| Project/Area Number |
18K07718
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 52040:Radiological sciences-related
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
浅井 佳央里 九州大学, 大学病院, 助教 (40635471)
松本 圭司 九州大学, 医学研究院, 助教 (40467907)
塩山 善之 九州大学, 医学研究院, 共同研究員 (10323304)
大賀 才路 九州大学, 大学病院, 助教 (90380427)
野元 諭 九州大学, 医学研究院, 准教授 (90258608)
平田 秀成 九州大学, 医学研究院, 共同研究員 (90721267)
本田 浩 九州大学, 大学病院, 教授 (90145433)
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 放射線治療 / 転移性脳腫瘍 / ディープラーニング / 深層学習 |
|---|
| Outline of Final Research Achievements |
Initially, we planed to build a multilayer neural networks model to determine the algorithm for predicting prognosis and deciding the treatment plan using 500 patients with metastatic tumors who underwent radiotherapy at our hospital. However, it was difficult to carry out the plan due to a larger variation in the background of the cases. Therefore, as an alternative study, we constructed an automatic extraction system using deep learning from 50 cases of supervised data for pelvic lymph node regions in radiotherapy for gynecological cancer. Verification using five test cases was conducted to compare and validate the contours obtained using this system with those created by radiooncologists, and a high degree of similarity was obtained with a Dice coefficient of 0.85.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究はニューラルネットワークを用いて骨盤リンパ節領域の輪郭抽出を行うアルゴリズムを構築し、放射線治療医の作成した輪郭と比較し、良好な一致率であり、その有用性を明らかにすることが可能であった。本研究の成果を他部位に応用することで、放射線治療医の仕事量軽減や放射線治療医間の輪郭のばらつきを抑えることが可能となり、放射線治療医の負担軽減や治療の均てん化が可能となる。
|
