An artificial intelligence model for instance segmentation and tooth numbering on orthopantomograms.

AIM: To develop a deep learning (DL) artificial intelligence (AI) model for instance segmentation and tooth numbering on orthopantomograms (OPGs). MATERIALS AND METHODS: Forty OPGs were manually annotated to lay down the ground truth for training two convolutional neural networks (CNNs): U-net and Faster RCNN. These algorithms were concurrently trained and validated on a dataset of 1280 teeth (40 OPGs) each. The U-net algorithm was trained on OPGs specifically annotated with polygons to label all 32 teeth via instance segmentation, allowing each tooth to be denoted as a separate entity from the surrounding structures. Simultaneously, teeth were also numbered according to the Fédération Dentaire Internationale (FDI) numbering system, using bounding boxes to train Faster RCNN. Consequently, both trained CNNs were combined to develop an AI model capable of segmenting and numbering all teeth on an OPG. RESULTS: The performance of the U-net algorithm was determined using various performance metrics including precision = 88.8%, accuracy = 88.2%, recall = 87.3%, F-1 score = 88%, dice index = 92.3%, and Intersection over Union (IoU) = 86.3%. The performance metrics of the Faster RCNN algorithm were determined using overlap accuracy = 30.2 bounding boxes (out of a possible of 32 boxes) and classifier accuracy of labels = 93.8%. CONCLUSIONS: The instance segmentation and tooth numbering results of our trained AI model were close to the ground truth, indicating a promising future for their incorporation into clinical dental practice. The ability of an AI model to automatically identify teeth on OPGs will aid dentists with diagnosis and treatment planning, thus increasing efficiency.

Integration of Mn-ZnFe2O4 with S-g-C3N4 for Boosting Spatial Charge Generation and Separation as an Efficient Photocatalyst.

The disposal of dyes and organic matter into water bodies has become a significant source of pollution, posing health risks to humans worldwide. With rising water demands and dwindling supplies, these harmful compounds must be isolated from wastewater and kept out of the aquatic environment. In the research presented here, hydrothermal synthesis of manganese-doped zinc ferrites' (Mn-ZnFe2O4) nanoparticles (NPs) and their nanocomposites (NCs) with sulfur-doped graphitic carbon nitride (Mn-ZnFe2O4/S-g-C3N4) are described. The samples' morphological, structural, and bonding features were investigated using SEM, XRD, and FTIR techniques. A two-phase photocatalytic degradation study of (0.5, 1, 3, 5, 7, 9, and 11 wt.%) Mn-doped ZnFe2O4 NPs and Mn-ZnFe2O4/(10, 30, 50, 60, and 70 wt.%) S-g-C3N4 NCs against MB was carried out to find the photocatalyst with maximum efficiency. The 9% Mn-ZnFe2O4 NPs and Mn-ZnFe2O4/50% S-g-C3N4 NCs exhibited the best photocatalyst efficiency in phase one and phased two, respectively. The enhanced photocatalytic activity of the Mn-ZnFe2O4/50% S-g-C3N4 NCs could be attributed to synergistic interactions at the Mn-ZnFe2O4/50% S-g-C3N4 NCs interface that resulted in a more effective transfer and separation of photo-induced charges. Therefore, it is efficient, affordable, and ecologically secure to modify ZnFe2O4 by doping with Mn and homogenizing with S-g-C3N4. As a result, our current research suggests that the synthetic ternary hybrid Mn-ZnFe2O4/50% S-g-C3N4 NCs may be an effective photocatalytic system for degrading organic pollutants from wastewater.