TY - GEN
T1 - Deeptoothduo
T2 - 21st IEEE International Symposium on Biomedical Imaging, ISBI 2024
AU - Hirunchavarod, Natthanich
AU - Phuphatham, Pornnakanok
AU - Sributsayakarn, Natnicha
AU - Prathansap, Narawit
AU - Pornprasertsuk-Damrongsri, Suchaya
AU - Jirarattanasopha, Varangkanar
AU - Intharah, Thanapong
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Age Estimation
KW - Model Understanding
KW - Multi-task Learning
KW - Sex Classification
KW - SHAP
UR - http://www.scopus.com/inward/record.url?scp=85203332346&partnerID=8YFLogxK
U2 - 10.1109/ISBI56570.2024.10635634
DO - 10.1109/ISBI56570.2024.10635634
M3 - Conference contribution
AN - SCOPUS:85203332346
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - IEEE International Symposium on Biomedical Imaging, ISBI 2024 - Conference Proceedings
PB - IEEE Computer Society
Y2 - 27 May 2024 through 30 May 2024
ER -