| Technical Name | Application of artificial intelligence deep learning ensemble model for detection of thoraciclumbar vertebral fractures on plain lateral radiographs | ||
|---|---|---|---|
| Project Operator | Taipei Veterans General Hospital | ||
| Project Host | 1 張明超 2 盧鴻興 (總計畫主持人: 張德明 院長 ) | ||
| Summary | AI model is consisted of detection, data pre-processingclassification ensemble model. We applied YOLO 3 to detect vertebral body from radiography,used data pre-processing to reduce image noisyenhance contrast, integrated ResNet34, DenseNet121, DenseNet201 into AI mode. Our result reveals the ensemble model has better performance in accuracy, sensitivityspecificity. |
||
| Scientific Breakthrough | AI deep learning ensemble model consisting of ResNet34, DenseNet121DenseNet201 to provide doctors in clinical diagnosis. Regarding the clinical application, doctors upload DICOM image to cloud server of radiology department,wait 45 seconds, the model will automatically report the final results about vertebral body fracture location labelingfracture probability. |
||
| Industrial Applicability | AI deep learning ensemble model can help doctors identify fractured vertebral on plain radiographs. AI model is a good solution to support them make accurateefficient diagnosis, especially in ER, doctors might not always be immediately available for medical consultation. The purpose of using AI model is assist diagnosis, early treatment, reduce waste,precision medicine. |
||
| Keyword | Artificial intelligence deep learning ensemble model (AIDLEM) Vertebral fractures (VFs) X-ray (lateral view) | ||
| Notes | |||
- Contact
- choupohsin@gmail.com
Other people also saw
