Random Gaussian noise and striping artifacts are common phenomena in hyperspectral images (HSI). In this article, an effective restoration method is proposed to simultaneously remove Gaussian noise and stripes by merging a denoising and a destriping submodel. A denoising submodel performs a multiband denoising, i.e., Gaussian noise removal, considering Gaussian noise variations between different bands, to restore the striped HSI from the corrupted image, in which the striped HSI is constrained by a weighted nuclear norm. For the destriping submodel, we propose an adaptive anisotropy total variation method to adaptively smoothen the striped HSI, and we apply, for the first time, the truncated nuclear norm to constrain the rank of the stripes to 1. After merging the above two submodels, an ultimate image restoration model is obtained for both denoising and destriping. To solve the obtained optimization problem, the alternating direction method of multipliers (ADMM) is carefully schemed to perform an alternative and mutually constrained execution of denoising and destriping. Experiments on both synthetic and real data demonstrate the effectiveness and superiority of the proposed approach.

Existing approaches still face issues such as the lack of spatial-temporal information and target prior information, as well as low detection efficiency when dealing with small infrared (IR) target detection tasks under heterogeneous backgrounds. To address the aforementioned issues, this article presents a low rank tensor approximation with saliency prior (LRTA-SP) approach, where the holistic spatiotemporal tensor model (STTM) is constructed by combining spatiotemporal related prior information of IR videos with target saliency prior information. Firstly, benefiting by the subspace optimization theory, the target and the background can be separated into a sparse and a low rank component, respectively. Crucially, the proposed LRTA-SP optimization approach updates the background tensor on a tangent space to accelerate the above optimization process, greatly reducing the computational complexity of low rank projection while improving the detection efficiency of our model. Also, applying a multi-rank constrain in low rank regularization term helps to adaptively preserve important information in the frequency domain. Furthermore, a prior weight tensor containing target saliency information is provided in sparse regularization term to preserve contextual information during the optimization process. Finally, an alternating projection-based algorithm framework is designed to robustly separate sparse targets and low rank backgrounds. The effectiveness and superiority, especially the detection efficiency, of the proposed LRTA-SP technology to similar detection technologies are validated on six real IR videos under various scenarios.

Near-infrared spectral tomography (NIRST) is a non-invasive imaging technique that provides functional information about biological tissues. Due to diffuse light propagation in tissue and limited boundary measurements, NIRST image reconstruction presents an ill-posed and ill-conditioned computational problem that is difficult to solve. To address this challenge, we developed a reconstruction algorithm (Model-CNN) that integrates a diffusion equation model with a convolutional neural network (CNN). The CNN learns a regularization prior to restrict solutions to the space of desirable chromophore concentration images. Efficacy of Model-CNN was evaluated by training on numerical simulation data, and then applying the network to physical phantom and clinical patient NIRST data. Results demonstrated the superiority of Model-CNN over the conventional Tikhonov regularization approach and a deep learning algorithm (FC-CNN) in terms of absolute bias error (ABE) and peak signal-to-noise ratio (PSNR). Specifically, in comparison to Tikhonov regularization, Model-CNN reduced average ABE by 55% for total hemoglobin (HbT) and 70% water (H2O) concentration, while improved PSNR by an average of 5.3 dB both for HbT and H2O images. Meanwhile, image processing time was reduced by 82%, relative to the Tikhonov regularization. As compared to FC-CNN, the Model-CNN achieved a 91% reduction in ABE for HbT and 75% for H2O images, with increases in PSNR by 7.3 dB and 4.7 dB, respectively. Notably, this Model-CNN approach was not trained on patient data; but instead, was trained on simulated phantom data with simpler geometrical shapes and optical source-detector configurations; yet, achieved superior image recovery when faced with real-world data.

Purpose: – This paper aim to build an information fusion model that can predict the bottom shape of welding groove for better welding quality control. Arc sensor is widely used in seam tracking due to its simplicity and good accessibility, but it heavily relies on the bottom shape of the groove. It is necessary to identify the welding groove bottom state. Therefore, arc sensor information and vision sensing information were fused by the rough set (RS) method to predict the groove state, which will lay the foundation for better welding quality control. Design/methodology/approach: – First, a multi-sensor information system was established, which included an arc sensing component and a vision sensing component. For the arc sensing system, the current waveform in each rotating period was obtained and divided into 12 parts to calculate variables representing the variation of arc length. For the vision sensing system, images were obtained by passive vision when the arc was near the groove sidewall. The positions of the sidewall and the arc were calculated to get the weld deviation which was unrelated with the bottom groove state. Second, experimental data were generated by workpiece with various bottom shapes. At last, the RS method was adopted to fuse the arc sensing and the vision information, and a rule-based model with good prediction ability was obtained. Findings: – By fusing arc sensing and vision sensing information, an RS-based model was built to predict the welding groove state. Originality/value: – The RS modeling method was used to fuse arc sensing information and vision sensing information to build a model that predicts groove bottom state. The arc sensing information represented the arc length variation, while the vision sensing information contains the seam deviation which was unrelated with the bottom groove state. The RS model gives satisfactory prediction results and can be applied to weld quality control.

Magnetic resonance imaging (MRI)-guided near infrared spectral tomography (NIRST) is a noninvasive and promising multimodal technique for early breast cancer detection and precise diagnosis. However, existing image-guided NIRST methods have not fully exploited the complementary information provided by MRI and NIRST, which limits reconstruction quality and diagnostic performance. To address this challenge, we propose a hybrid convolutional neural network-Transformer architecture (CNN-Trans) for MRI-guided NIRST reconstruction. Specifically, CNN-Trans employs convolutional neural networks (CNNs) to extract local features from NIRST measurements, while Transformers are used to capture global contextual information from MRI images. Dynamic feature fusion (DFF) modules are further incorporated to effectively integrate multimodal features, thereby enhancing NIRST reconstruction quality. Numerical simulation results demonstrate that, compared with three state-of-the-art methods, CNN-Trans reduces the average mean squared error (MSE) by at least 3.81%, while increasing the average peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and total hemoglobin (HbT) contrast by at least 1.81%, 7.23%, and 2.92%, respectively. Furthermore, the CNN-Trans trained solely on simulated datasets was directly applied to clinical data from 16 patients without retraining or fine-tuning, and achieved a sensitivity of 90.9%, an accuracy of 87.5%, and an area under the curve (AUC) of 0.909. These results indicate that CNN-Trans holds strong potential for clinical application in breast cancer imaging.

Diffuse correlation spectroscopy (DCS) is a powerful optical technique for noninvasive quantification of deep-tissue microvascular blood flow quantification. Conventional DCS systems are bulky and rely on external computing devices, limiting their point-of-care applicability. In this study, we implemented the proposed DCS system on a Xilinx Zynq-7000 system-on-chip (SoC) via hardware-software co-design approach. The proposed approach employed the programmable logic (PL) for a multi-tau digital autocorrelator and the processing system (PS) for real-time blood flow index (BFI) extraction via the Nelder–Mead algorithm. Arterial occlusion and breath-holding in vivo tests demonstrated strong consistency and high correlation with a conventional PC-based DCS system. Additionally, the proposed system significantly reduces instrumentation size and cost, enabling portable assessment of tissue microcirculation.