2023 Fiscal Year Final Research Report
Realization of exhaustive mathematical analysis of micro-anatomical structure for micro computational anatomy
Project/Area Number |
21K19898
|
Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
Allocation Type | Multi-year Fund |
Review Section |
Medium-sized Section 90:Biomedical engineering and related fields
|
Research Institution | Nagoya University |
Principal Investigator |
Mori Kensaku 名古屋大学, 情報学研究科, 教授 (10293664)
|
Co-Investigator(Kenkyū-buntansha) |
小田 昌宏 名古屋大学, 情報連携推進本部, 准教授 (30554810)
中村 彰太 名古屋大学, 医学部附属病院, 講師 (20612849)
|
Project Period (FY) |
2021-07-09 – 2024-03-31
|
Keywords | 微細構造解析 / マイクロ計算解剖 / 機械学習 / 画像処理 / 医用画像処理 / 画像診断支援 |
Outline of Final Research Achievements |
The purpose of this study is to develop image recognition methods for comprehensive anatomical structures aimed at the creation of micro computational anatomy. Our research group has conducted medical image processing research targeting macro anatomical structures. The aim of this work is to develop technology that automatically recognizes anatomical structures necessary for the creation of micro computational anatomy from high-resolution images such as micro-CT. High-resolution micro-CT images were scanned, and methods were developed to automatically extract fine blood vessels, very narrow bronchial structures, sheet-like structures such as membranes and wall structures, and lesions like cancer in micro-CT images. For network structures like blood vessels and bronchi, a method was established to describe their network connection as graph structures and perform topological structural analysis.
|
Free Research Field |
画像処理
|
Academic Significance and Societal Importance of the Research Achievements |
本研究の目的は、マイクロ計算解剖学創成に向けた網羅的解剖構造解析のための画像認識技術の開発である。マイクロ解剖構造認識において重要となる解剖構造を明らかにするための画像認識技術の開発を行う。このような画像認識技術は、機械学習による単なる画像認識のみで解決できるものではなく、トポロジー解析など数多くの数理的な基盤が必要となる。マイクロ計算解剖学創成を画像数理研究的な側面から取り組む点において極めて挑戦的な研究である。
|