Related Experiment Video
Updated: May 25, 2025
09:36
Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin
Published on: March 14, 2018
9.3K
Automatic maxillary sinus segmentation and age estimation model for the northwestern Chinese Han population
Yu-Xin Guo1, Jun-Long Lan1, Wen-Qing Bu1,2
1Key Laboratory of Shaanxi Province for Craniofacial Precision Medicine Research, College of Stomatology, Xi'an Jiaotong University, 98 XiWu Road, Xi'an, 710004, Shaanxi, People's Republic of China.
BMC Oral Health
|February 26, 2025
Summary
Forensic age estimation using maxillary sinus development is now more accurate. A new automated model precisely predicts age, especially in adults, offering a valuable tool for legal and anthropological applications.
Area of Science:
- Forensic Anthropology
- Medical Imaging
- Computer Vision
Background:
- Accurate age estimation is crucial in forensic science.
- Maxillary sinus development provides a reliable indicator for age assessment.
- This study introduces an automated approach for maxillary sinus analysis to aid age determination.
Purpose of the Study:
- To develop an automatic segmentation model for maxillary sinus identification and parameter measurement.
- To create regression and machine learning models for age estimation based on sinus features.
- To evaluate the accuracy and precision of the developed age estimation models.
Main Methods:
- Utilized Cone Beam Computed Tomography (CBCT) images from 292 Han individuals (ages 5-53).
- Developed and validated an automatic segmentation model for the maxillary sinus.
- Extracted sinus dimensions (length, width, height), inter-sinus distance, and volume for analysis.
- Built age estimation models using multiple linear regression and random forest algorithms.
Main Results:
- The automatic segmentation model achieved high accuracy with a Dice Similarity Coefficient (DSC) of 0.873 and Intersection over Union (IoU) of 0.7753.
- The regression model demonstrated strong performance with Mean Absolute Errors (MAE) of 1.45 years (under 18) and 3.51 years (18 and above).
- The models provided relatively precise age predictions, highlighting the utility of maxillary sinus features.
Conclusions:
- The maxillary sinus-based age estimation model shows significant promise, particularly for adult individuals.
- The automated approach offers an efficient and accurate method for forensic age assessment.
- Future enhancements could include integrating additional variables, such as dental dimensions, for improved accuracy.
