The development of medical big data analysis technology has enabled vast imaging datasets to play an important role in identifying complex pathologies, supporting individualized diagnoses, and enhancing diagnostic and treatment precision. Pediatric pneumonia, a leading cause of mortality in children, results from infections and is characterized by inflammation of the terminal airways, alveoli, and pulmonary interstitium. Accurate and timely diagnosis is essential for successful intervention. However, most current studies are constrained by simplistic classification tasks, and existing models struggle to effectively extract multi-scale features from Chest X-Ray (CXR) images while eliminating redundant information. Moreover, the datasets used in existing studies lack the diversity and scale necessary to meet the demands of clinical practice. To address these challenges, this paper presents the a multi-branch dual residual attention Convolutional Neural Network (CNN) model for pediatric pneumonia classification model (namely PP-ConvNeXt), designed to enable automatic diagnosis of pediatric pneumonia. First, the model incorporates a novel multi-branch dual-residual structure, enhancing its capacity to extract multi-scale features. Second, the Coordinate Attentional Feature Fusion (CAFF) module is introduced to integrate cross-branch features, allowing for comprehensive acquisition of lesion information. Finally, this research pioneers the automatic five-class diagnosis of pediatric pneumonia, offering clinicians more accurate diagnostic insights. Additionally, a comprehensive dataset comprising 5632 CXR images from Hainan Women and Children’s Medical Center (HWCMC) is presented. Experimental results indicate that the PP-ConvNeXt model surpasses state-of-the-art models and expert human diagnosticians in the five-class diagnosis of pediatric pneumonia, achieving an Area Under the Curve (AUC) score of 89.01%. Additionally, key performance metrics, including accuracy and recall, further validate the model’s superior performance.

Accurate left atrial segmentation is essential for improving cardiovascular diagnosis and therapeutic strategies. The adoption of fully convolutional networks, particularly those based on the U-shaped network (U-Net) architecture, has substantially improved semantic segmentation accuracy, becoming predominant in medical segmentation tasks. Nevertheless, the left atrium, characterized by its complex and non-rigid motion, presents substantial challenges for existing segmentation models, which often fail to fully utilize channel feature information and suffer from redundant semantic information extraction, thereby compromising segmentation accuracy. To address these limitations, the RPEU-Net network model for left atrial segmentation is proposed. Initially, the residual parallel convolution unit (RPCU) is initially incorporated to improve the model’s capability in capturing and representing complex feature information. Subsequently, the proposed hybrid enhanced attention module (HEAM) mitigates the shortcomings of traditional attention mechanisms, significantly improving the screening capability of relevant feature information and demonstrating robust adaptability to noise and redundant information. Finally, the network employs a lightweight architectural design to reduce redundancy while maintaining computational efficiency. Evaluation experiments conducted on two left atrial datasets indicate that RPEU-Net achieves superior results, exhibiting higher segmentation performance and potential compared to existing methods.