A U-Net Approach to Apical Lesion Segmentation on Panoramic Radiographs.

The purpose of the paper was the assessment of the success of an artificial intelligence (AI) algorithm formed on a deep-convolutional neural network (D-CNN) model for the segmentation of apical lesions on dental panoramic radiographs. A total of 470 anonymized panoramic radiographs were used to progress the D-CNN AI model based on the U-Net algorithm (CranioCatch, Eskisehir, Turkey) for the segmentation of apical lesions. The radiographs were obtained from the Radiology Archive of the Department of Oral and Maxillofacial Radiology of the Faculty of Dentistry of Eskisehir Osmangazi University. A U-Net implemented with PyTorch model (version 1.4.0) was used for the segmentation of apical lesions. In the test data set, the AI model segmented 63 periapical lesions on 47 panoramic radiographs. The sensitivity, precision, and F1-score for segmentation of periapical lesions at 70% IoU values were 0.92, 0.84, and 0.88, respectively. AI systems have the potential to overcome clinical problems. AI may facilitate the assessment of periapical pathology based on panoramic radiographs.

Fractal properties of the trabecular pattern of the mandible in chronic renal failure.

OBJECTIVES: The purpose of this study was to evaluate fractal analysis as a tool to quantitatively determine the mandibular trabecular bone changes in patients with chronic renal failure (CRF). METHODS: In the present study, fractal analysis was performed using ImageJ (National Institutes of Health, Bethesda, MD) program with box-counting method over panoramic radiographs of 25 patients (14 females and 11 males) with CRF and 26 healthy individuals (14 females and 12 males) as a control group. The fractal dimension (FD) values of the patients and healthy individuals were compared. In addition, average biochemical parameters [parathyroid hormone (PTH), calcium (Ca), phosphorus (P), product of Ca and P levels (CaxP), alkaline phosphatase (ALP), vitamin D] of the patients with CRF, as measured during the 3 months before the panoramic radiographs, were compared with FD values. RESULTS: According to the results, FD values of the patients with CRF were found to be statistically lower than the control group (p < 0.05). The average PTH levels of the patients with CRF were 416.16 ± 310.3 pg ml(-1); average Ca levels were 8.94 ± 1.2 mg dl(-1); average P levels were 5.76 ± 1.7 mg dl(-1); average CaxP values were 51.12 ± 15.03; average ALP levels were 83.44 ± 36.8 U l(-1); and the average vitamin D values were 19.43 ± 9.7 ng ml(-1). In addition, there was no significant correlation between FD values and the biochemical parameters of the patients, and there was no correlation between age, gender and FD. CONCLUSIONS: The FD values of the patients with CRF were lower than those of the controls. This finding suggests that FD analysis might be a promising simple and cost-effective tool for evaluating trabecular bone structure.