Search

Objectives Instance-level tooth segmentation extracts abundant localization and shape information from panoramic radiographs (PRs). The aim of this study was to evaluate the performance of a mask refinement network that extracts precise tooth edges. Methods A public dataset which consists of 543 PRs and 16211 labelled teeth was utilized. The structure of a typical Mask Region-based Convolutional Neural Network (Mask RCNN) was used as the baseline. A novel loss function was designed focus on producing accurate mask edges. In addition to our proposed method, 3 existing tooth segmentation methods were also implemented on the dataset for comparative analysis. The average precisions (APs), mean intersection over union (mIoU), and mean Hausdorff distance (mHAU) were exploited to evaluate the performance of the network. Results A novel mask refinement region-based convolutional neural network was designed based on Mask RCNN architecture to extract refined masks for individual tooth on PRs. A total of 3311 teeth were correctly detected from 3382 tested teeth in 111 PRs. The AP, precision, and recall were 0.686, 0.979, and 0.952, respectively. Moreover, the mIoU and mHAU achieved 0.941 and 9.7, respectively, which are significantly better than the other existing segmentation methods. Conclusions This study proposed an efficient deep learning algorithm for accurately extracting the mask of any individual tooth from PRs. Precise tooth masks can provide valuable reference for clinical diagnosis and treatment. This algorithm is a fundamental basis for further automated processing applications. [ABSTRACT FROM AUTHOR]

Whether or not a hyperspectral anomaly detector is effective is determined by two crucial issues, anomaly detectability and background suppressibility (BS), both of which are very closely related to two factors, the datasets used for a selected hyperspectral anomaly detector and detection measures used for its performance evaluation. This paper explores how anomaly detectability and BS play key roles in hyperspectral anomaly detection (HAD). To address these two issues, we investigate three key elements attributed to HAD. One is a selected hyperspectral anomaly detector, and another is the datasets used for experiments. The third one is the detection measures used to evaluate the effectiveness of a hyperspectral anomaly detector. As for hyperspectral anomaly detectors, twelve commonly used anomaly detectors were evaluated and compared. To address the appropriate use of datasets for HAD, seven popular and widely used datasets were studied for HAD. As for the third issue, the traditional area under a receiver operating characteristic (ROC) curve of detection probability—PD versus false alarm probability, PF, (AUC(D,F))—was extended to 3D ROC analysis where a 3D ROC curve was developed to generate three 2D ROC curves from which eight detection measures could be derived to evaluate HAD in all round aspects, including anomaly detectability, BS and joint anomaly detectability and BS. Qualitative analysis showed that many works reported in the literature which claimed that their developed hyperspectral anomaly detectors performed better than other anomaly detectors are actually not true because they overlooked these two issues. Specifically, a comprehensive study via extensive experiments demonstrated that these 3D ROC curve-derived detection measures can be further used to address the various characterizations of different data scenes and also to provide explanations as to why certain data scenes are not suitable for HAD. [ABSTRACT FROM AUTHOR]

Simple Summary: Pigs have been evaluated as good model animals for human physiological and pathological research. During the weaned period, piglets are vulnerable to pathogens due to the transformation from a liquid to a solid feed, environmental changes, and an immature autoimmune system. Intraperitoneal injection of lipopolysaccharide (LPS) has been widely applied to simulate liver injury in piglets, but there are still some puzzles and gaps in our understanding. Therefore, we explored the effects of continuous low-dose LPS induction on serum enzyme activity, antioxidant level, liver morphology, and mRNA expression related to liver injury in weaned piglets. The findings demonstrated that oxidative damage and liver injury occurred at the early stage with LPS induction, but the damage was gradually weakened at the later stage. This indicated that continuous LPS induction may cause endotoxin tolerance after a certain amount of time. Due to imperfections in their immune and digestive systems, weaned piglets are susceptible to invasions of the external environment and diseases, especially bacterial infections, which lead to slow growth, tissue damage, and even the death of piglets. Here, a model of weaned piglets induced by Escherichia coli lipopolysaccharide (LPS) was established to explore the effects of continuous low-dose LPS induction on the mechanism of liver injury. A total of forty-eight healthy 28-day-old weaned piglets (weight = 6.65 ± 1.19 kg) were randomly divided into two groups: the CON group and LPS group. During the experimental period of thirteen days, the LPS group was injected intraperitoneally with LPS (100 μg/kg) once per day, and the CON group was treated with the same volume of 0.9% NaCl solution. On the 1st, 5th, 9th, and 13th days, the serum and liver of the piglets were collected for the determination of serum biochemical indexes, an antioxidant capacity evaluation, and histopathological examinations. In addition, the mRNA expression levels of the TLR4 pathway and inflammatory cytokines were detected. The results showed that the activities of aspartate aminotransferase (AST), alanine aminotransferase (ALT), and alkaline phosphatase (ALP) in the serum increased after LPS induction. The activities of total antioxidant capacity (T-AOC) and glutathione peroxidase (GSH-Px) in the serum and liver homogenate of the LPS group were lower than those of the CON group, while the malondialdehyde (MDA) content in the serum and the activities of catalase (CAT) and superoxide dismutase (SOD) in the liver of the LPS group were higher than those in the CON group. At the same time, morphological impairment of the livers occurred, including hepatocyte caryolysis, hepatocyte vacuolization, karyopycnosis, and inflammatory cell infiltration, and the mRNA expression levels of TLR4, MyD88, NF-κB, TNF-α, IL-6, and IL-10 were upregulated in the livers after LPS induction. The above results were more obvious on the 1st and 5th days of LPS induction, while the trend during the later period was not significant. It was concluded that the oxidative stress and liver injury occurred at the early stage of LPS induction, while the liver damage weakened at the later stage. The weaned piglets probably gradually developed tolerance to the endotoxin after the continuous low-dose induction of LPS. [ABSTRACT FROM AUTHOR]

This letter extends one of popular spectral–spatial classification methods for hyperspectral images, called edge preserving filtering (EPF)-based method to an iterative version of EPF method, referred to as iterative EPF (IEPF). Instead of finding maximum of the final soft probability maps obtained from the initial binary probability maps by EPF, the proposed IEPF feeds back the soft probability maps and combines them with the currently being processed image cube to create a new image cube as the next input to IEPF to reimplement support vector machine (SVM) for classification. The process is carried out iteratively by repeatedly feeding back the spatial information provided by EPF-obtained soft probability maps and terminated by a Tanimoto index (TI)-based automatic stopping rule. The experimental results demonstrate that IEPF performed better than EPF by providing higher classification accuracy. [ABSTRACT FROM AUTHOR]