Deep Learning for Midfacial Fracture Detection in CT Images

被引：2

作者：

Warin, Kritsasith ^{[1
]}

Vicharueang, Sothana ^{[2
]}

Jantana, Patcharapon ^{[2
]}

Limprasert, Wasit ^{[2
,3
]}

Thanathornwong, Bhornsawan ^{[4
]}

Suebnukarn, Siriwan ^{[1
]}

机构：

[1] Thammasat Univ, Fac Dent, Bangkok, Thailand

[2] Storemesh, Thailand Sci Pk, Pathum Thani, Thailand

[3] Thammasat Univ, Coll Interdisciplinary Studies, Bangkok, Thailand

[4] Srinakharinwirot Univ, Fac Dent, Bangkok, Thailand

来源：

MEDINFO 2023 - THE FUTURE IS ACCESSIBLE | 2024年 / 310卷

关键词：

Facial trauma; midfacial fracture; artificial intelligence; deep learning;

D O I：

10.3233/SHTI231262

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This study deploys the deep learning-based object detection algorithms to detect midfacial fractures in computed tomography (CT) images. The object detection models were created using faster R-CNN and RetinaNet from 2,000 CT images. The best detection model, faster R-CNN, yielded an average precision of 0.79 and an area under the curve (AUC) of 0.80. In conclusion, faster R-CNN model has good potential for detecting midfacial fractures in CT images.

引用

页码：1497 / 1498

页数：2

共 3 条

[1] Automated fracture screening using an object detection algorithm on whole-body trauma computed tomography [J].