Medical image restoration tasks aim to recover high-quality images from degraded observations, exhibiting emergent desires in many clinical scenarios, such as low-dose CT image denoising, MRI super-resolution, and MRI artifact removal. Despite the success achieved by existing deep learning-based restoration methods with sophisticated modules, they struggle with rendering computationally-efficient reconstruction results. Moreover, they usually ignore the reliability of the restoration results, which is much more urgent in medical systems. To alleviate these issues, we present LRformer, a Lightweight Transformer-based method via Reliability-guided learning in the frequency domain. Specifically, inspired by the uncertainty quantification in Bayesian neural networks (BNNs), we develop a Reliable Lesion-Semantic Prior Producer (RLPP). RLPP leverages Monte Carlo (MC) estimators with stochastic sampling operations to generate sufficiently-reliable priors by performing multiple inferences on the foundational medical image segmentation model, MedSAM. Additionally, instead of directly incorporating the priors in the spatial domain, we decompose the cross-attention (CA) mechanism into real symmetric and imaginary anti-symmetric parts via fast Fourier transform (FFT), resulting in the design of the Guided Frequency Cross-Attention (GFCA) solver. By leveraging the conjugated symmetric property of FFT, GFCA reduces the computational complexity of naive CA by nearly half. Extensive experimental results in various tasks demonstrate the superiority of the proposed LRformer in both effectiveness and efficiency.

Cross domain medical image reconstruction aims to address the issue that deep learning models trained solely on one source dataset might not generalize effectively to unseen target datasets from different hospitals. Some recent methods achieve satisfactory reconstruction performance, but often at the expense of extensive parameters and time consumption. To strike a balance between cross domain image reconstruction quality and model computational efficiency, we propose a lightweight sparse Bayesian deep learning method. Notably, we apply a fixed-form variational Bayes (FFVB) approach to quantify pixel-wise uncertainty priors derived from degradation distribution of the source domain. Furthermore, by integrating the uncertainty prior into the posterior sampled through stochastic gradient Langevin dynamics (SGLD), we develop a training strategy that dynamically generates and optimizes the prior distribution on the network weights for each unseen domain. This strategy enhances generalizability and ensures robust reconstruction performance. When evaluated on medical image reconstruction tasks, our proposed approach demonstrates impressive performance across various previously unseen domains.

The remarkable success of deep learning (DL) in predicting battery health has prompted interest in its application in recent years. While state-of-the-art DL models have achieved high accuracy in battery health prediction, they have not been widely adopted in industrial workflows, primarily due to their lack of interpretability and security. To address this issue, we propose a blockchain-based interpretable prediction algorithm for battery health prediction in electric vehicles (EVs) within the Internet of Vehicles (IoV). Specifically, the proposed method includes a platform architecture for a blockchain-based DL system, ensuring secure storage of user data during the prediction process. Notably, we develop a novel battery life prediction algorithm called BLP-Transformer, which leverages short-term relationships between degraded data and explains the impact of feature extraction on predicted results through the contribution of aggregated features based on a feature focusing mechanism. Experimental results demonstrate that the system is feasible for security and can provide accurate battery life prediction. In addition, the comparison study further highlights the superiority of the proposed algorithm in terms of robustness, prediction accuracy, and model interpretability.

Deep learning (DL)-based Low-dose CT (LDCT) image denoising methods may face domain shift problem, where data from different domains (i.e., hospitals) may have similar anatomical regions but exhibit different intrinsic noise characteristics. Therefore, we propose a plug-and-play model called Lowand High-frequency Alignment (LHFA) to address this issue by leveraging semantic features and aligning noise distributions of different CT datasets, while maintaining diagnostic image quality and suppressing noise. Specifically, the LHFA model consists of a Low-frequency Alignment (LFA) module that preserves semantic features (i.e., low-frequency components) with fewer perturbations from both domains for reconstruction. Notably, a Highfrequency Alignment (HFA) module is proposed to quantify the discrepancy between noise representations (i.e., high-frequency components) in a latent space mapped by an auto-encoder. Experimental results demonstrate that the LHFA model effectively alleviates the domain shift problem and significantly improves the performance of DL-based methods on cross-domain LDCT image denoising task, outperforming other domain adaptationbased methods.

Recently, cross domain adaptation has been applied into quite a few image restoration tasks. While promising performance has been achieved, the domain shift problem between the training set (a.k.a., source domain) and the testing set (a.k.a., target domain) in Low-dose Computed Tomography (LDCT) image denoising tasks is typically ignored by most existing methods. This is prone to the degradation of the denoising performance due to large discrepancy of feature distribution in each dataset from various vendors. Therefore, a simple yet effective LDCT denoising approach has been proposed in this paper to alleviate the domain shift between source and target domains through a novel semantic information alignment. Specifically, we first propose an adaptive version of random frequency mask (RFM) to extract the shared semantic information of cross domains. Then, we incorporate the mask into the existing denoiser to construct a semantic-information-guided objective. Experiments on synthetic and real datasets show our proposed method achieves impressive performance.