| Project/Area Number |
18K15573
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 52040:Radiological sciences-related
|
|---|
| Research Institution | National Cancer Center Japan |
|---|
Principal Investigator |
Kuno Hirofumi 国立研究開発法人国立がん研究センター, 東病院, 医長 (50544475)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 頭頸部癌 / テクスチャ解析 / Radiomics / CT / MRI / 画像診断 / dual energy CT / Dual energy CT |
|---|
| Outline of Final Research Achievements |
This study aimed to explore texture features practical for qualitative diagnosis and prediction of treatment efficacy of head and neck cancer using texture analysis, establish a diagnostic method, and build a model for clinical application. The results suggest that CT texture analysis may be helpful in the diagnosis of lymph node metastasis in head and neck cancer. Texture analysis using virtual monochromatic X-ray images of dual-energy CT may also be beneficial in evaluating benign and malignant thyroid nodules. MRI was a more promising imaging method than CT for building a model to predict postoperative recurrence and prognosis in surgical cases of locally advanced tongue cancer. In summary, texture/radiomics analysis may be helpful as additional noninvasive information for qualitative diagnosis and prediction of treatment efficacy in head and neck cancer. However, there are still issues with its clinical application.
|
| Academic Significance and Societal Importance of the Research Achievements |
頭頸部領域は，発声や嚥下といった生命活動の質に重要な役割を果たしており，頭頸部癌の治療方法の選択やその効果は患者のQOLに直結する．近年では，頭頸部癌に対して外科的治療や放射線治療だけでなく，薬物療法を組み合わせた集学的治療が行われ，個別化治療に向けた治療法の開発が進んでいる．テクスチャ解析・Radiomics解析は，画像の空間パターンを数値化し画像分類を行う手法で，近年は機械学習を用いたモデル構築により，臨床応用に向けた研究がすすんでいる．多様化する治療法それぞれに対して画像による非侵襲的な予後予測や治療効果予測方法があれば，適切な治療方針決定と過度な治療の抑制に寄与すると考えられる．
|
