TY - GEN
T1 - Combining anatomical constraints and deep learning for 3-D CBCT dental image multi-label segmentation
AU - Huang, Jiayu
AU - Yan, Hao
AU - Li, Jing
AU - Stewart, H. Milton
AU - Setzer, Frank
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/4
Y1 - 2021/4
N2 - Machine learning research on medical images is becoming popular as advanced imaging technologies and equipment in medicine become more and more available. Dental Cone-beam Computed Tomography (Dental CBCT), a frequently-used visualization tool for oral diagnosis, provides valuable three-dimensional information, whose development for automation of Dental CBCT analysis, on the other hand, is relatively preliminary. Generally, there are three important characteristics for analyzing Dental CBCT with noisy labels and limited labeled sample size, and availability of oral medicine knowledge. Based on those characteristics, we develop an image segmentation method for Dental CBCT by integrating domain knowledge into deep U-Net for the 3D segmentation. Finally, depending on whether the knowledge can be decomposed into each pixel, the knowledge constraints are classified into two types: separable and non-separable constraints. All knowledge constraints can be represented as a posterior regularization term and solved in different ways in accordance with related types. For separable constraints, the mean-field theory is employed to solve an optimization problem with the independence assumption about the distributions of output variables on each pixel. For non-separable constraints, we propose to combine the importance sampling based approach and the stochastic optimization algorithm. Finally, we propose to formulate the domain knowledge to the learning stage to improve the accuracy and efficiency of automation of Dental CBCT segmentation.
AB - Machine learning research on medical images is becoming popular as advanced imaging technologies and equipment in medicine become more and more available. Dental Cone-beam Computed Tomography (Dental CBCT), a frequently-used visualization tool for oral diagnosis, provides valuable three-dimensional information, whose development for automation of Dental CBCT analysis, on the other hand, is relatively preliminary. Generally, there are three important characteristics for analyzing Dental CBCT with noisy labels and limited labeled sample size, and availability of oral medicine knowledge. Based on those characteristics, we develop an image segmentation method for Dental CBCT by integrating domain knowledge into deep U-Net for the 3D segmentation. Finally, depending on whether the knowledge can be decomposed into each pixel, the knowledge constraints are classified into two types: separable and non-separable constraints. All knowledge constraints can be represented as a posterior regularization term and solved in different ways in accordance with related types. For separable constraints, the mean-field theory is employed to solve an optimization problem with the independence assumption about the distributions of output variables on each pixel. For non-separable constraints, we propose to combine the importance sampling based approach and the stochastic optimization algorithm. Finally, we propose to formulate the domain knowledge to the learning stage to improve the accuracy and efficiency of automation of Dental CBCT segmentation.
UR - http://www.scopus.com/inward/record.url?scp=85112867205&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112867205&partnerID=8YFLogxK
U2 - 10.1109/ICDE51399.2021.00319
DO - 10.1109/ICDE51399.2021.00319
M3 - Conference contribution
AN - SCOPUS:85112867205
T3 - Proceedings - International Conference on Data Engineering
SP - 2750
EP - 2755
BT - Proceedings - 2021 IEEE 37th International Conference on Data Engineering, ICDE 2021
PB - IEEE Computer Society
T2 - 37th IEEE International Conference on Data Engineering, ICDE 2021
Y2 - 19 April 2021 through 22 April 2021
ER -