Adenoid hypertrophy may lead to pediatric obstructive sleep apnea and mouth breathing. The routine screening of adenoid hypertrophy in dental practice is helpful for preventing relevant craniofacial and systemic consequences. The purpose of this study was to develop an automated assessment tool for adenoid hypertrophy based on artificial intelligence. A clinical dataset containing 581 lateral cephalograms was used to train the convolutional neural network (CNN). According to Fujioka’s method for adenoid hypertrophy assessment, the regions of interest were defined with four keypoint landmarks. The adenoid ratio based on the four landmarks was used for adenoid hypertrophy assessment. Another dataset consisting of 160 patients’ lateral cephalograms were used for evaluating the performance of the network. Diagnostic performance was evaluated with statistical analysis. The developed system exhibited high sensitivity (0.906, 95% confidence interval [CI]: 0.750–0.980), specificity (0.938, 95% CI: 0.881–0.973) and accuracy (0.919, 95% CI: 0.877–0.961) for adenoid hypertrophy assessment. The area under the receiver operating characteristic curve was 0.987 (95% CI: 0.974–1.000). These results indicated the proposed assessment system is able to assess AH accurately. The CNN-incorporated system showed high accuracy and stability in the detection of adenoid hypertrophy from children’ lateral cephalograms, implying the feasibility of automated adenoid hypertrophy screening utilizing a deep neural network model.

A monolayer adsorption amount of MB (714.29 mg g⁻¹) was found on a coal-based activated carbon prepared by a simple method.

Few-shot detection in remote sensing images has witnessed significant advancements recently. Despite these progresses, the capacity for continuous conceptual learning still poses a significant challenge to existing methodologies. In this paper, we explore the intricate task of incremental few-shot object detection (iFSOD) in remote sensing images. We present a pioneering transfer-learning-based technique, termed InfRS, designed to enable the incremental learning of novel classes using a restricted set of examples, while simultaneously preserving the knowledge learned from previously seen classes without the need to revisit old data. Specifically, we pretrain the detector using sufficient data from base datasets and then generate a set of class-wise prototypes that represent the intrinsic characteristics of the data. In the incremental learning session, we design a Hybrid Prototypical Contrastive (HPC) encoding module for learning discriminative representations. Furthermore, we develop a prototypical calibration strategy based on the Wasserstein distance to overcome the catastrophic forgetting problem. Comprehensive evaluations conducted with two aerial imagery datasets show that our InfRS effectively addresses the iFSOD issue in remote sensing imagery. Code is available at https://github.com/lyanna4869/InfRS.git.

Few-shot object detection (FSOD) has attracted significant research attention in remote sensing due to its potential to reduce reliance on large annotated datasets. However, two challenges remain in this area: (1) axis-aligned proposals, which can result in misalignment for arbitrarily oriented objects, and (2) object misclassification due to limited annotated data, which hinders generalization to unseen classes. To address these issues, we propose a novel method for few-shot oriented object detection in remote sensing images. Our approach employs oriented bounding boxes instead of horizontal ones to learn more effective feature representations for arbitrarily oriented aerial objects, enhancing detection accuracy. Additionally, we introduce a supervised contrastive learning module with a dynamically updated memory bank, enabling the model to leverage large batches of negative samples and to better learn discriminative features for unseen classes. Extensive experiments on DOTA, HRSC2016, and DIOR-R datasets demonstrate superior performance of our proposed method in few-shot oriented object detection. Code and pre-trained models will be made publicly available.

Total electron content (TEC) is a key parameter for characterizing ionospheric morphology and significantly impacts the Global Navigation Satellite System. The ionosphere responds dramatically to solar and geomagnetic activity, leading to substantial TEC fluctuations and disturbances. To improve TEC prediction accuracy, we propose Encoder‐Decoder (ED)‐Autoformer, a novel model combining ED structure with the Autoformer model. The model integrates time series data with TEC to enable 24‐hr forecasts of both disturbance storm time index (Dst) and TEC. Evaluated on global ionospheric maps TEC, our model achieves a improvement (0.51 TECu) in the root mean squared error (RMSE) during solar maximum and an improvement (0.14 TECu) in RMSE during solar minimum compared to the Convolutional Long‐Short‐Term Memory (ConvLSTM) method. Furthermore, ED‐Autoformer shows superior computational efficiency with faster inference speed compared to ED‐ConvLSTM. We further analyzed TEC disturbances during geomagnetic storm periods. For the geomagnetic storm on 20 September 2015, the RMSE remained below 3.50 TECu for most periods, peaking at 5.50 TECu during the main phase. These results demonstrate the robustness of the model in accurately predicting TEC disturbances during geomagnetic storm periods.