Development of computer-aided detection system for ideopathic normal pressure hydrocephalus on CT images

• Project/Area Number: 18K07655
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 52040:Radiological sciences-related
• Research Institution: Fukushima Medical University (2019-2020); Akita Cerebrospinal and Cardiovascular Center (2018)
• Principal Investigator: Takahashi Noriyuki 福島県立医科大学, 公私立大学の部局等, 教授 (90595076)
• Co-Investigator(Kenkyū-buntansha): 木下 俊文 秋田県立循環器・脳脊髄センター(研究所), 放射線医学研究部, 副病院長 (70314599)
• Project Period (FY): 2018-04-01 – 2021-03-31
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000); Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2018: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: 特発性正常圧水頭症 / コンピュータ支援診断 / DESH / CT / CT画像 / Evans Index / 脳梁角 / computed tomography / 正常圧水頭症

Outline of Final Research Achievements

The early diagnosis of idiopathic normal pressure hydrocephalus (iNPH) considered as a treatable dementia is important. We have developed three follow methods to help diagnose iNPH on CT images: an automated method to compute Evans Index, an automatic measurement of callosal angle on coronal images and an automated estimation of dispropotionately enlarged ssubarachoid space on coronal images.
AS results of performance studies, the correlation coefficient in Evans indexes between the computerized method and the manual measurement was 0.98, the correlation coefficient in callosal angle between the sutomated measurement and the manual measurement was 0.999, and the correlation coefficient in a ratio of CSF space of sylvian fissure to that of vertex sulci between the automated estimation and the manual measurement was 0.999. The resluts suggest that thses methods have the potential to help diagnose iNPH on CT images.

Academic Significance and Societal Importance of the Research Achievements

特発性正常圧水頭症診断のためにCT検査を広く普及させることを目的として，CT検査における特発性正常圧水頭症(iNPH)診断支援システムを開発した．急速に高齢化が進む現在，潜在的に多くのiNPH患者が存在するため，iNPHを早期に正確に診断することが重要になっている．本研究では，iNPHに特有の3つの画像所見を検出するため，自動計測法と自動検出法を開発した．性能評価実験の結果，これらの手法は医師と同等レベルの性能を示した．

Research Products

• [Journal Article] Development of automatic measurement of callosal angle on coronal image in head CT (2018)
  • Author(s): Takahashi N，Kinoshita T，Ohmura T，Matsuyama Eand Toyoshima H
  • Journal Title: Int. Journal of Computer Assisted radiography and surgery Volume: vol. 13
• [Presentation] Computerized detection of Alzheimer’s disease using deep learning in CT scan (2020)
  • Author(s): 高橋 規之，篠原 祐樹，大村 知己，木下 俊文，坂元健太郎
  • Organizer: 第76回日本放射線技術学会総会学術大会
• [Presentation] Development of automated estimation of disproportionately enlarged subarachnoid space in head CT (2019)
  • Author(s): N. Takahashi, T. Kinoshita, Y. Shinohara, T.Ohmura, E. Matsuyama, and H. Toyoshima
  • Organizer: CARS2019 Computer Assisted Radiology and Surgery
  • Int'l Joint Research
• [Presentation] Development of automatic measurement of callosal angle on coronal image in head CT (2018)
  • Author(s): Takahashi N，Kinoshita T，Ohmura T，Matsuyama Eand Toyoshima H
  • Organizer: CARS2018 Computer AssistedRadiology and Surgery
  • Int'l Joint Research