An ultrasound image-based deep multi-scale texture network for liver fibrosis grading in patients with chronic HBV infection.

BACKGROUND & AIMS: The evaluation of the stage of liver fibrosis is essential in patients with chronic liver disease. However, due to the low quality of ultrasound images, the non-invasive diagnosis of liver fibrosis based on ultrasound images is still an outstanding question. This study aimed to investigate the diagnostic accuracy of a deep learning-based method in ultrasound images for liver fibrosis staging in multicentre patients. METHODS: In this study, we proposed a novel deep learning-based approach, named multi-scale texture network (MSTNet), to assess liver fibrosis, which extracted multi-scale texture features from constructed image pyramid patches. Its diagnostic accuracy was investigated by comparing it with APRI, FIB-4, Forns and sonographers. Data of 508 patients who underwent liver biopsy were included from 4 hospitals. The area-under-the ROC curve (AUC) was determined by receiver operating characteristics (ROC) curves for significant fibrosis (≥F2) and cirrhosis (F4). RESULTS: The AUCs (95% confidence interval) of MSTNet were 0.92 (0.87-0.96) for ≥F2 and 0.89 (0.83-0.95) for F4 on the validation group, which significantly outperformed APRI, FIB-4 and Forns. The sensitivity and specificity of MSTNet (85.1% (74.5%-92.0%) and 87.6% (78.0%-93.6%)) were better than those of three sonographers in assessing ≥F2. CONCLUSIONS: The proposed MSTNet is a promising ultrasound image-based method for the non-invasive grading of liver fibrosis in patients with chronic HBV infection.

Spatially-Aware Context Neural Networks.

A variety of computer vision tasks benefit significantly from increasingly powerful deep convolutional neural networks. However, the inherently local property of convolution operations prevents most existing models from capturing long-range feature interactions for improved performances. In this paper, we propose a novel module, called Spatially-Aware Context (SAC) block, to learn spatially-aware contexts by capturing multi-mode global contextual semantics for sophisticated long-range dependencies modeling. We enable customized non-local feature interactions for each spatial position through re-weighted global context fusion in a non-normalized way. SAC is very lightweight and can be easily plugged into popular backbone models. Extensive experiments on COCO, ImageNet, and HICO-DET benchmarks show that our SAC block achieves significant performance improvements over existing baseline architectures while with a negligible computational burden increase. The results also demonstrate the exceptional effectiveness and scalability of the proposed approach on capturing long-range dependencies for object detection, segmentation, and image classification, outperforming a bank of state-of-the-art attention blocks.

Validity of scalar diffraction theory and effective medium theory for analysis of a blazed grating microstructure at oblique incidence.

The accuracy of scalar diffraction theory (SDT) and effective medium theory (EMT) for analyzing a blazed grating is quantitatively demonstrated by making a comparison of diffraction efficiencies calculated by the two simplified methods to exact results from the Fourier modal method (FMM). It is found that when the normalized period is more than fivefold wavelength of incident light at normal incidence and is more than about tenfold wavelength at larger incident angle, SDT can be used to easily analyze effectively the transmittance characteristics of a blazed grating with divergence less than 1%. Particularly, for zeroth-order diffraction when the groove depth is less than threefold wavelength, the transmittance calculated by SDT with refractive index of 1.5 and normalized period of 5.0 agrees well with that of FMM at normal incidence. But, for ±1 orders, the validity of SDT is degraded from that for zeroth order. Generally, the deviation of transmittances between the SDT and the FMM increases as the incident angle and refractive index augment. Furthermore, when higher diffraction orders other than zeroth order are not propagating, the EMT is valid to evaluate the transmittance of a blazed grating at normal incidence. Similarly, the error of transmittances between the EMT and the FMM increases with the increase of incident angle and refractive index. The effectiveness of the SDT and the EMT for analyzing a blazed grating in the range of the normalized period far more than and less than the wavelength of incident light, respectively, is dependent on the parameters including incident angle, refractive index, normalized period, and normalized groove depth.