RESUMO
Abstract Dental fillings, frequently used in dentistry to address various dental tissue issues, may pose problems when not aligned with the anatomical contours and physiology of dental and periodontal tissues. Our study aims to detect the prevalence and distribution of normal and overhanging filling restorations using a deep CNN architecture trained through supervised learning, on panoramic radiography images. A total of 10480 fillings and 2491 overhanging fillings were labeled using CranioCatch software from 2473 and 1850 images, respectively. After the data obtaining phase, validation (80%), training 10%), and test-groups (10%) were formed from images for both labelling. The YOLOv5x architecture was used to develop the AI model. The model's performance was assessed through a confusion matrix and sensitivity, precision, and F1 score values of the model were calculated. For filling, sensitivity is 0.95, precision is 0.97, and F1 score is 0.96; for overhanging were determined to be 0.86, 0.89, and 0.87, respectively. The results demonstrate the capacity of the YOLOv5 algorithm to segment dental radiographs efficiently and accurately and demonstrate proficiency in detecting and distinguishing between normal and overhanging filling restorations.
RESUMO
OBJECTIVES: Fabry disease (FD) is a rare disease associated with sphingolipid accumulation. Sphingolipids are components of plasma membranes that are important in podocyte function and accumulate in various glomerular diseases such as focal segmental glomerulosclerosis (FSGS). Both FD and FSGS can cause podocyte damage and are classified as podocytopathies. In this respect, FD and FSGS share the same pathophysiologic pathways. Previous screening studies have shown that a significant proportion of end-stage renal disease (ESRD) patients receiving hemodialysis (HD) have unsuspected FD, and the prevalence of low alpha-galactosidase A (αGLA) enzyme activity in these patients is higher than that in the normal population. We aimed to compare αGLA enzyme activity in patients with biopsy-proven FSGS and ESRD receiving HD. METHODS: The records of 232 patients [62 FSGS (F/M: 33/29); 170 HD (M/F: 93/79)] were evaluated retrospectively. The screening was performed based on the αGLA enzyme activity on a dried blood spot, with the confirmation of plasma LysoGb3 levels, and the known GLA mutations were tested in patients with low enzyme activities. The two groups were compared using these parameters. RESULTS: The mean level of αGLA enzyme activity was found to be lower in FSGS patients than in the HD group (2.88±1.2 µmol/L/h versus 3.79±1.9 µmol/L/h, p<0.001). There was no significant relationship between the two groups with regard to the plasma LysoGb3 levels (2.2±1.22 ng/ml versus 1.7±0.66 ng/ml, p: 0.4). In the analysis of GLA mutations, a D313Y mutation [C(937G>T) in exon p] was found in one patient from the FSGS group. CONCLUSIONS: We found that αGAL activity in patients with FSGS is lower than that in patients undergoing HD. The low enzyme activity in patients with FSGS may be explained by considering the similar pathogenesis of FSGS and FD, which may also lead to sphingolipid deposition and podocyte injury.
Assuntos
Falência Renal Crônica/terapia , alfa-Galactosidase/sangue , Feminino , Glomerulosclerose Segmentar e Focal/sangue , Glomerulosclerose Segmentar e Focal/epidemiologia , Humanos , Falência Renal Crônica/epidemiologia , Masculino , Prevalência , Estudos RetrospectivosRESUMO
OBJECTIVES: Fabry disease (FD) is a rare disease associated with sphingolipid accumulation. Sphingolipids are components of plasma membranes that are important in podocyte function and accumulate in various glomerular diseases such as focal segmental glomerulosclerosis (FSGS). Both FD and FSGS can cause podocyte damage and are classified as podocytopathies. In this respect, FD and FSGS share the same pathophysiologic pathways. Previous screening studies have shown that a significant proportion of end-stage renal disease (ESRD) patients receiving hemodialysis (HD) have unsuspected FD, and the prevalence of low alpha-galactosidase A (αGLA) enzyme activity in these patients is higher than that in the normal population. We aimed to compare αGLA enzyme activity in patients with biopsy-proven FSGS and ESRD receiving HD. METHODS: The records of 232 patients [62 FSGS (F/M: 33/29); 170 HD (M/F: 93/79)] were evaluated retrospectively. The screening was performed based on the αGLA enzyme activity on a dried blood spot, with the confirmation of plasma LysoGb3 levels, and the known GLA mutations were tested in patients with low enzyme activities. The two groups were compared using these parameters. RESULTS: The mean level of αGLA enzyme activity was found to be lower in FSGS patients than in the HD group (2.88±1.2 μmol/L/h versus 3.79±1.9 μmol/L/h, p<0.001). There was no significant relationship between the two groups with regard to the plasma LysoGb3 levels (2.2±1.22 ng/ml versus 1.7±0.66 ng/ml, p: 0.4). In the analysis of GLA mutations, a D313Y mutation [C(937G>T) in exon p] was found in one patient from the FSGS group. CONCLUSIONS: We found that αGAL activity in patients with FSGS is lower than that in patients undergoing HD. The low enzyme activity in patients with FSGS may be explained by considering the similar pathogenesis of FSGS and FD, which may also lead to sphingolipid deposition and podocyte injury.