2016 Fiscal Year Final Research Report
Lung cancer screening (LCS) in ultra-low-dose CT (U-LDCT) by means of massive-training artificial neural network (MTANN) image-quality improvement
| Project/Area Number |
26461793
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Radiation science
|
|---|
| Research Institution | Hiroshima University |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
SUZUKI Kenji イリノイ工科大学
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Keywords | 機械学習 |
|---|
| Outline of Final Research Achievements |
We developed a radiation dose reduction technology based on massive-training artificial neural network (MTANN) that learned to convert mDCT images to higher-dose-like CT images; thus term vHDCT technology. Our purpose in this study was to investigate and compare nodule detectability in mDCT with our vHDCT technology and that in low-dose CT (LDCT) in lung cancer screening (LCS).
Detectability of solid nodules in vHDCT obtained with our MTANN technology at an mD level (0.2 mSv) would be comparable to that of LDCT (2.0 mSv); thus 90% dose reduction was achieved.
|
| Free Research Field |
放射線診断
|
