Bone age assessment (BAA) based on hand X-ray imaging is a common clinical practice for investigating disorders and predicting the adult height of a child. However, the traditional manual method is time consuming and prone to obverse variability. There is an urgent need for a fully automatic framework based on deep learning with high performance and efficiency. We propose an end-to-end BAA model based on lossless image compression and a squeeze-and-excitation deep residual network (SE-ResNet). First, we apply the compression module to compress the raw image without losing important features. Second, the SE-ResNet-based model extracts features of the compressed images. Furthermore, the regression model with improved loss function predicts bone age. The experiments on a public dataset reveal that our method outperforms the baseline models. In conclusion, the presented method is a fully automatic and effective solution to process hand X-ray images for BAAs.

The object detection, which has been widely applied in the biomedical field already, is of real significance but technically challenging. In practice, the object detection accuracy is vulnerable to labeling quality, which is usually not a big headache for simple algorithm or model verification since there are a bunch of ideal public available datasets whose classes and tags are all well-marked. However, in real scenarios, image data is often partially or even incorrectly labelled. Particularly, in cell detection, this becomes a thorny issue since the labelling of the dataset is incomplete and inac- curate. To address this issue, we propose a data-augmentation algorithm that can generate full labelled cell image data from incomplete labeled ones. First of all, we randomly extract the labeled objects from raw cell images, and mean- while, keep their corresponding position information. Next, we employ the framework of cycle-consistent adversarial network, but significantly distinguished from the original one, to generate fully labeled data including both objects and backgrounds. We conduct extensive experiments on a blood cell classification dataset called BCCD to evaluate our model, and experimental results show that our proposed method can successfully address the weak annotation problem and improve the performance of object detection.

Semantic classification of Chinese long discourses is an important and challenging task. Discourse text is high‐dimensional and sparse. Furthermore, when the number of classes of dataset is large, the data distribution will be seriously imbalanced. In solving these problems, we propose a novel end‐to‐end model called CRAFL, which is based on the convolutional layer with attention mechanism, recurrent neural networks, and improved focal loss function. First, the residual network (ResNet) extracts phrase semantic representations from word embedding vectors and reduces the dimensionality of the input matrix. Then, the attention mechanism differentiates the focus on the output of ResNet, and the long short‐term memory layer learns the features of the sequences. Lastly but most significantly, we apply an improved focal loss function to mitigate the problem of data class imbalance. Our model is compared with other state‐of‐the‐art models on the long discourse dataset, and CRAFL model has proven be more efficient for this task.

Maritime small object detection is critical for UAV-based sea surveillance but remains challenging due to the small size of targets and interference from sea reflections and waves. This paper proposes SeaLSOD-YOLO, a lightweight detection algorithm based on YOLOv11, designed to improve small object detection accuracy while maintaining real-time performance. The method incorporates four key modules: Shallow Multi-scale Output Reconstruction, which fuses shallow and mid-level features to preserve fine-grained details; SPPF-FD, which combines spatial pyramid pooling with frequency-domain adaptive convolution to enhance sensitivity to high-frequency textures and suppress sea-surface interference; attention-based feature fusion, which emphasizes small object features through channel and spatial attention; and dynamic multi-scale sampling, which optimizes feature representation across different scales. Experiments on the SeaDroneSee dataset demonstrate that, compared with YOLOv11s, the proposed method improves precision from 75.6% to 81.9%, recall from 62.6% to 73.5%, and mAP@0.5 from 67.9% to 77.0%. The mAP@0.5:0.95 also increases from 41.1% to 44.9%. The model achieves an inference speed of 256 FPS. Although the parameter size increases from 18.2 MB to 30.8 MB, the method maintains a favorable balance between detection accuracy and computational efficiency. Comparative evaluation further shows superior performance in detecting small maritime objects such as buoys and lifeboats. These results indicate that SeaLSOD-YOLO effectively balances accuracy, efficiency, and real-time capability in complex maritime environments. Future work will focus on further optimization of attention mechanisms and upsampling strategies to enhance the detection of extremely small targets.

In industrial vision, the lack of defect samples is one of the key constraints of depth vision quality inspection. This paper mainly studies defect detection under a small training set, trying to reduce the dependence of the model on defect samples by using normal samples. Therefore, we propose a Knowledge-Embedding Relational Network. We propose a Knowledge-Embedding Relational Network (KRN): firstly, unsupervised clustering and convolution features are used to model the knowledge of normal samples; at the same time, based on CNN feature extraction assisted by image segmentation, the conv feature is obtained from the backbone network; then, we build the relationship between knowledge and prediction samples through covariance, embed the knowledge, further mine the correlation using gram operation, normalize the power of the high-order features obtained by covariance, and finally send them to the prediction network. Our KRN has three attractive characteristics: (I) Knowledge Modeling uses the unsupervised clustering algorithm to statistically model the standard samples so as to reduce the dependence of the model on defect data. (II) Covariance-based Knowledge Embedding and the Gram Operation capture the second-order statistics of knowledge features and predicted image features to deeply mine the robust correlation. (III) Power Normalizing suppresses the burstiness of covariance module learning and the complexity of the feature space. KRN outperformed several advanced baselines in small training sets on the DAGM 2007, KSDD, and Steel datasets.