With the development of deep learning, the medical image field has also been widely used it to assist in research, and the main research in this paper is to solve the low-dose computed tomography (LDCT) denoising problem using deep learning. Although LDCT reduces the radiation hazard to patients, it also brings more noise which has some visual interference to the doctor's judgment and affects the diagnosis result. To solve this problem, referring to the architecture of cycle-generative adversarial networks (Cycle-GAN) for unsupervised learning, this paper innovatively proposes an end-to-end unsupervised LDCT denoising framework. It combines the U-Net structure for multiscale feature extraction, the attention mechanism for feature fusion, the combination of residual network for feature transformation, and also consider the comparison of GAN network models and introduce perceptual loss to improve the network for the characteristics of medical images. In addition, we build a real LDCT database and design a large number of comparative experiments to validate the method, using both experimental standards in the image field and evaluation standards in the medical field. The main feature of this paper compared with classical methods is that this paper solves the drawback that real data cannot be used for supervised learning, while this experimental result still have quite excellent performance compared with classical excellent methods, which are professionally judged by imaging physicians and meet the clinical needs of physicians.

To address the issues of high missed detection rates for small objects and interference from complex backgrounds in brain tumor detection, this paper proposes an improved model named YOLO-DCS based on YOLOv8. First, a C2fDAttention module is designed to replace the original backbone network, enhancing feature extraction in tumor regions through a dynamic attention mechanism. Second, the CARAFE (ContentAware ReAssembly of FEatures) upsampling operator is adopted to improve contour reconstruction accuracy for small tumors. Finally, the SEAMHead (Squeeze-and-Excitation Augmented Mask Head) is introduced into the detection head to achieve adaptive fusion of multi-scale features. Experimental results on the dataset demonstrate that the improved model achieves an mAP50 of 97.3 % with only a 0.06 % increase in parameter count, while the recall rate is improved by 3.3 % compared to the original YOLOv8, and the floating-point operations per second are reduced by 8.6 %. This provides a high-precision and lightweight solution for medical image-assisted diagnosis.

Reliable localization is essential for the efficiency and safety of autonomous underwater operations. In this study, we propose a novel localization framework centered on a strapdown inertial navigation system, which receives high-precision pose corrections from image-based visible-light positioning. A structured LED array is deployed as a stable underwater positioning reference, and an adaptive optical signal processing method is developed to enhance the extraction of light spot features under challenging scenarios. To address the distortions introduced by cross-medium refraction, we introduce a compensation model that restores accurate camera pose estimation without the need for cumbersome recalibration. Extensive experimental evaluations demonstrate that the proposed system achieves millimeter-level accuracy under favorable scenarios and maintains centimeter-level robustness in unfavorable observation scenarios. Owing to its high-precision, robustness, and cost-effectiveness, the proposed approach holds significant promise for advancing autonomous underwater navigation and next-generation intelligent robotic systems.

Full waveform inversion (FWI) is currently the most accurate technique for obtaining the properties of subsurface media. The absence of low frequencies in the observed data caused cycle-skipping phenomenon and poor initial model which affect the convergence of FWI. We propose a global-feature-fusion and multi-scale network (GM-Net) in a way of supervised learning to compensate for the absent low frequency components in the observed data trace by trace. The difficulty of extrapolating frequency is to achieve smoothness and continuity when changing from high frequency signals to low frequency signals, which is visually shown in the reduction and movement of the sidelobes in high-frequency signals and the overall oscillation of the signals is slowed down. For achieving better extrapolation, the encoder-decoder architecture with multi-scale feature extraction is designed as the backbone of the network. For avoiding the loss of information, we propose to perform 1/2 down-sampling on the original input signal separately based on the odd and even time samples, and then concatenate them along the channel dimension. Since 1-dimensional (1D) seismic data is a type of time-series signal and the wavelengths of low frequencies are long, we pay more attention to the relevance of contextual information. Thus, dilated convolution layers, gridding convolution blocks and non-local attention blocks are used to enlarger the receptive field both in time and channel dimensions to extract and fuse global features. Numerical tests both on synthetic data and different types of field marine data demonstrate the feasibility and generalization of our method.

Distributed acoustic sensing (DAS) has been considered as a breakthrough technique in seismic data collection owing to its advantages in acquisition cost and accuracy. However, the existence of complex background noise combined with a tough exploration environment always results in incomplete data with a low signal-to-noise ratio, posing a big challenge for the subsequent processing of DAS data. To improve the quality of DAS data, convolutional neural networks (CNN) have gradually been utilized to deal with the denoising and reconstruction tasks. Meanwhile, some successful applications have verified that CNN-based methods can significantly alleviate the impacts of DAS background noise and missing trace records, compared with conventional approaches. Nonetheless, in most researches, the denoising and reconstruction tasks are accomplished independently, severely affecting the processing efficiency. In this study, a multi-scale encoder-decoder network (MEDN) is proposed to simultaneously achieve the DAS background noise suppression and weak signal recovery through a unified model. Generally, MEDN can extract the different-scale features through both a multi-scale network architecture and a multi-scale residual (MSR) block. The captured different-scale features are then fused to enhance the effective feature. In addition, the encoder-decoder scheme is also utilized in the design of the network architecture to further enhance the reconstruction performance. Moreover, depthwise separable convolution (DSC) blocks are also utilized to ease the computational burden and improve the processing efficiency. Theoretical and field data processing results show that MEDN can provide better denoising and reconstruction performance than conventional methods and popular CNN-based frameworks.