| Project/Area Number |
18K17184
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 57060:Surgical dentistry-related
|
|---|
| Research Institution | Aichi Gakuin University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2018: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | Deep Learning / シェーグレン症候群 / Deep learning |
|---|
| Outline of Final Research Achievements |
CT images of the parotid gland and ultrasound (US) images of the parotid and submandibular glands of patients with Sjogren's syndrome and healthy subjects were used to validate the diagnostic accuracy of the artificial intelligence (AI). The results showed that the diagnostic accuracy of both CT and US images was higher than that of inexperienced radiologists and comparable to that of experienced radiologists. Therefore, the diagnostic accuracy of CT and US images of Sjogren's syndrome by AI could support radiologists in their diagnosis. We further investigated the accuracy of AI in classifying three types of US images of patients with Sjogren's syndrome, healthy subjects and patients with inflammatory complications due to sialolithiasis, and found that the results were comparable to those of experienced radiologists.
|
| Academic Significance and Societal Importance of the Research Achievements |
シェーグレン症候群は、確定診断のため特殊な検査が必要であることと、進行が緩慢であるため患者自身が自覚するのに時間がかかるため早期発見が困難な病気である。本研究では、CT・超音波検査画像を人工知能で診断させ精度の高い診断性能を示した。従って、シェーグレン症候群のスクリーニングが可能となり早期発見へと繋がることが期待できる。
最新技術である人工知能の精度の検証および患者への応用の可能性があることから、学術的意義および社会的意義は大きいと考えられる。
|
