Artificial intelligence-based analysis of chest X-ray to predict hemodynamic parameters
| Project/Area Number |
19K17559
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 53020:Cardiology-related
|
|---|
| Research Institution | Mie University |
|---|
Principal Investigator |
Toba Shuhei 三重大学, 医学部附属病院, 助教 (20806111)
|
|---|
| Project Period (FY) |
2019-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2022: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2021: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2020: ¥130,000 (Direct Cost: ¥100,000、Indirect Cost: ¥30,000)
Fiscal Year 2019: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
|
|---|
| Keywords | 人工知能 / 胸部X線写真 / 先天性心疾患 / 血行動態 / 血行動態予測 / 胸部レントゲン写真 / 基盤モデル / 転移学習 / 12誘導心電図 / 小児 / 学校心臓検診 / 胸部X線 / 肺体血流比 / 機械学習 / deep learning |
|---|
| Outline of Research at the Start |
肺体血流比（Qp/Qs）は、先天性心疾患を有する患者における治療方針の決定や手術適応の判断に重要な指標であるが、その正確な測定にはカテーテル検査を必要とするため、測定における侵襲が大きい。本研究では、近年飛躍的に精度が向上している機械学習（いわゆる人工知能、AI）による画像認識技術を用いて、肺体血流比を胸部X線写真から正確に予測する方法を開発する。さらに同手法を他の様々な血行動態指標に応用し、より低侵襲で迅速、簡便な血行動態指標の検査法を開発する。
|
| Outline of Final Research Achievements |
We developed artificial intelligence to predict pulmonary to systemic flow ratio, an important hemodynamic index for patients with congenital heart disease, from chest radiographs, and applied for a patent. In addition, we have developed an artificial intelligence to predict hemodynamics from chest radiographs in the field of adult cardiology, and an artificial intelligence that automatically classifies pediatric 12-lead electrocardiograms. The results were presented in a journal and at national and international conferences.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は、人工知能により胸部X線写真から血行動態（カテーテル検査結果）を予測できることを世界で初めて示し、それが小児・成人を問わず様々な血行動態指標に応用可能であることを示した。より低侵襲かつ簡便な胸部X線写真から血行動態を正確に予測できれば、小児・成人循環器診療において、正確な血行動態評価を頻回に行うことができるようになり、より優れた医療の実現につながる。
|
Report
(5 results)
Research Products
(19 results)
-
-
-
[Journal Article] Prediction of Pulmonary to Systemic Flow Ratio in Patients With Congenital Heart Disease Using Deep Learning-Based Analysis of Chest Radiographs2020
Author(s)
Shuhei Toba, MD; Yoshihide Mitani, MD, PhD; Noriko Yodoya, MD; Hiroyuki Ohashi, MD; Hirofumi Sawada, MD, PhD; Hidetoshi Hayakawa,MD, PhD; Masahiro Hirayama, MD, PhD; Ayano Futsuki, MD; Naoki Yamamoto, MD; Hisato Ito,MD, PhD; Takeshi Konuma, MD, PhD; Hideto Shimpo,MD, PhD; Motoshi Takao, MD, PhD
-
Journal Title
JAMA Cardiology
Volume: -
Issue: 4
Pages: 449-457
DOI
Related Report
Peer Reviewed / Open Access
-
[Presentation] Perioperative Changes of Pulmonary to Systemic Flow Ratio Predicted by Deep Learning-Based Analysis of Chest Radiographs in Patients with Atrial Septal Defect2023
Author(s)
Yusuke Sugitani, Shuhei Toba, Keishin Hattori, Umezu Kentaro, Yoshihide Mitani, Hirofumi Sawada, Hiroyuki Ohashi, Noriko Yodoya, Kazunobu Ohya, Naoki Tsuboya, Hisato Itoh, Yu Shomura, Masahiro Hirayama, Motoshi Takao
Organizer
第87回日本循環器学会学術集会
Related Report
-
-
-
-
-
-
-
-
-
-
[Presentation] Quantitative Analysis Of Chest X-ray Using Deep Learning To Predict Pulmonary To Systemic Flow Ratio In Patients With Congenital Heart Disease2019
Author(s)
Shuhei Toba, Yoshihide Mitani, Noriko Yodoya, Hiroyuki Ohashi, Hirofumi Sawada, Hidetoshi Hayakawa, Masahiro Hirayama, Ayano Fusuki, Naoki Yamamoto, Hisato Ito, Takeshi Konuma, Hideto Shimpo, Motoshi Takao
Organizer
American Heart Association Scientific Sessions 2019
Related Report
Int'l Joint Research
-
-
-
-
-
