Quantification of craniofacial growth by machine learning
| Project/Area Number |
18K19605
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 56:Surgery related to the biological and sensory functions and related fields
|
|---|
| Research Institution | Tokyo Medical and Dental University |
|---|
Principal Investigator |
Sachiko Iseki 東京医科歯科大学, 大学院医歯学総合研究科, 教授 (80251544)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
武智 正樹 東京医科歯科大学, 大学院医歯学総合研究科, 講師 (10455355)
塗 隆志 大阪医科大学, 医学部, 准教授 (40445995)
二宮 洋一郎 国立情報学研究所, 大学共同利用機関等の部局等, 特任研究員 (90237777)
上田 晃一 大阪医科大学, 医学部, 教授 (90257858)
|
|---|
| Project Period (FY) |
2018-06-29 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000)
Fiscal Year 2020: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2019: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2018: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 頭蓋 / 成長 / 機械学習 / 定量化 / 頭蓋冠 / 形態 / 頭蓋縫合早期癒合症 / 幾何学的形態解析法 / X線microCT / 骨格形態 / X線μCT画像 |
|---|
| Outline of Final Research Achievements |
The diagnosis of congenital anomalies on craniofacial region is usually evaluated by doctors subjectively or based on their experience. However, the objective method to evaluate the phenotypes has been required for diagnoses. In this study, we investigated the morphological change of the skull on 3 mouse craniosynostosis models of Saethre-Chotzen syndrome, Aperts syndrome and Crouzon syndrome after weaning period by geometric morphometric approach using micro-computed tomography images by paying attention to the shape change. Saethre-Chotzen syndrome mice showed similar morphological change to WT mice. Apert syndrome and Crouzon syndrome mice showed different growth pattern. Both of them showed impaired growth in anterior-downwards extension of facial area while calvarial flattening was observed. The common morphological feature among 3 mouse models base on coronal suture fusion was not detected by quantitatively.
|
| Academic Significance and Societal Importance of the Research Achievements |
先天異常はその60%以上が原因不明であることから、診断について、定性的な表現型を診断する者の経験や裁量に頼ることが多い。よって、表現型を客観的に認識する必要がある。本研究では、遺伝的背景がより均一であるマウスを用いて、頭蓋に先天異常を示すモデルマウスを複数用いて、生後の頭蓋形態の成長をμCT画像を機械学習させ、パターン化が得られることを示した。将来的には形態の変化によるより正確な診断や適正な治療計画の決定や予後の予測につなげる可能性がある。
|
Report
(4 results)
Research Products
(5 results)
