LCAT-Net: Lightweight Context-Aware Deep Learning Approach for Teeth Segmentation in Panoramic X-rays

Teeth segmentation is a crucial and fundamental player for doctors in diagnosis and treatment planning in dentistry. Due to the blurred interdental boundaries, variations in noise, and the complexities arising from the orientation and overlapping of dental structures within oral images, the segmentation process becomes extremely challenging and time-consuming. Nowadays, computational tools have been introduced as promising strategies for automating teeth segmentation. As one of them, this paper presents a novel architecture called LCAT-Net, designed to address these challenges and improve teeth segmentation in panoramic X-rays. The proposed architecture incorporates several components to address the above challenges. Firstly, it leverages the main components of the Half-UNet for lightweight feature extraction, starting from ghost modules, unified channel numbers, and full-scale feature fusion. Secondly, to give our model the ability to focus on critical regions for improved differentiation in complex dental structures, a convolutional block attention module (CBAM) is integrated into the network. Thirdly, the architecture incorporates a novel multi-scale context fusion (MCF) module, our proposed MCF module extracts multi-scale spatial information through a spatial context fusion (SCF) block, followed by a CBAM block that learns to balance channel-wise features. The network uses a Dense skip connection module (DSM) to reduce the semantic gap. Experiments on three dental panoramic X-ray image datasets of Children, Adults, and Combined (Children and Adults) consisting of 193, 1776, and 1969 X-rays show that our model outperformed the SOTA models in teeth segmentation, with a high mean Dice-scores of 0.9235, 0.9444, 0.9405, respectively. While requiring significantly fewer parameters and floating-point operations (FLOPs) than existing methods.