Development of image biomarker for the diagnosis of lung cancer in PET/CT and pathological images
| Project/Area Number |
17K09070
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Medical Physics and Radiological Technology
|
|---|
| Research Institution | Fujita Health University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
塚本 徹哉 藤田医科大学, 医学部, 教授 (00236861)
今泉 和良 藤田医科大学, 医学部, 教授 (50362257)
外山 宏 藤田医科大学, 医学部, 教授 (90247643)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 人工知能 / 医用画像 / 肺がん / 診断 / PET/CT / 病理画像 / 深層学習 / 鑑別 / 敵対的生成ネットワーク / 自動分類 / 肺癌 / Classification / Deep learning / 医療・福祉 / 画像 |
|---|
| Outline of Final Research Achievements |
Lung cancer has become the leading cause of death and has become a social problem. The purpose of this study was to develop a technology that can diagnose lung diseases with high accuracy using PET/CT images taken by differential diagnosis and microscopic images taken by definitive diagnosis. In this study, we first collected image data of lung disease patients. Then, the image features are calculated from them, and the benign/malignant classification of the lung nodule and the histological classification of the lung cancer are performed based on the calculated image features using a machine learning method. As a result of the evaluation, it was confirmed that the classification accuracy was improved by combining a plurality of images.
|
| Academic Significance and Societal Importance of the Research Achievements |
PET/CT画像のような放射線画像と、病理画像を対象とした深層学習の研究は多数行われているが、それらを組合せた研究は実施例が極めて少ない。本研究は深層学習や統計的手法を駆使した診断支援処理を実現しようとしたものであり、学術的な意義がある。また、画像診断を専門としない主治医にとって，本研究で算出できるようにした画像バイオマーカーは病変部の特徴を把握しやすく，予後判定や治療方針の決定にも活用できる．これらの技術によって肺がんの早期診断や正確な診断が実現する可能性が高く、患者のQOL向上や医療費の削減につながる。
|
Report
(4 results)
Research Products
(39 results)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Automated classification and segmentation of malignant pulmonary cells in the cytological image2018
Author(s)
A.Teramoto, A.Yamada, Y.Kiriyama, T.Tsukamoto, Y.Ke, Z.Ling, RM.Summers, K.Saito, H.Fujita, "Automated classification and segmentation of malignant pulmonary cells in the cytological image," 4th Digit
Organizer
4th Digital Pathology Congres Asia
Related Report
Int'l Joint Research
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
