Underwater sonar imaging is a key technology in modern ocean exploration and maritime defense. However, distortions often occur during transmission or compression due to the harsh underwater communication environment. These distortions can severely degrade image quality. Therefore, implementing Sonar Image Quality Assessment (SIQA) of transmitted images is crucial to ensure their reliable performance in downstream tasks. In practice, collecting large-scale annotated sonar datasets is both costly and challenging, and high-quality reference images are often unavailable. Therefore, SIQA methods must be reference-free and independent of training data. To address this challenge, we introduce a novel zero-shot SIQA paradigm, where task-oriented image quality is defined by the magnitude of semantic shift under contour degradation. High-quality images, with clearer contours, exhibit larger semantic shifts when perturbed; in contrast, low-quality images with blurred structures show smaller shifts. We simulate contour degradation by filtering the mid-frequency components and quantify the resulting semantic shift using cosine similarity. This approach bypasses conventional feature engineering and regression-based modeling, directly using the measured semantic shift as the quality score, thereby enabling zero-shot evaluation. Experiments on sonar datasets show that our method outperforms existing zero-shot IQA baselines and demonstrates strong potential for practical application.

A CM2-S3 transmission link in wireless body area networks (WBAN) is implemented with a joint source channel coding (JSCC) system based on double protograph low-density parity-check (DP-LDPC) code pairs with high reliability and low power consumption. For the practicality and suitability considerations, the$M$-ary differential chaos shift keying scheme is introduced to modulate the CM2-S3 channel with better performance than the standard modulations in WBAN. Due to the non-Gaussian-like distribution of the CM2-S3 channel model, the initial joint protograph extrinsic information transfer (JPEXIT) algorithm does not work as a coding analysis tool. To solve this problem, a numerical Gaussian approximation is employed to modify the iterative mutual information function of the JPEXIT for achieving more precise output. Then, a joint code rate compatible (JCRC) method, designed with compatibility in resisting variable channel variances and adapting different source statistics, is proposed for optimizing the DP-LDPC code pairs. Based on the JCRC method, the code searching algorithm is simplified with lower complexity because of the reduced cycle-index. The simulation results show that optimized code pairs have better bit-error ratio performances compared to existing codes, which provides a strong technical support to promote high-quality data transmission in eHealthcare on the physical layer.

This paper proposes a novel fully automatic diagnosis method for liver cirrhosis based on the reading of high-frequency ultrasound images. The proposed method determines the cirrhosis stage via a deep-learning neural network. First, we feed an ultrasound image into an autoencoder to generate the capsule-enhanced version of the image and binarize the enhanced image. Then, we employ a partition-clustering algorithm to obtain the top-end largest-area partition cluster, which represents the upper layer of the liver, and thereby locate the final liver capsule based on least-squares polynomial fitting. After separating the parenchymal region from the image, we use the proposed residual neural network to determine the cirrhosis stage. Experimental results demonstrate the high accuracy and effectiveness of the proposed method, which outperforms five other state-of-the-art methods. The proposed method is expected to improve the efficiency and accuracy of the clinical diagnosis of liver cirrhosis.