2022 Fiscal Year Final Research Report
Development of a noninvasive monitoring intracranial pressure by deep learning methods used the external auditory canal pressure pulse information
Project/Area Number |
18K08940
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 56010:Neurosurgery-related
|
Research Institution | Shinshu University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
本郷 一博 信州大学, 医学部附属病院, 特任教授 (00135154)
後藤 哲哉 信州大学, 医学部, 特任准教授 (30362130)
|
Project Period (FY) |
2018-04-01 – 2023-03-31
|
Keywords | 頭蓋内圧 / 外耳道内圧脈波 / 深層学習 / 頭蓋内自然共振周波数 / 非侵襲的頭蓋内圧推定法 / パワースペクトル / 微分法によるピーク定量化 / 回帰木モデル |
Outline of Final Research Achievements |
We found that the intracranial natural resonance frequency (NRF) depended only on the intracranial pressure (ICP) and that the relationship between the ICP and the NRF in the brain was able to be calculated using a quadratic function (ICP = 0.0329NRF*NRF + 0.0842NRF), with an excellent correlation (R2 = 0.9952). Therefore,the individual NRF depends only on the ICP value.Deep learning is effective for countermeasures against artifacts other than the extra-auditory canal pressure waveform (EACPW). These results confirmed that the predicted response using a regression tree model was the most stable and could be applied to new clinical data.
|
Free Research Field |
脳神経外科学関連
|
Academic Significance and Societal Importance of the Research Achievements |
学術的意義は、頭蓋内の直流成分であるICP値と交流脈波信号EACPに含まれるNRF値の関係を解明したことである。 社会的意義は、深層学習法がEACP信号以外の雑音対策に有効であり、NRFを推定するにも回帰木モデルが新規データにも有効であることから、緊急医療現場でも精度よくICP値が類推できる点である。
|