer
      International Conference on Alzheimer’s Disease & Dementia (Alzheimer 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Smart Medical Image Processing and Diagnostic Aid with Deep-Learning-Driven-AI2019

    • Author(s)
      Suzuki K.
    • Organizer
      1st International Promotion Forum for Super Smart Society
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Deep Learning in Medical Image Processing, Pattern Recognition, and Diagnosis2019

    • Author(s)
      Suzuki K.
    • Organizer
      International Conference on Computing and Pattern Recognition (ICCPR 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Deep Learning-based AI in Medical Image Processing and Computer-aided Diagnosis2019

    • Author(s)
      Suzuki K.
    • Organizer
      2nd International Conference on Medical Imaging and Case Reports (MICR 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Deep Learning for Image Processing, Patten Recognition, and Diagnosis in Medicine2019

    • Author(s)
      Suzuki K.
    • Organizer
      2nd Artificial Intelligence and Cloud Computing Conference (AICCC 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] AI Doctor and Smart Medical Imaging with Deep Learning2019

    • Author(s)
      Kenji Suzuki
    • Organizer
      2019 3rd International Conference on Artificial Intelligence, Automation and Control Technologies (AIACT 2019)
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] Radiation dose reduction in digital breast tomosynthesis (DBT) by means of deep-learning-based supervised image processing.2018

    • Author(s)
      Liu J., Zarshenas A., Wei Z., Yang L., Fajardo L., and Suzuki K.
    • Organizer
      Proc. SPIE Medical Imaging (SPIE MI)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Reduction in training time of a deep learning (DL) model in radiomics analysis of lesions in CT.2018

    • Author(s)
      Makkinejad N., Tajbakhsh N., Zarshenas A., Khokhar A., and Suzuki K.
    • Organizer
      Proc. SPIE Medical Imaging (SPIE MI)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Radiation dose reduction in digital breast tomosynthesis (DBT) by means of neural network convolution (NNC) deep learning.2018

    • Author(s)
      Liu J., Zarshenas A., Qadir S, Yang L., Fajardo L., and Suzuki K.
    • Organizer
      Proc. International Workshop on Breast Imaging (IWBI)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Sequential Neural Network Convolution (NNC) Deep Learning in Radiation Dose Reduction in Digital Breast Tomosynthesis (DBT): Preliminary Results.2018

    • Author(s)
      Liu J., Zarshenas A., Wei Z., Yang L., Fajardo L., and Suzuki K.
    • Organizer
      Proc. International Conference on IEEE Engineering in Medicine & Biology Society (IEEE EMBC)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Deep 3D Anatomy-Specific Neural Network Convolution for Radiation Dose Reduction in Chest CT at a Micro-Dose Level.2018

    • Author(s)
      Zarshenas A., Zhao Y., Liu J., Higaki T., Fukumoto W., Awai K., and Suzuki K.:
    • Organizer
      Proc. International Conference on IEEE Engineering in Medicine & Biology Society (IEEE EMBC),
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Deep Neural Network Convolution for Natural Image Denoising.2018

    • Author(s)
      Zarshenas A., and Suzuki K.
    • Organizer
      IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2018)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Mixture of Deep-Learning Experts for Separation of Bones from Soft Tissue in Chest Radiographs.2018

    • Author(s)
      Zarshenas A., Liu J., Forti P., and Suzuki K.
    • Organizer
      IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2018)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Effect of Simulated Micro-Dose (mD) CT on the Performance of Neural Network Convolution (NNC) Deep-Learning (DL) In Radiation Dose Reduction in Chest CT.2018

    • Author(s)
      Zhao Y., Zarshenas A., Higaki T., Awai K., and Suzuki K.
    • Organizer
      Program of Scientific Assembly and Annual Meeting of Radiological Society of North America (RSNA), 2018
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] “Virtual” High-Dose Technology: Radiation Dose Reduction in Thin-Slice Chest CT at a Micro-Dose (mD) Level by Means of 3D Deep Neural Network Convolution (NNC).2018

    • Author(s)
      Zarshenas A., Zhao Y., Liu J., Higaki T., Awai K., and Suzuki K.
    • Organizer
      Program of Scientific Assembly and Annual Meeting of Radiological Society of North America (RSNA), 2018
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Historical Overview of Machine Learning (ML) and Deep Learning in Medical Image Analysis - What are the Sources of the Power of Deep Learning?2018

    • Author(s)
      Suzuki K., Zarshenas A., Liu J., Zhao Y., and Luo Y.
    • Organizer
      Program of Scientific Assembly and Annual Meeting of Radiological Society of North America (RSNA), 2018
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Deep Learning-based AI in Medical Image Processing and Computer-aided Diagnosis, International Forum on Intelligent Medical Image Analysis2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      Tsinghua University
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] Overview of Deep Learning and Its Advanced Applications in Medical Image Processing, Analysis, and Diagnosis2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      7th International Conference on Informatics, Electronics & Vision (ICIEV) & 2nd International Conference on Imaging, Vision & Pattern Recognition (IVPR)
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] Deep Learning and Its Advanced Applications in Medical Image Processing, Analysis, and Diagnosis2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      3rd Asia-Pacific Conference on Intelligent Robot Systems (ACIRS 2018)
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] Deep Learning in Medical Image Processing, Analysis and Diagnosis,2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      The 2nd International Summer School on Deep Learning (DeepLearn 2018)
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] Deep Learning in Medical Image Processing and Diagnosis,2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      5th International Conference on Computational Science and Technology 2018 (ICCST2018)
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] IEEE SPS winter school program2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      IEEE Signal Processing Society (SPS) Malaysia Chapter
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] Introduction to Deep Learning2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      2018 IEEE SPS Winter School on Big Data and Deep Learning in Healthcare
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] Deep Learning for Image Processing2018

    • Author(s)
      Kenji Suzuki
    • Organizer
      2018 IEEE SPS Winter School on Big Data and Deep Learning in Healthcare
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Book] Machine Learning and Medical Engineering for Cardiovascular Health and Intravascular Imaging and Computer Assisted Stenting2019

    • Author(s)
      Liao H., Balocco S., Wang G., Zhang F., Liu Y., Ding Z., Duong L., Phellan R., Zahnd G., Breininger K., Albarqouni S., Moriconi S., Lee S.-L., Demirci S., Suzuki K., Greenspan H., Wang Q., van Ginneken B., Zhou L.
    • Total Pages
      199
    • Publisher
      Springer International Publishing
    • ISBN
      9783030333270
    • Related Report
      2019 Annual Research Report
  • [Book] Uncertainty for Safe Utilization of Machine Learning in Medical Imaging and Clinical Image-Based Procedures2019

    • Author(s)
      Greenspan H., Tanno R., Erdt M., Arbel T., Baumgartner C., Dalca A., Sudre C.H., Wells III W.M., Drechsler K., Linguraru M.G., Oyarzun Laura C., Shekhar R., Wesarg S., Gonzalez Ballester M. A., Suzuki K., Liao H., Wang Q., van Ginneken B., Zhou L.
    • Total Pages
      184
    • Publisher
      Springer International Publishing
    • ISBN
      9783030326890
    • Related Report
      2019 Annual Research Report
  • [Book] Artificial intelligence in decision support systems for diagnosis in medical imaging2018

    • Author(s)
      Chen, Yisong、Suzuki, Kenji
    • Total Pages
      387
    • Publisher
      Springer
    • ISBN
      9783319688428
    • Related Report
      2018 Annual Research Report
  • [Book] Emerging Developments and Practices in Oncology2018

    • Author(s)
      Xu J., Zarshenas A., Chen Y., and Suzuki K.
    • Total Pages
      305
    • Publisher
      IGI Global
    • ISBN
      9781522530855
    • Related Report
      2018 Annual Research Report
  • [Book] Artificial Intelligence in Decision Support Systems for Diagnosis in Medical Imaging2018

    • Author(s)
      Tajbakhsh N. and Suzuki K.
    • Total Pages
      387
    • Publisher
      Springer-Verlag
    • ISBN
      9783319688435
    • Related Report
      2018 Annual Research Report

URL: 

Published: 2018-04-23   Modified: 2021-12-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi