Authors:
Arnela Hadzic
1
;
Barbara Kirnbauer
2
;
Darko Štern
3
and
Martin Urschler
1
Affiliations:
1
Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria
;
2
Department of Dental Medicine and Oral Health, Medical University of Graz, Graz, Austria
;
3
Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria
Keyword(s):
Teeth Localization, Lesion Segmentation, SpatialConfiguration-Net, U-Net, CBCT, Class Imbalance.
Abstract:
The localization of teeth and segmentation of periapical lesions in cone-beam computed tomography (CBCT) images are crucial tasks for clinical diagnosis and treatment planning, which are often time-consuming and require a high level of expertise. However, automating these tasks is challenging due to variations in shape, size, and orientation of lesions, as well as similar topologies among teeth. Moreover, the small volumes occupied by lesions in CBCT images pose a class imbalance problem that needs to be addressed. In this study, we propose a deep learning-based method utilizing two convolutional neural networks: the SpatialConfiguration-Net (SCN) and a modified version of the U-Net. The SCN accurately predicts the coordinates of all teeth present in an image, enabling precise cropping of teeth volumes that are then fed into the U-Net which detects lesions via segmentation. To address class imbalance, we compare the performance of three reweighting loss functions. After evaluation on
144 CBCT images, our method achieves a 97.3% accuracy for teeth localization, along with a promising sensitivity and specificity of 0.97 and 0.88, respectively, for subsequent lesion detection.
(More)