Deeptoothduo: Multi-Task Age-Sex Estimation and Understanding Via Panoramic Radiograph
Issued Date
2024-01-01
Resource Type
ISSN
19457928
eISSN
19458452
Scopus ID
2-s2.0-85203332346
Journal Title
Proceedings - International Symposium on Biomedical Imaging
Rights Holder(s)
SCOPUS
Bibliographic Citation
Proceedings - International Symposium on Biomedical Imaging (2024)
Suggested Citation
Hirunchavarod N., Phuphatham P., Sributsayakarn N., Prathansap N., Pornprasertsuk-Damrongsri S., Jirarattanasopha V., Intharah T. Deeptoothduo: Multi-Task Age-Sex Estimation and Understanding Via Panoramic Radiograph. Proceedings - International Symposium on Biomedical Imaging (2024). doi:10.1109/ISBI56570.2024.10635634 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/101196
Title
Deeptoothduo: Multi-Task Age-Sex Estimation and Understanding Via Panoramic Radiograph
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
We proposed DeepToothDuo, a Deep Convolutional Neural Network trained with a multi-task approach to estimate age and sex from a panoramic radiograph. This reduced the number of parameters required when training the model to predict age and sex separately. Moreover, we showed that training model to simultaneously predict age and sex provided better network understanding results from SHAP. Our proposed network could predict sex with 87.38% accuracy and estimate age within 1.96 years error. The model understanding study showed that the network considered anatomical features aligned with existing human dental and anatomical studies.