Deep-learning-based pyramid-transformer for localized porosity analysis of hot-press sintered ceramic paste.

Scanning Electron Microscope (SEM) is a crucial tool for studying microstructures of ceramic materials. However, the current practice heavily relies on manual efforts to extract porosity from SEM images. To address this issue, we propose PSTNet (Pyramid Segmentation Transformer Net) for grain and pore segmentation in SEM images, which merges multi-scale feature maps through operations like recombination and upsampling to predict and generate segmentation maps. These maps are used to predict the corresponding porosity at ceramic grain boundaries. To increase segmentation accuracy and minimize loss, we employ several strategies. (1) We train the micro-pore detection and segmentation model using publicly available Al2O3 and custom Y2O3 ceramic SEM images. We calculate the pixel percentage of segmented pores in SEM images to determine the surface porosity at the corresponding locations. (2) Utilizing high-temperature hot pressing sintering, we prepared and captured scanning electron microscope images of Y2O3 ceramics, with which a Y2O3 ceramic dataset was constructed through preprocessing and annotation. (3) We employed segmentation penalty cross-entropy loss, smooth L1 loss, and structural similarity (SSIM) loss as the constituent terms of a joint loss function. The segmentation penalty cross-entropy loss helps suppress segmentation loss bias, smooth L1 loss is utilized to reduce noise in images, and incorporating structural similarity into the loss function computation guides the model to better learn structural features of images, significantly improving the accuracy and robustness of semantic segmentation. (4) In the decoder stage, we utilized an improved version of the multi-head attention mechanism (MHA) for feature fusion, leading to a significant enhancement in model performance. Our model training is based on publicly available laser-sintered Al2O3 ceramic datasets and self-made high-temperature hot-pressed sintered Y2O3 ceramic datasets, and validation has been completed. Our Pix Acc score improves over the baseline by 12.2%, 86.52 vs. 76.01, and the mIoU score improves from by 25.5%, 69.10 vs. 51.49. The average relative errors on datasets Y2O3 and Al2O3 were 6.9% and 6.36%, respectively.

AMENet is a monocular depth estimation network designed for automatic stereoscopic display.

Monocular depth estimation has a wide range of applications in the field of autostereoscopic displays, while accuracy and robustness in complex scenes are still a challenge. In this paper, we propose a depth estimation network for autostereoscopic displays, which aims at improving the accuracy of monocular depth estimation by fusing Vision Transformer (ViT) and Convolutional Neural Network (CNN). Our approach feeds the input image as a sequence of visual features into the ViT module and utilizes its global perception capability to extract high-level semantic features of the image. The relationship between the losses is quantified by adding a weight correction module to improve robustness of the model. Experimental evaluation results on several public datasets show that AMENet exhibits higher accuracy and robustness than existing methods in different scenarios and complex conditions. In addition, a detailed experimental analysis was conducted to verify the effectiveness and stability of our method. The accuracy improvement on the KITTI dataset compared to the baseline method is 4.4%. In summary, AMENet is a promising depth estimation method with sufficient high robustness and accuracy for monocular depth estimation tasks.

Dense monocular depth estimation for stereoscopic vision based on pyramid transformer and multi-scale feature fusion.

Stereoscopic display technology plays a significant role in industries, such as film, television and autonomous driving. The accuracy of depth estimation is crucial for achieving high-quality and realistic stereoscopic display effects. In addressing the inherent challenges of applying Transformers to depth estimation, the Stereoscopic Pyramid Transformer-Depth (SPT-Depth) is introduced. This method utilizes stepwise downsampling to acquire both shallow and deep semantic information, which are subsequently fused. The training process is divided into fine and coarse convergence stages, employing distinct training strategies and hyperparameters, resulting in a substantial reduction in both training and validation losses. In the training strategy, a shift and scale-invariant mean square error function is employed to compensate for the lack of translational invariance in the Transformers. Additionally, an edge-smoothing function is applied to reduce noise in the depth map, enhancing the model's robustness. The SPT-Depth achieves a global receptive field while effectively reducing time complexity. In comparison with the baseline method, with the New York University Depth V2 (NYU Depth V2) dataset, there is a 10% reduction in Absolute Relative Error (Abs Rel) and a 36% decrease in Root Mean Square Error (RMSE). When compared with the state-of-the-art methods, there is a 17% reduction in RMSE.

Clinical study showing a lower abundance of Neisseria in the oral microbiome aligns with low birth weight pregnancy outcomes.

OBJECTIVES: The objective of this study was to examine the association between the oral microbiome and pregnancy outcomes, specifically healthy or preterm low birth weight (PLBW) in individuals with and without periodontal disease (PD). MATERIAL AND METHODS: In this prospective clinical trial, we recruited 186 pregnant women, 17 of whom exhibited PD and delivered PLBW infants (PD-PLBW group). Of the remaining women, 155 presented PD and delivered healthy infants; 18 of these subjects with similar periodontal condition and age matched to the PD-PLBW group, and they became the PD-HD group. From the total group, 11 women exhibited healthy gingiva and had a healthy delivery (HD) and healthy infants (H-HD group), and 3 exhibited healthy gingiva and delivered PLBW infants (H-PLBW group). Periodontal parameters were recorded, and subgingival plaque and serum were collected during 26-28 gestational weeks. For the plaque samples, microbial abundance and diversity were accessed by 16S rRNA sequencing. RESULTS: Women with PD showed an enrichment in the genus Porphyromonas, Treponema, and Filifactor, whereas women with healthy gingiva showed an enrichment in Streptococcus, Actinomyces, and Corynebacterium, independently of the birth status. Although no significant difference was found in the beta diversity between the 4 groups, women that had PLBW infants presented a significantly lower abundance of the genus Neisseria, independently of PD status. CONCLUSION: Lower levels of Neisseria align with preterm low birth weight in pregnant women, whereas a higher abundance of Treponema, Porphyromonas, Fretibacterium, and Filifactor and a lower abundance of Streptococcus may contribute to periodontal disease during pregnancy. CLINICAL RELEVANCE: The oral commensal Neisseria have potential in the prediction of PLBW.

Unculturable and culturable periodontal-related bacteria are associated with periodontal inflammation during pregnancy and with preterm low birth weight delivery.

Recent studies revealed culturable periodontal keystone pathogens are associated with preterm low birth weight (PLBW). However, the oral microbiome is also comprised of hundreds of 'culture-difficult' or 'not-yet-culturable' bacterial species. To explore the potential role of unculturable and culturable periodontitis-related bacteria in preterm low birth weight (PLBW) delivery, we recruited 90 pregnant women in this prospective study. Periodontal parameters, including pocket probing depth, bleeding on probing, and clinical attachment level were recorded during the second trimester and following interviews on oral hygiene and lifestyle habits. Saliva and serum samples were also collected. After delivery, birth results were recorded. Real-time PCR analyses were performed to quantify the levels of periodontitis-related unculturable bacteria (Eubacterium saphenum, Fretibacterium sp. human oral taxon(HOT) 360, TM7 sp. HOT 356, and Rothia dentocariosa), and cultivable bacteria (Aggregatibacter actinomycetemcomitans, Porphyromonas gingivalis, Tannerella forsythia, Treponema denticola, Fusobacterium nucleatum and Prevotella intermedia) in saliva samples. In addition, ELISA analyses were used to determine the IgG titres against periodontal pathogens in serum samples. Subjects were categorized into a Healthy group (H, n = 20) and periodontitis/gingivitis group (PG, n = 70) according to their periodontal status. The brushing duration was significantly lower in the PG group compared to the H group. Twenty-two of 90 subjects delivered PLBW infants. There was no significant difference in periodontal parameters and serum IgG levels for periodontal pathogens between PLBW and healthy delivery (HD) groups. However, ordinal logistic regression analysis revealed that a higher abundance of Treponema denticola, Prevotella intermedia, Fretibacterium sp. HOT360 and lower levels of Rothia dentocariosa were significantly associated with the presence of periodontal disease during pregnancy. Moreover, the amount of Eubacterium saphenum in saliva and serum IgG against Aggregatibacter actinomycetemcomitans were negatively correlated with PLBW. Taken together, unculturable periodontitis-associated bacteria may play an important role both in the presence of periodontal inflammation during pregnancy and subsequent PLBW.