Development of new prognostic biomarker for uterine sarcoma using FDG-PET texture analysis method
| Project/Area Number |
16K20181
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Obstetrics and gynecology
|
|---|
| Research Institution | University of Fukui |
|---|
Principal Investigator |
YAMAMOTO MAKOTO 福井大学, 学術研究院医学系部門(附属病院部), 助教 (70719054)
|
|---|
| Project Period (FY) |
2016-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 子宮肉腫 / テクスチャー解析 / FDG-PET / テクスチャ解析 / バイオマーカー |
|---|
| Outline of Final Research Achievements |
Uterine sarcoma is a very rare disease with a poor prognosis, and a high rate of lung metastases even after surgical removal. New prognostic tools are essential for effective treatment development. Therefore, we focused on the Radiomics analysis method using a new molecular imaging method. Texture analysis, which is one of the Radiomics analysis methods, is an attempt to quantify information such as roughness and smoothness. In this study, we searched for features useful for uterine sarcoma texture analysis and prognosis prediction in clinical samples. As a result, it was reported in the paper submission that not only the SUVmax, which is the primary feature amount that has been conventionally used to distinguish between uterine sarcoma and uterine fibroids, but also the secondary feature amount has a good discrimination ability.
|
| Academic Significance and Societal Importance of the Research Achievements |
子宮肉腫は外科治療後も高率に転移再発を起こすため、予後不良の疾患であるものの有効な化学療法が限られている。また鑑別疾患として良性の子宮筋腫が挙げられるが、子宮肉腫自体が非常に稀な疾患であるためその鑑別は困難である。本研究では、子宮肉腫と子宮筋腫の鑑別に従来用いられているSUVmaxというパラメータだけでなくテクスチャ解析を用いた二次特徴量も有用であることが分かった。今後は、AIを用いたdeep learningを導入することで、更に精度の高い鑑別や子宮肉腫の予後予測が可能になると考えられる。
|
Report
(5 results)
Research Products
(16 results)
