Cracks pose severe threats to the integrity of concrete structures and hence timely detection of concrete cracks are essential for assessment and maintenance of built concrete infrastructure. In particular, the accurate quantification of cracks, preferably in pixel-level with assistance of computer vision, has immense value to explicitly assess the in-service concrete structures. However, current approaches fail to capture fine cracks necessary for early-stage damage identification, and lack both accuracy and robustness under challenging environmental conditions. This study introduces a comprehensive concrete crack quantification algorithm based on the integration of super-resolution and multi-modal feature fusion. It incorporates a super-resolution network to recover fine crack details lost due to motion blur, compression artifacts, or low sensor quality, and a multi-modality feature fusion-based segmentation network (SQFormer) designed to improve segmentation accuracy in visually challenging environments. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art approaches, achieving 92.29% F1-score and 90.62% mIoU for crack segmentation, accurately quantifies thin cracks as narrow as 0.25 mm with an error rate of 7.3% The proposed algorithm enhances crack quantification precision while exceptional robustness, provides reliable quantitative metrics for concrete structural assessment.

Multi-source generative models have gained significant attention due to their ability to capture complex data distributions across diverse domains. However, existing approaches often struggle with limitations such as negative transfer and an over-reliance on large pre-trained models. To address these challenges, we propose a novel method that effectively handles scenarios with outlier source domains, while making weaker assumptions about the data, thus ensuring broader applicability. Our approach enhances robustness and efficiency, supported by rigorous theoretical analysis, including non-asymptotic error bounds and asymptotic guarantees. In the experiments, we validate our methods through numerical simulations and realworld data experiments, showcasing their practical effectiveness and adaptability.

Hyperspectral image super-resolution (HISR) aims to fuse a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) to obtain a high-resolution hyperspectral image (HR-HSI). Due to some existing HISR methods ignoring the significant feature difference between LR-HSI and HR-MSI, the reconstructed HR-HSI typically exhibits spectral distortion and blurring of spatial texture. To solve this issue, we propose a multi-scale feature transfer network (MFTN) for HISR. Firstly, three multi-scale feature extractors are constructed to extract features of different scales from the input images. Then, a multi-scale feature transfer module (MFTM) consisting of three improved feature matching Transformers (IMatchFormers) is designed to learn the detail features of different scales from HR-MSI by establishing the cross-model feature correlation between LR-HSI and degraded HR-MSI. Finally, a multiscale dynamic aggregation module (MDAM) containing three spectral aware aggregation modules (SAAMs) is constructed to reconstruct the final HR-HSI by gradually aggregating features of different scales. Extensive experimental results on three commonly used datasets demonstrate that the proposed model achieves better performance compared to state- of-the-art (SOTA) methods.

Tensor Gaussian graphical models (GGMs), interpreting conditional independence structures within tensor data, have important applications in numerous areas. Yet, the available tensor data in one single study is often limited due to high acquisition costs. Although relevant studies can provide additional data, it remains an open question how to pool such heterogeneous data. In this paper, we propose a transfer learning framework for tensor GGMs, which takes full advantage of informative auxiliary domains even when non-informative auxiliary domains are present, benefiting from the carefully designed data-adaptive weights. Our theoretical analysis shows substantial improvement of estimation errors and variable selection consistency on the target domain under much relaxed conditions, by leveraging information from auxiliary domains. Extensive numerical experiments are conducted on both synthetic tensor graphs and brain functional connectivity network data, which demonstrates the satisfactory performance of the proposed method.

Optical endoscopy, as one of the common clinical diagnostic modalities, provides irreplaceable advantages in the diagnosis and treatment of internal organs. However, the approach is limited to the characterization of superficial tissues due to the strong optical scattering properties of tissue. In this work, a microwave-induced thermoacoustic (TA) endoscope (MTAE) was developed and evaluated. The MTAE system integrated a homemade monopole sleeve antenna (diameter = 7 mm) for providing homogenized pulsed microwave irradiation to induce a TA signal in the colorectal cavity and a side-viewing focus ultrasonic transducer (diameter = 3 mm) for detecting the TA signal in the ultrasonic spectrum to construct the image. Our MTAE, system combined microwave excitation and acoustic detection; produced images with dielectric contrast and high spatial resolution at several centimeters deep in soft tissues, overcome the current limitations of the imaging depth of optical endoscopy and mechanical wave-based imaging contrast of ultrasound endoscopy, and had the ability to extract complete features for deep location tumors that could be infiltrating and invading adjacent structures. The practical feasibility of the MTAE system was evaluated i n vivo with rabbits having colorectal tumors. The results demonstrated that colorectal tumor progression could be visualized from the changes in electromagnetic parameters of the tissue via MTAE, showing its potential clinical application.

Microwave-induced thermoacoustic imaging (MTAI) is a promising alternative for breast tumor detection due to its deep imaging depth, high resolution, and minimal biological hazards. However, due to the bulky size and complicated system configuration of conventional benchtop MTAI, it is limited to imaging various anatomical sites and its application in different clinical scenarios. In this study, a handheld MTAI system equipped with a compact impedance matching microwave-sono and an ergonomically designed probe was presented and evaluated. The probe integrates a flexible coaxial cable for microwave delivery, a miniaturized microwave antenna, a linear transducer array, and wedge-shaped polystyrene blocks for efficient acoustic coupling, achieving microwave illumination and ultrasonic detection coaxially, and enabling high signal-to-noise ratio (SNR). Phantom experiments demonstrated that the maximum imaging depth is 5 cm (SNR = 8 dB), and the lateral and axial resolutions are 1.5 mm and 0.9 mm, respectively. Finally, three healthy female volunteers of different ages were subjected to breast thermoacoustic tomography and ultrasound imaging. The results showed that the h-MTAI data are correlated with the data of ultrasound imaging, indicating the safety and effectiveness of the system. Thus, the proposed h-MTAI system might contribute to breast tumor screening.

SUMMARY: Heterogeneity is a hallmark of many complex human diseases, and unsupervised heterogeneity analysis has been extensively conducted using high-throughput molecular measurements and histopathological imaging features. 'Classic' heterogeneity analysis has been based on simple statistics such as mean, variance and correlation. Network-based analysis takes interconnections as well as individual variable properties into consideration and can be more informative. Several Gaussian graphical model (GGM)-based heterogeneity analysis techniques have been developed, but friendly and portable software is still lacking. To facilitate more extensive usage, we develop the R package HeteroGGM, which conducts GGM-based heterogeneity analysis using the advanced penaliztaion techniques, can provide informative summary and graphical presentation, and is efficient and friendly. AVAILABILITYAND IMPLEMENTATION: The package is available at https://CRAN.R-project.org/package=HeteroGGM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.