Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hongyu Kang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Novel Dual-Modality Dual-View Hybrid Deep Learning–Machine Learning Framework for the Prediction of Carotid Plaque Vulnerability via Late Fusion

    by Wenxuan Zhang, Chao Hou, Xinyi Wang, Hongyu Kang, Shuai Li, Yu Sun, Yongping Zheng, Wei Zhang, Sai-Kit Lam

    Background: Ultrasound imaging is an ideal tool for regular carotid plaque screening to identify individuals at high risk of stroke for clinical intervention. However, no existing study leverages multi-modal multi-view ultrasound imaging for AI-enabled auto-classification of carotid plaque vulnerability. This study aims to develop and validate an effective AI model for carotid plaque vulnerability classification through the applications of dual-modal (B-Mode and contrast-enhanced mode) dual-view (longitudinal and cross-sectional) settings to maximize the utility and potential of ultrasound imaging. Methods: Hybrid deep-learning (DL) and machine-learning (ML) methods were employed to balance between model discriminability and interpretability. B-Mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) images from 241 patients were retrospectively analyzed using the proposed hybrid-DL-ML variants. Results: Our findings suggest the hybrid VGG-RF model developed from a dual-modal dual-view setting outperforms those developed from other settings for identifying vulnerable carotid plaques. The VGG-RF model emerged as the best-performing model, achieving an optimal performance with an AUC of 0.908, precision of 0.765, recall of 0.929, specificity of 0.886, and F1 score of 0.839. The inherent interpretability of the VGG-RF model divulged that long-axis views of BMUS and CEUS images were the major contributing features for discriminating vulnerable carotid plaques against their counterparts. Conclusions: The present study underscored the effectiveness of AI models developed from dual-modal dual-view settings of ultrasound images. Notably, the hybrid VGG-RF model was benchmarked as the best-performing model among other studied hybrid DL-ML variants. Further studies on a larger cohort in a prospective setting are warranted to validate the findings of the current study.


  • Open Access

    Rectus Femoris Muscle Segmentation on Ultrasound Images of Older Adults Using Automatic Segment Anything Model, nnU-Net and U-Net—A Prospective Study of Hong Kong Community Cohort

    by Dawei Zhang, Hongyu Kang, Yu Sun, Justina Yat Wa Liu, Ka-Shing Lee, Zhen Song, Jien Vei Khaw, Jackie Yeung, Tao Peng, Sai-Kit Lam, et al.

    Sarcopenia is characterized by a degeneration of muscle mass and strength that incurs impaired mobility, posing grievous impacts on the quality of life and well-being of older adults worldwide. In 2018, a new international consensus was formulated to incorporate ultrasound imaging of the rectus femoris (RF) muscle for early sarcopenia assessment. Nonetheless, current clinical RF muscle identification and delineation procedures are manual, subjective, inaccurate, and challenging. Thus, developing an effective AI-empowered RF segmentation model to streamline downstream sarcopenia assessment is highly desirable. Yet, this area of research readily goes unnoticed compared to other disciplines, and relevant research is desperately wanted, especially in comparison among traditional, classic, and cutting-edge segmentation networks. This study evaluated an emerging Automatic Segment Anything Model (AutoSAM) compared to the U-Net and nnU-Net models for RF segmentation on ultrasound images. We prospectively analyzed ultrasound images of 257 older adults (aged > 65) in a community setting from Hong Kong’s District Elderly Community Centers. Three models were developed on a training set (n = 219) and independently evaluated on a testing set (n = 38) in aspects of DICE, Intersection-over-Union, Hausdorff Distance (HD), accuracy, precision, recall, as well as stability. The results indicated that the AutoSAM achieved the best segmentation agreement in all the evaluating metrics, consistently outperforming the U-Net and nnU-Net models. The results offered an effective state-of-the-art RF muscle segmentation tool for sarcopenia assessment in the future.


  • Open Access

    Automatic Transcranial Sonography-Based Classification of Parkinson’s Disease Using a Novel Dual-Channel CNXV2-DANet

    by Hongyu Kang, Xinyi Wang, Yu Sun, Shuai Li, Xin Sun, Fangxian Li, Chao Hou, Sai-Kit Lam, Wei Zhang, Yong-Ping Zheng

    Transcranial sonography (TCS) has been introduced to assess hyper-echogenicity in the substantia nigra of the midbrain for Parkinson’s disease (PD); however, its subjective and resource-demanding nature has impeded its widespread application. An AI-empowered TCS-based PD classification tool is greatly demanding, yet relevant research is severely scarce. Therefore, we proposed a novel dual-channel CNXV2-DANet for TCS-based PD classification using a large cohort. A total of 1176 TCS images from 588 subjects were retrospectively enrolled from Beijing Tiantan Hospital, encompassing both the left and right side of the midbrain for each subject. The entire dataset was divided into a training/validation/testing set at a ratio of 70%/15%/15%. Development of the proposed CNXV2-DANet was performed on the training set with comparisons between the single-channel and dual-channel input settings; model evaluation was conducted on the independent testing set. The proposed dual-channel CNXV2-DANet was compared against three state-of-the-art networks (ConvNeXtV2, ConvNeXt, Swin Transformer). The results demonstrated that both CNXV2-DANet and ConvNeXt V2 performed more superiorly under dual-channel inputs than the single-channel input. The dual-channel CNXV2-DANet outperformed the single-channel, achieving superior average metrics for accuracy (0.839 ± 0.028), precision (0.849 ± 0.014), recall (0.845 ± 0.043), F1-score (0.820 ± 0.038), and AUC (0.906 ± 0.013) compared with the single channel metrics for accuracy (0.784 ± 0.037), precision (0.817 ± 0.090), recall (0.748 ± 0.093), F1-score (0.773 ± 0.037), and AUC (0.861 ± 0.047). Furthermore, the dual-channel CNXV2-DANet outperformed all other networks (all p-values < 0.001). These findings suggest that the proposed dual-channel CNXV2-DANet may provide the community with an AI-empowered TCS-based tool for PD assessment.