Kaohsiung Medical University / Prof. Ying-Hui Su

 Pain Points Solved 

• Traditional CBCT image segmentation relies heavily on manual operation, which is time-consuming and prone to subjective errors.
  
• Metal prosthetics and complex tissue structures often cause image artifacts and distortion, reducing diagnostic accuracy.
• Existing automated algorithms show insufficient accuracy in identifying small anatomical structures, such as root canals.
• The proposed technology utilizes a U-net deep learning architecture to effectively overcome metal artifact interference, significantly improving image segmentation accuracy and efficiency.

 Technology Introduction 

With the rapid advancement of artificial intelligence and deep learning technologies, Convolutional Neural Networks (CNNs) have shown great potential in medical image analysis. The U-net model, a type of CNN, is widely used for medical image segmentation due to its efficient feature extraction and reconstruction capabilities. U-net effectively addresses challenges such as metal artifacts and complex tissue structures, significantly improving accuracy and efficiency in image processing. This patent introduces an artificial intelligence algorithm based on U-net deep learning for automatic tissue segmentation in Cone-Beam Computed Tomography (CBCT) scans, generating accurate three-dimensional models. The technology effectively segments bones, teeth, root canals, and prosthetics, with applications in orthodontic diagnosis, orthognathic surgery.

 Application Examples 

• Automatically generates three-dimensional jawbone models for orthodontic diagnosis to assist in occlusal analysis.
  
• Provides high-precision 3D anatomical structures for orthognathic and dental implant surgeries, supporting surgical navigation.
• Applied in root canal therapy and autogenous tooth transplantation to assist clinicians with precise guidance and treatment planning.

 Related Links 

https://www.youtube.com/watch?v=sA08gFDS37g

 Patent Name and Number 

TW 114106467
PCT/CN2025/078519

 Industry-Academia / Tech Transfer Partner 

None

 Honors and Awards  

None

 Technical Contact  

Mr. Hung, Assistant Manager

Kaohsiung Medical University 
Tel: +886 7-3121101 ext. 2360
Email: R121084@kmu.edu.tw