| Project/Area Number |
17591306
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Radiation science
|
|---|
| Research Institution | University of Occupational & Environmental Health, Scool of Medicine |
|---|
Principal Investigator |
KOROGI Yukunori University of Occupational & Environmental Health, Japan, School of Medicine, Professor, 医学部, 教授 (60195691)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
AOKI Takatoshi University of Occupational & Environmental Health, Japan, Scool of Medicine, Assistant Professor, 医学部, 講師 (40299631)
KAKEDA Shingo University of Occupational & Environmental Health, Japan, Scool of Medicine, ResearchAssistant, 医学部, 助手 (30352313)
|
|---|
| Project Period (FY) |
2005 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥3,500,000 (Direct Cost: ¥3,500,000)
Fiscal Year 2006: ¥800,000 (Direct Cost: ¥800,000)
Fiscal Year 2005: ¥2,700,000 (Direct Cost: ¥2,700,000)
|
|---|
| Keywords | MR angiography / Computer-aided diagnosis (CAD) / Intracranial aneurysm / 脳動脈流 / コンピュータ支援映像診断 / CAD / 読影実験 / ROC曲線 |
|---|
| Research Abstract |
OBJECTIVE. To determine whether the use of a computer-aided diagnosis (CAD) system can shorten the reading time while maintaining a diagnostic performance of radiologists in the detection of intracranial aneurysms on MR angiograms.
MATERIALS AND METHODS. Fifty maximum intensity projection MR angiograms in 50 patients (16 cases with intracranial aneurysms and 34 negative cases) were used for observer performance study. Sixteen radiologists (8 neuroradiologists and 8 less experienced radiologists) participated in observer studies and interpreted the MR angiograms without and with the CAD output images by using an independent test method. The reading time for each observer was recorded in each case. The observers' performance was evaluated by use of receiver operating characteristic (ROC) analysis.
RESULTS. For the less experienced radiologists, the mean reading time per case was reduced significantly by 20.4 sec (34.4%) for the aneurysm cases (from 59.3 sec to 38.9 sec, p < 0.01) and 38.2 sec (48.7%) for the negative cases (from 78.4 sec to 40.2 sec, p <0.01), when CAD output images were available. The observer performance with CAD output images (mean Az = 0.911) was significantly better than that without CAD (mean Az = 0.787) (p = 0.022). For the neuroradiologists, however, both the mean reading time and observer performance was not improved with CAD output.
CONCLUSION. The use of the CAD system can shorten the reading time while improving diagnostic performance for less experienced radiologists.
|
