An Approach for Efficient Detection of Cephalometric Landmarks

Lateral Cephalometric Landmark Annotation Using Histogram Oriented Gradients Extracted from Region of Interest Patches

Introduction

Two-dimensional cephalometric image analysis plays a crucial role in orthodontic diagnosis and treatment planning. While deep learning-based algorithms have emerged to automate the laborious task of anatomical landmark annotation, their effectiveness is hampered by the challenges of acquiring and labelling clinical data. In this study, we propose a model that leverages conventional machine learning techniques to enhance the accuracy of landmark detection using limited dataset.

Materials and methods

Our methodology involves coarse localization through region of interest (ROI) extraction and fine localization utilizing histogram-oriented gradient (HOG) feature. The image patch containing landmark pixels is classified using the light gradient boosting machine (LGBM) algorithm. To evaluate our model's performance, we conducted rigorous tests on the ISBI Cephalometric dataset and Dental Cepha dataset, aiming to achieve accuracy within a 2 mm radial precision range. We also employed cross-validation to assess our approach, providing a robust evaluation.

Results

Our model's performance on the ISBI Cephalometric dataset showed an accuracy rate of 77.11% within the desired 2 mm radial precision range. The cross-validation results further confirmed the effectiveness of our approach, yielding a mean accuracy of 78.17%. Additionally, we applied our model to the Dental Cepha dataset, where we achieved a remarkable landmark detection accuracy of 84%.

Conclusion

The results demonstrate that traditional machine learning techniques can be effective for accurate landmark detection in cephalometric images, even with limited data. Our findings highlight the potential of these techniques for clinical applications, where large datasets of labelled images may not be available.

Use of automated learning techniques for predicting mandibular morphology in skeletal class I, II and III

BACKGROUND

The prediction of the mandibular bone morphology in facial reconstruction for forensic purposes is usually performed considering a straight profile corresponding to skeletal class I, with application of linear and parametric analysis which limit the search for relationships between mandibular and craniomaxillary variables.

OBJECTIVE

To predict the mandibular morphology through craniomaxillary variables on lateral radiographs in patients with skeletal class I, II and III, using automated learning techniques, such as Artificial Neural Networks and Support Vector Regression.

MATERIALS AND METHODS

229 standardized lateral radiographs from Colombian patients of both sexes aged 18-25 years were collected. Coordinates of craniofacial landmarks were used to create mandibular and craniomaxillary variables. Mandibular measurements were selected to be predicted from 5 sets of craniomaxillary variables or input characteristics by using automated learning techniques, and they were evaluated through a correlation coefficient by a ridge regression between the real value and the predicted value.

RESULTS

Coefficients from 0.84 until 0.99 were obtained with Artificial Neural Networks in the 17 mandibular measures, and two coefficients above 0.7 were obtained with the Support Vector Regression.

CONCLUSION

The craniomaxillary variables used, showed a high predictability ability of the selected mandibular variables, this may be the key to facial reconstruction from specific craniomaxillary measures in the three skeletal classifications.