Kanwal Mehreen, Ur Rehman Muhammad Mutti, Farooq Muhammad Umar, Chae Dong-Kyu
DeepChain AI&IT Technologies, Islamabad 45570, Pakistan.
Department of Computer and Software Engineering, National University of Science and Technology, Islamabad 43701, Pakistan.
Bioengineering (Basel). 2023 Jul 17;10(7):843. doi: 10.3390/bioengineering10070843.
Teeth segmentation plays a pivotal role in dentistry by facilitating accurate diagnoses and aiding the development of effective treatment plans. While traditional methods have primarily focused on teeth segmentation, they often fail to consider the broader oral tissue context. This paper proposes a panoptic-segmentation-based method that combines the results of instance segmentation with semantic segmentation of the background. Particularly, we introduce a novel architecture for instance teeth segmentation that leverages a dual-path transformer-based network, integrated with a panoptic quality (PQ) loss function. The model directly predicts masks and their corresponding classes, with the PQ loss function streamlining the training process. Our proposed architecture features a dual-path transformer block that facilitates bi-directional communication between the pixel path CNN and the memory path. It also contains a stacked decoder block that aggregates multi-scale features across different decoding resolutions. The transformer block integrates pixel-to-memory feedback attention, pixel-to-pixel self-attention, and memory-to-pixel and memory-to-memory self-attention mechanisms. The output heads process features to predict mask classes, while the final mask is obtained by multiplying memory path and pixel path features. When applied to the UFBA-UESC Dental Image dataset, our model exhibits a substantial improvement in segmentation performance, surpassing existing state-of-the-art techniques in terms of performance and robustness. Our research signifies an essential step forward in teeth segmentation and contributes to a deeper understanding of oral structures.
牙齿分割在牙科领域起着关键作用，有助于进行准确诊断并辅助制定有效的治疗方案。虽然传统方法主要专注于牙齿分割，但它们往往未能考虑更广泛的口腔组织背景。本文提出了一种基于全景分割的方法，该方法将实例分割结果与背景语义分割相结合。具体而言，我们引入了一种新颖的实例牙齿分割架构，该架构利用基于双路径变换器的网络，并集成了全景质量（PQ）损失函数。该模型直接预测掩码及其相应类别，PQ损失函数简化了训练过程。我们提出的架构具有一个双路径变换器模块，该模块促进像素路径卷积神经网络（CNN）与记忆路径之间的双向通信。它还包含一个堆叠解码器模块，该模块在不同的解码分辨率上聚合多尺度特征。变换器模块集成了像素到记忆反馈注意力、像素到像素自注意力以及记忆到像素和记忆到记忆自注意力机制。输出头处理特征以预测掩码类别，而最终掩码通过将记忆路径和像素路径特征相乘获得。当应用于UFBA - UESC牙科图像数据集时，我们的模型在分割性能方面表现出显著提升，在性能和鲁棒性方面超过了现有的最先进技术。我们的研究标志着牙齿分割向前迈出了重要一步，并有助于更深入地理解口腔结构。
