Maxillary sinus detection on cone beam computed tomography images using ResNet and Swin Transformer-based UNet.

OBJECTIVES: This study, which uses artificial intelligence-based methods, aims to determine the limits of pathologic conditions and infections related to the maxillary sinus in cone beam computed tomography (CBCT) images to facilitate the work of dentists. METHODS: A new UNet architecture based on a state-of-the-art Swin transformer called Res-Swin-UNet was developed to detect sinus. The encoder part of the proposed network model consists of a pre-trained ResNet architecture, and the decoder part consists of Swin transformer blocks. Swin transformers achieve powerful global context properties with self-attention mechanisms. Because the output of the Swin transformer generates sectorized features, the patch expanding layer was used in this section instead of the traditional upsampling layer. In the last layer of the decoder, sinus diagnosis was conducted through classical convolution and sigmoid function. In experimental works, we used a data set including 298 CBCT images. RESULTS: The Res-Swin-UNet model achieved more success, with a 91.72% F1-score, 99% accuracy, and 84.71% IoU, than outperforming the state-of-the-art models. CONCLUSIONS: The deep learning-based model proposed in the present study can assist dentists in automatically detecting the boundaries of pathologic conditions and infections within the maxillary sinus based on CBCT images.

ResMIBCU-Net: an encoder-decoder network with residual blocks, modified inverted residual block, and bi-directional ConvLSTM for impacted tooth segmentation in panoramic X-ray images.

OBJECTIVE: Impacted tooth is a common problem that can occur at any age, causing tooth decay, root resorption, and pain in the later stages. In recent years, major advances have been made in medical imaging segmentation using deep convolutional neural network-based networks. In this study, we report on the development of an artificial intelligence system for the automatic identification of impacted tooth from panoramic dental X-ray images. METHODS: Among existing networks, in medical imaging segmentation, U-Net architectures are widely implemented. In this article, for dental X-ray image segmentation, blocks and convolutional block structures using inverted residual blocks are upgraded by taking advantage of U-Net's network capacity-intensive connections. At the same time, we propose a method for jumping connections in which bi-directional convolution long short-term memory is used instead of a simple connection. Assessment of the proposed artificial intelligence model performance was evaluated with accuracy, F1-score, intersection over union, and recall. RESULTS: In the proposed method, experimental results are obtained with 99.82% accuracy, 91.59% F1-score, 84.48% intersection over union, and 90.71% recall. CONCLUSION: Our findings show that our artificial intelligence system could help with future diagnostic support in clinical practice.