Xun Gong

Rain and fog significantly degrade visibility in rail transit monitoring systems due to their non-uniform spatial distribution and dynamic temporal variations. Traditional image restoration methods struggle to balance computational efficiency and edge preservation under extreme weather conditions. We propose a Frequency-Adaptive Multi-Scale Network (FAMNet) that jointly optimizes wavelet-based spectral decomposition and similarity-driven feature aggregation. Our framework dynamically models degradation patterns through adaptive spectral kernels while capturing cross-region dependencies via similarity-driven aggregation. Evaluated on 8500 synthetic rail transit images derived from the RailSem19 benchmark, the method achieves 32.6 dB PSNR/0.95 SSIM for deraining (+1.0 dB/+4% vs. Restormer). Our method, evaluated on an NVIDIA RTX 3080 GPU with 256 × 256 inputs (batch size 1, FP32 precision), achieves an end-to-end inference speed approximately 40× faster than Restormer—a leading baseline in restoration quality—while maintaining competitive performance. This efficiency shows strong potential for cost-effective deployment in all-weather rail transit inspection systems, with possible applications in safety-critical scenarios such as track obstacle detection.

Estimating Left Ventricular Ejection Fraction (LVEF) from echocardiograms constitutes an ill-posed inverse problem. Inherent noise, artifacts, and limited viewing angles introduce ambiguity, where a single video sequence may map not to a unique ground truth, but rather to a distribution of plausible physiological values. Prevailing deep learning approaches typically formulate this task as a standard regression problem that minimizes the Mean Squared Error (MSE). However, this paradigm compels the model to learn the conditional expectation, which may yield misleading predictions when the underlying posterior distribution is multimodal or heavy-tailed -- a common phenomenon in pathological scenarios. In this paper, we investigate the paradigm shift from deterministic regression toward generative regression. We propose the Multimodal Conditional Score-based Diffusion model for Regression (MCSDR), a probabilistic framework designed to model the continuous posterior distribution of LVEF conditioned on echocardiogram videos and patient demographic attribute priors. Extensive experiments conducted on the EchoNet-Dynamic, EchoNet-Pediatric, and CAMUS datasets demonstrate that MCSDR achieves state-of-the-art performance. Notably, qualitative analysis reveals that the generation trajectories of our model exhibit distinct behaviors in cases characterized by high noise or significant physiological variability, thereby offering a novel layer of interpretability for AI-aided diagnosis.

Imbalanced data presents a critical challenge in the medical domain, significantly influencing the accuracy of disease diagnosis and treatment. Traditional machine learning algorithms often favor the majority class. Common approaches to mitigate this bias include augmenting minority class samples, reducing majority class samples, or leveraging ensemble classifiers. However, in medical applications, these methods often compromise data authenticity and information density, or require extensive computational resources and intricate parameter tuning to achieve optimal results. To address these challenges, this paper introduces a method named ROAFS that integrates random over-sampling techniques with axiomatic fuzzy set theory based decision trees. This approach effectively improves both classifier performance and interpretability. Random over-sampling is utilized to balance the imbalanced datasets, which are combined with fuzzy decision trees to generate clear semantic descriptions for each class. Experiments conducted on 10 datasets with 5-fold cross-validation show that ROAFS maintains high classification accuracy. It also provides intuitive and meaningful semantic explanations, outperforming existing methods. This approach offers a practical and interpretable solution to the problem of imbalanced data, showing significant potential for real-world medical applications.