TY - GEN

T1 - Benefits of auxiliary information in deep learning-based teeth segmentation

AU - Dascalu, Tudor Laurentiu

AU - Kuznetsov, Artem

AU - Ibragimov, Bulat

N1 - Publisher Copyright: © 2022 SPIE.

PY - 2022

Y1 - 2022

N2 - This paper evaluates deep learning methods on segmentation of dental arches in panoramic radiographs. Our main aim is to test whether introducing auxiliary learning goals can improve image segmentation. We implement three multi-output networks that detect (1) patient characteristics (e.g missing teeth, no dental artifacts), (2) buccal area, (3) individual teeth, alongside the dental arches. These design choices may restrict the region of interest and improve the internal representation of teeth shapes. The models are based on the modified U-net1 architecture and optimized with Dice loss. Two data sets, of 1500 and 116 samples, collected at different institutions2, 3 were used for training and testing the methods. Additionally, we evaluated the networks against various patient conditions, namely: 32 teeth, ? 32 teeth, dental artifacts, no dental artifacts. The standard U-net architecture reaches the highest Dice scores of 0.932 on the larger data set2 and 0.946 on the group of patients with no missing teeth. The model that outputs probability masks for individual teeth reaches the best Dice score of 0.903 on the smaller data set.3 We observe certain benefits in augmenting teeth segmentation with other information sources, which indicate the potential of this research direction and justifies further investigations.

AB - This paper evaluates deep learning methods on segmentation of dental arches in panoramic radiographs. Our main aim is to test whether introducing auxiliary learning goals can improve image segmentation. We implement three multi-output networks that detect (1) patient characteristics (e.g missing teeth, no dental artifacts), (2) buccal area, (3) individual teeth, alongside the dental arches. These design choices may restrict the region of interest and improve the internal representation of teeth shapes. The models are based on the modified U-net1 architecture and optimized with Dice loss. Two data sets, of 1500 and 116 samples, collected at different institutions2, 3 were used for training and testing the methods. Additionally, we evaluated the networks against various patient conditions, namely: 32 teeth, ? 32 teeth, dental artifacts, no dental artifacts. The standard U-net architecture reaches the highest Dice scores of 0.932 on the larger data set2 and 0.946 on the group of patients with no missing teeth. The model that outputs probability masks for individual teeth reaches the best Dice score of 0.903 on the smaller data set.3 We observe certain benefits in augmenting teeth segmentation with other information sources, which indicate the potential of this research direction and justifies further investigations.

UR - http://www.scopus.com/inward/record.url?scp=85131959728&partnerID=8YFLogxK

U2 - 10.1117/12.2610765

DO - 10.1117/12.2610765

M3 - Article in proceedings

AN - SCOPUS:85131959728

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

SP - 1

EP - 9

BT - Medical Imaging 2022

A2 - Colliot, Olivier

A2 - Isgum, Ivana

A2 - Landman, Bennett A.

A2 - Loew, Murray H.

PB - SPIE

T2 - Medical Imaging 2022: Image Processing

Y2 - 21 March 2021 through 27 March 2021

ER -