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.

Evaluation of accessory mental foramen and accessory infraorbital foramen with cone-beam computed tomography in Turkish population.

It was aimed to evaluate the frequency of accessory mental foramen (AMF) and accessory infraorbital foramen (AIOF) and analyse the correlation between these two foramina using cone-beam computed tomography (CBCT). The retrospective study reviewed the CBCT images of 1020 patients. The rates of AMF and AIOF were evaluated according to sex and age distributions. Correlations between the localizations of AMF and AIOF in the right and left jaws and the correlations between the occurrences of these foramina were evaluated. In the CBCT images of the 1020 patients, AMFs were detected in 48 patients, among which 14 were in the right half jaw, and 34 were in the left half jaw. AIOFs were detected in 143 patients, among which 65 were in the right half jaw, and 78 were in the left half jaw. Recognising and detecting AMF and AIOF with CBCT is important in terms of preventing complications that may occur in surgical procedures.

The therapeutic effect of bovine colostrum on 5-Fluorouracil-Induced oral mucositis in rats.

OBJECTIVE: The purpose of this study is to determine the effect of bovine colostrum on 5-fluorouracil-induced oral mucositis in rats. MATERIAL AND METHOD: Twenty-four male Wistar albino rats were randomly divided into three groups as the Preoperative, Postoperative and Control groups. All rats were administered 100 mg/kg 5-fluorouracil on the first day and 65 mg/kg 5-FU on the third day intraperitoneally. On the third and fifth days, a superficial incision was created on the mucosa of the right cheek pouch. The oral mucositis protocol was applied in the control group. The preoperative group was given bovine colostrum by gavage from the 1st day of the 5-FU procedure to the 5th day, while the postoperative group was given bovine colostrum by gavage from the 5th day to the 10th day. RESULTS: According to the scoring made in terms of secondary infections, two cases in the control group had moderate infections, and two cases in each of the preoperative and postoperative groups had severe infections. The difference between the control group and the preoperative and postoperative groups was significant (p=0.020). There was no significant difference between the preoperative and postoperative groups. While the degree of wound healing in the postoperative group was higher than the other groups, the difference was not statistically significant. CONCLUSION: No significant effect of bovine colostrum on the healing of oral mucositis was observed. Additional studies are needed to shed light on the pathogenic inflammatory mechanisms in mucositis and the prophylactic and therapeutic roles of antioxidants.