ABSTRACT
BACKGROUND: Deep learning, as an artificial intelligence method has been proved to be powerful in analyzing images. The purpose of this study is to construct a deep learning-based model (ToothNet) for the simultaneous detection of dental caries and fissure sealants in intraoral photos. METHODS: A total of 1020 intraoral photos were collected from 762 volunteers. Teeth, caries and sealants were annotated by two endodontists using the LabelMe tool. ToothNet was developed by modifying the YOLOX framework for simultaneous detection of caries and fissure sealants. The area under curve (AUC) in the receiver operating characteristic curve (ROC) and free-response ROC (FROC) curves were used to evaluate model performance in the following aspects: (i) classification accuracy of detecting dental caries and fissure sealants from a photograph (image-level); and (ii) localization accuracy of the locations of predicted dental caries and fissure sealants (tooth-level). The performance of ToothNet and dentist with 1year of experience (1-year dentist) were compared at tooth-level and image-level using Wilcoxon test and DeLong test. RESULTS: At the image level, ToothNet achieved an AUC of 0.925 (95% CI, 0.880-0.958) for caries detection and 0.902 (95% CI, 0.853-0.940) for sealant detection. At the tooth level, with a confidence threshold of 0.5, the sensitivity, precision, and F1-score for caries detection were 0.807, 0.814, and 0.810, respectively. For fissure sealant detection, the values were 0.714, 0.750, and 0.731. Compared with ToothNet, the 1-year dentist had a lower F1 value (0.599, p < 0.0001) and AUC (0.749, p < 0.0001) in caries detection, and a lower F1 value (0.727, p = 0.023) and similar AUC (0.829, p = 0.154) in sealant detection. CONCLUSIONS: The proposed deep learning model achieved multi-task simultaneous detection in intraoral photos and showed good performance in the detection of dental caries and fissure sealants. Compared with 1-year dentist, the model has advantages in caries detection and is equivalent in fissure sealants detection.
Subject(s)
Deep Learning , Dental Caries , Pit and Fissure Sealants , Humans , Dental Caries/diagnosis , Pit and Fissure Sealants/therapeutic use , Pilot Projects , Photography, Dental/methods , Adult , Male , FemaleABSTRACT
As a huge reservoir of economic metallic elements, oceanic polymetallic nodules have important strategic significance and are one of the main research objects in marine geology, especially their formation process and genetic mechanism. In this study, polymetallic nodules from the cobalt-rich crust exploration contract area in the Western Pacific Ocean were taken as the research object. Optical microscopy, scanning electron microscopy (SEM), X-ray diffraction (XRD), and energy dispersive spectroscopy (EDS) were used for observation and testing. The results indicate that many nanomineral particles, mainly composed of Fe and Mn, developed in polymetallic nodules from the western Pacific Ocean. The solid-liquid interface process of nanomineral particles plays an important role in the growth and evolution of nodules. We propose that the growth process of polymetallic nodules in the western Pacific Ocean can be divided into three stages. First, terrigenous detritus nucleates, and nanomineral particles composed of Fe, Mn, and other elements form, aggregate and attach to the core to form the initial shell. Second, a dense layer of the shell forms under stable conditions. In the third stage, the redox conditions of the nodules change, and the polymetallic nodules experience a variety of interface process modifications.
Subject(s)
Cobalt , Pacific Ocean , Oceans and Seas , Spectrometry, X-Ray Emission , Microscopy, Electron, ScanningABSTRACT
Nanoparticles have been extensively found in brittle faults or ductile shear zones, and their formation is closely related to shear movement along the fault plane. However, the formation mechanisms of these nanoparticles are not yet clear. In this study, dolomite samples were triaxially compressed, at a confining pressure of 200-300 MPa, a temperature between 27 °C and 900 °C and a strain rate of approximately 10-5s-1, with a Paterson designed gas medium high-temperature and high-pressure deformation apparatus (HTPDA). Samples deformed at room temperature were characterized by universal microcracks and undulatory extinctions in some grains; when at a temperature between 300 °C and 500 °C, well-developed mechanical twins dominated the microstructure, while at a temperature ≥800 °C, displacements of twin lamellae along a cleavage and a well-developed fracture zone could be seen. Nanoparticles of different shapes were discovered on the slip surfaces of a shear fracture or in microcracks by field emission scanning electron microscopy (FESEM). Nanoparticles on deformed samples under low differential stress were usually of sporadic spherical shapes and uneven distribution; while deformed samples under high differential stress had more dense distributions that were identified. Moreover, grain-overlap and nanofine granulation could be recognized in high strain samples. Based on a mechanical data analysis and microstructural observations, it was suggested that the initial formation of nanoparticles was macroscopically determined by the differential stress subjected to the host rocks, and had nothing to do with temperature; whereas the aggregation morphology of the nanoparticles was related to the temperature during the formation and evolution processes of the nanoparticles.