| Project/Area Number |
18K07693
|
|---|
| 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 | St. Luke's International University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
原 武史 岐阜大学, 工学部, 教授 (10283285)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥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 | 肺癌 / 深層学習 / 胸部X線CT / AutoEncoder / 人工知能 / 特徴抽出 / 胸部CT画像 / 結節状陰影 / 胸部 / オートエンコーダー / 定量解析 / 体積倍加時間 / 定量画像解析 |
|---|
| Outline of Final Research Achievements |
The purpose of this study was to predict the growth of nodules suspected of being lung cancer and to determine whether they would be benign or malignant based on the image features of nodule obtained from chest CT images. Volume Doubling Time (VDT) is often used as a measure of nodule growth rate. Therefore, we aimed to extract image features related to VDT using deep learning. In order to determine whether a nodule was benign or malignant from the image features, we analyzed the features using AutoEncoder, a convolutional neural network, to identify the possibility of differentiating between benign and malignant nodules.
|
| Academic Significance and Societal Importance of the Research Achievements |
肺がんの早期発見は，結節状陰影の検出とその悪性度の予測が重要である．これは医師の高度な経験に基づいて行われる操作であるが，その定量解析を医師の見地から実現し，深層学習を用いて不偏的な画像特徴量を抽出する方法を明らかにした内容である．データベースの拡充が世界的な課題である中，本研究者のみが構築できた世界で唯一といえるデータベースを新たに構築し，定量画像解析が結節状陰影の鑑別に有益であると結論づけた有意義な内容である．
|
