LCLingyu Chen

Lingyu Chen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lingyu Chen has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    GrayUI: A Visual Context Attack Framework Against VLM-Based Mobile Agents

    by Yawen Zeng, Dun Tan, Hantao Zheng, Lingyu Chen, Hao Chen, Ning Han

  • Gaussian Distribution-Based Dynamic Optimization for Capsule Robot Pose Estimation in Ultrasound Images

    by Yue Wang, Lingyu Chen, Yixuan Yang, Daoqiang Zhang, Hongen Liao, Fang Chen

    Harnessing the full potential of capsule robots requires highly precise and reliable pose estimation. This article presents a dynamic bounding box optimization strategy based on Gaussian similarity for accurately estimating the pose of capsule robots in ultrasound (US) images. Specifically, a robot-adaptive label assignment (RALA) strategy is developed to effectively extract features through learning the geometric properties of capsule robots. Subsequently, a novel bounding box representation (BBR) is presented to accommodate variations in position and orientation. In addition, a predicted boxes similarity metric, based on the elliptical Gaussian distributions, is proposed to achieve optimal bounding box similarity beyond the conventional intersection over union (IoU) metric. This metric not only mitigates the limitations of IoU in nonoverlapping cases but also provides a more refined basis for network optimization. Finally, a dynamic and adaptive optimization strategy is introduced to enhance estimation accuracy. A localization error of 0.11 mm and an angle error of 1.00° were achieved by the proposed model, demonstrating superior estimation accuracy. To evaluate the model’s generalizability, a private dataset reflecting real-world clinical scenarios more closely was constructed. Without any fine-tuning, the model trained solely on the public dataset yielded a localization error of 0.39 mm and an angle estimation error of 2.60° on the private dataset, confirming the robustness and generalization capability of the proposed model.

  • MEDSQ: Towards personalized medical education via multi-form interaction guidance

    by Yong Ouyang, Wenjin Gao, Huanwen Wang, Lingyu Chen, Jing Wang, Yawen Zeng


  • Thinking Like Sonographers: Human-Centered CNN Models for Gout Diagnosis From Musculoskeletal Ultrasound

    by Lingyu Chen, Zhi Cao, Weijing Zhang, Xin Tang, Di Zhao, Daoqiang Zhang, Hongen Liao, Fang Chen

    We explore the potential of deep convolutional neural network (CNN) models for differential diagnosis of gout from musculoskeletal ultrasound (MSKUS). Our exhaustive study of state-of-the-art (SOTA) CNN image classification models for this problem reveals that they often fail to learn the gouty MSKUS features, including the double contour sign, tophus, and snowstorm, which are essential for sonographers' decisions. In this study, we establish a human-centered adjusting framework to make CNN models diagnosis gout in the way of thinking like sonographers. This framework consists of three components: (1) Where to adjust: Modeling sonographers' attention map to emphasize the region that needs adjust; (2) What to adjust: Identifying MSKUS instances that mislead the model to predict according to unreasonable/biased features; (3) How to adjust: Developing a human-centered training fine-tuning mechanism that adjusts CNN models to focus on the desired MSKUS feature regions. This mechanism balances the gout prediction accuracy and attention reasonability by introducing the sonographers-like attention constraints. The experimental results on clinical MSKUS datasets demonstrate that our framework significantly outperforms the existing SOTA CNN models.


  • Do as Sonographers Think: Contrast-Enhanced Ultrasound for Thyroid Nodules Diagnosis via Microvascular Infiltrative Awareness

    by Fang Chen, Haojie Han, Peng Wan, Lingyu Chen, Wentao Kong, Hongen Liao, Baojie Wen, Chunrui Liu, Daoqiang Zhang

    Dynamic contrast-enhanced ultrasound (CEUS) imaging can reflect the microvascular distribution and blood flow perfusion, thereby holding clinical significance in distinguishing between malignant and benign thyroid nodules. Notably, CEUS offers a meticulous visualization of the microvascular distribution surrounding the nodule, leading to an apparent increase in tumor size compared to gray-scale ultrasound (US). In the dual-image obtained, the lesion size enlarged from gray-scale US to CEUS, as the microvascular appeared to be continuously infiltrating the surrounding tissue. Although the infiltrative dilatation of microvasculature remains ambiguous, sonographers believe it may promote the diagnosis of thyroid nodules. We propose a deep learning model designed to emulate the diagnostic reasoning process employed by sonographers. This model integrates the observation of microvascular infiltration on dynamic CEUS, leveraging the additional insights provided by gray-scale US for enhanced diagnostic support. Specifically, temporal projection attention is implemented on time dimension of dynamic CEUS to represent the microvascular perfusion. Additionally, we employ a group of confidence maps with flexible Sigmoid Alpha Functions to aware and describe the infiltrative dilatation process. Moreover, a self-adaptive integration mechanism is introduced to dynamically integrate the assisted gray-scale US and the confidence maps of CEUS for individual patients, ensuring a trustworthy diagnosis of thyroid nodules. In this retrospective study, we collected a thyroid nodule dataset of 282 CEUS videos. The method achieves a superior diagnostic accuracy and sensitivity of 89.52% and 93.75%, respectively. These results suggest that imitating the diagnostic thinking of sonographers, encompassing dynamic microvascular perfusion and infiltrative expansion, proves beneficial for CEUS-based thyroid nodule diagnosis.


  • Open Access

    Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment

    by Zihao Li, Meini Wu, Changhao Yin, Zhenqi Wang, Jianhang Wang, Lingyu Chen, Weina Zhao

    Background: Vascular cognitive impairment (VCI) is a major cause of cognitive impairment in the elderly and a co-factor in the development and progression of most neurodegenerative diseases. With the continuing development of neuroimaging, multiple markers can be combined to provide richer biological information, but little is known about their diagnostic value in VCI.Methods: A total of 83 subjects participated in our study, including 32 patients with vascular cognitive impairment with no dementia (VCIND), 21 patients with vascular dementia (VD), and 30 normal controls (NC). We utilized resting-state quantitative electroencephalography (qEEG) power spectra, structural magnetic resonance imaging (sMRI) for feature screening, and combined them with support vector machines to predict VCI patients at different disease stages.Results: The classification performance of sMRI outperformed qEEG when distinguishing VD from NC (AUC of 0.90 vs. 0,82), and sMRI also outperformed qEEG when distinguishing VD from VCIND (AUC of 0.8 vs. 0,0.64), but both underperformed when distinguishing VCIND from NC (AUC of 0.58 vs. 0.56). In contrast, the joint model based on qEEG and sMRI features showed relatively good classification accuracy (AUC of 0.72) to discriminate VCIND from NC, higher than that of either qEEG or sMRI alone.Conclusion: Patients at varying stages of VCI exhibit diverse levels of brain structure and neurophysiological abnormalities. EEG serves as an affordable and convenient diagnostic means to differentiate between different VCI stages. A machine learning model that utilizes EEG and sMRI as composite markers is highly valuable in distinguishing diverse VCI stages and in individually tailoring the diagnosis.


  • TSM: Three-Stream Mix For Unsupervised Medical Image Registration

    by Zhen Gu, Daoqiang Zhang, Fang Chen, Peng Wan, Lingyu Chen

    Medical image registration is a crucial preprocessing step in medical image processing. Due to the potential impact of treatments and disease progression on patients' organ geometry, such as in magnetic resonance imaging (MRI) and computed tomography (CT) images, medical image registration is of significant importance for cancer diagnosis, treatment planning, and therapy. Existing methods usually adopt convolutional neural networks and Transformer frameworks, but still face challenges to effectively solve both tissue robustness and registration accuracy. Therefore, we propose TSM, a hybrid Transformer-Convolution model, for non-rigid registration of volumetric medical multi-tissue images. We perform dynamic global filtering convolution in the frequency domain and multi-scale parallel convolution, capturing local tissue structure information; meanwhile, we use a special attention combination mechanism to obtain semantic associations among tissue structures. We evaluate our method on the publicly available LPBA40 and EMPIRE10 challenge datasets. With comparison of the state-of-the-arts, we improve the dice score by 1.2% on the LPBA40 dataset and by 3% on the EMPIRE10 dataset, achieving the best registration results.


  • Deep Semi-Supervised Ultrasound Image Segmentation by Using a Shadow Aware Network With Boundary Refinement

    by Fang Chen, Lingyu Chen, Wentao Kong, Weijing Zhang, Pengfei Zheng, Liang Sun, Daoqiang Zhang, Hongen Liao

    Accurate ultrasound (US) image segmentation is crucial for the screening and diagnosis of diseases. However, it faces two significant challenges: 1) pixel-level annotation is a time-consuming and laborious process; 2) the presence of shadow artifacts leads to missing anatomy and ambiguous boundaries, which negatively impact reliable segmentation results. To address these challenges, we propose a novel semi-supervised shadow aware network with boundary refinement (SABR-Net). Specifically, we add shadow imitation regions to the original US, and design shadow-masked transformer blocks to perceive missing anatomy of shadow regions. Shadow-masked transformer block contains an adaptive shadow attention mechanism that introduces an adaptive mask, which is updated automatically to promote the network training. Additionally, we utilize unlabeled US images to train a missing structure inpainting path with shadow-masked transformer, which further facilitates semi-supervised segmentation. Experiments on two public US datasets demonstrate the superior performance of the SABR-Net over other state-of-the-art semi-supervised segmentation methods. In addition, experiments on a private breast US dataset prove that our method has a good generalization to clinical small-scale US datasets.


  • Open Access

    NLRP3 inflammasome inhibitor MCC950 attenuates primary dysmenorrhea in mice via the NF-κB/COX-2/PG pathway

    by Biao Tang, Dan Liu, Lingyu Chen, Yu Liu

    Background: Primary dysmenorrhea (PD) constitutes a common gynecological disease among young women. The NLRP3 inflammasome may be activated and expressed in PD, but the mechanistic link between NLRP3 inflammasome activation and PD is still unclear. Methods: To investigate the potential role of NLRP3 inflammasome activation in the pathogenesis of PD, 30 female Kunming mice without pregnancy were used for experiments. The PD mouse model was constructed by 11 days of successive co-treatment with estradiol and oxytocin. MCC950, a potent and specific small-molecule inhibitor of the NLRP3 inflammasome, was used to treat PD mice. The disease level was assessed by the writhing response and hot water tail-flick test. The levels of prostaglandin E2 (PGE2) and prostaglandin F2 alpha (PGF2α) in the uterine tissues of mice were detected by ELISA. The expression levels of protein and cytokines, including NLRP3, cysteine aspartic acid-specific protease 1 (caspase-1), interleukin (IL)-1β, IL-18, nuclear factor kappa B (NF-κB) p65, phospho-NF-κB p65, and cyclooxygenase-2 (COX-2) were revealed by western blot analysis. Results: MCC950 greatly ameliorated the writhing response induced by the combination of oxytocin and estradiol, with an increasing length of tail-flick latency. MCC950 also significantly decreased the levels of PGF2α and PGE2, and the expressions of NLRP3, caspase-1, IL-1β, IL-18, phospho-NF-κB p65, NF-κB p65, and COX-2 in the uterus. Conclusions: MCC950 markedly alleviated the pain and pathological damage in PD mice by inhibiting NLRP3 activation. The underlying mechanism may be related to hypoactive uterine inflammation via suppression of NLRP3 activation and the NF-κB/COX-2/PG pathway in uteruses of PD mice.