| Project/Area Number |
17K10455
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Radiation science
|
|---|
| Research Institution | Gihu University of Medical Science |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
原 武史 岐阜大学, 工学部, 教授 (10283285)
|
|---|
| Project Period (FY) |
2017-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 深層学習 / 核医学画像 / ペーパーファントム / ガンマカメラ / 人工知能 / SPECT画像 / 分解能 / シンチグラム / AI / 被ばく軽減 / 定量化 / 高分解能 / 放射線 / 情報工学 |
|---|
| Outline of Final Research Achievements |
Nuclear medicine images have the ability to acquire functional information of organs, but have limitations when extracting detailed structures of organs.In this study, we investigated the improvement of image quality in nuclear medicine images with low spatial resolution using deep learning-based super-resolution techniques and a custom dataset that we created, focusing on the recently highlighted field of research.
The results demonstrated the potential of super-resolution techniques to provide quantitative information for the diagnosis of nuclear medicine examinations and contribute to improving diagnostic capabilities. Additionally, the significance lies in achieving image enhancement solely through software by capturing the multi-faceted process of image generation. This study has identified new possibilities for artificial intelligence technology and laid the foundation for the development of quantitative software in nuclear medicine image analys
|
| Academic Significance and Societal Importance of the Research Achievements |
画像生成プロセスを多角的に捉えることで，ソフトウェアのみで画質が改善できる点に意義があり，本手法で提案したデータセット作成法は，容易に入手可能であり，医用画像データセットの拡充に有用性があった．また，本研究においては，「低解像度コリメータの画像」から「高解像度コリメータの画像」を生成する手段をファントム実験によって明らかにし，空間分解能の低い核医学画像の画質改善が可能になり学術的にも寄与できた．
|
