Yeying Qin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yeying Qin has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Pak Kin Wong
University of Macau
4 shared publications - In Neng Chan
Department of Electromechanical Engineering, University of Macau, Macao, Macao
2 shared publications - Liang Yao
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
2 shared publications Tao Yan
2 shared publicationsYun Zhang
2 shared publicationsBaoliang Zhao
1 shared publication
Latest Publications
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Robotics and Bionics
- Vol. PP (3) , 1
Safe Variable Force Control for Robotic Ultrasound Scanning via ℓ 2 -Regularized Fuzzy Broad Offline Reinforcement Learning
Robotic ultrasound scanning (RUSS) is a promising technology for standardizing examinations, improving repeatability, and alleviating the workload of sonographers. A key prerequisite for its safe clinical use is reliable control of the contact force between the probe and the patient’s skin. In practice, this force should vary along the scan: it must be reduced over symptomatic or painful regions to avoid discomfort and potential tissue damage, while remaining sufficiently high elsewhere to ensure good acoustic coupling and image quality. Patient-specific soft-tissue properties and unstructured examination environments make it difficult to tune conventional (adaptive) impedance controllers, often leading to force overshoot or poor tracking performance. To address this challenge, we propose an ℓ2-regularized fuzzy broad offline reinforcement learning framework (ℓ2-FBORL) that learns variable force control policies from limited, suboptimal demonstrations generated by stabilizing controllers. Building on ℓ2-FBORL, we formulate variable force tracking in RUSS as a Markov decision process and develop a Fuzzy Learning-based Adaptive Impedance Control (FLAIC) scheme that adaptively adjusts the impedance adaptation rate to suppress overshoot while maintaining fast convergence. The proposed approach is evaluated in high-fidelity simulation, phantom experiments, and in vivo upper-limb venous and abdominal scanning under respiratory motion. Across all scenarios, FLAIC reduces force overshoot and improves tracking accuracy compared with conventional impedance and adaptive impedance controllers, without patient-specific retuning, indicating its potential to enhance the safety, robustness, and standardization of robotic ultrasound procedures.
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Robotics and Bionics
- Vol. PP (3) , 1
Safe Variable Force Control for Robotic Ultrasound Scanning via ℓ 2 -Regularized Fuzzy Broad Offline Reinforcement Learning
Robotic ultrasound scanning (RUSS) is a promising technology for standardizing examinations, improving repeatability, and alleviating the workload of sonographers. A key prerequisite for its safe clinical use is reliable control of the contact force between the probe and the patient’s skin. In practice, this force should vary along the scan: it must be reduced over symptomatic or painful regions to avoid discomfort and potential tissue damage, while remaining sufficiently high elsewhere to ensure good acoustic coupling and image quality. Patient-specific soft-tissue properties and unstructured examination environments make it difficult to tune conventional (adaptive) impedance controllers, often leading to force overshoot or poor tracking performance. To address this challenge, we propose an ℓ2-regularized fuzzy broad offline reinforcement learning framework (ℓ2-FBORL) that learns variable force control policies from limited, suboptimal demonstrations generated by stabilizing controllers. Building on ℓ2-FBORL, we formulate variable force tracking in RUSS as a Markov decision process and develop a Fuzzy Learning-based Adaptive Impedance Control (FLAIC) scheme that adaptively adjusts the impedance adaptation rate to suppress overshoot while maintaining fast convergence. The proposed approach is evaluated in high-fidelity simulation, phantom experiments, and in vivo upper-limb venous and abdominal scanning under respiratory motion. Across all scenarios, FLAIC reduces force overshoot and improves tracking accuracy compared with conventional impedance and adaptive impedance controllers, without patient-specific retuning, indicating its potential to enhance the safety, robustness, and standardization of robotic ultrasound procedures.
- Open Access
- 30 January 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3474
Automatic medical report generation: a comprehensive review of methodologies and applications
The increasing demand for medical imaging has significantly challenged healthcare systems, emphasizing the need for efficient and accurate diagnostic support tools. Recent advancements in computer vision (CV) and natural language processing (NLP) have demonstrated great promise in addressing these challenges, particularly through the automation of medical report generation. Automatic medical report generation (AMRG) has become a pivotal application of artificial intelligence (AI) in the medical domain, which involves extracting critical information from medical images and generating textual reports. These reports aid clinicians in analyzing image content more efficiently and accurately, thereby improving diagnostic precision. This article provides a comprehensive review of recent advancements in AMRG, with a particular focus on the commonly—employed methodologies, including convolutional neural network (CNN), recurrent neural network (RNN), Transformers and their variants, and large language model (LLM) into AMRG. Moreover, this review also examines both widely—used and less frequently-used datasets and compares various evaluation metrics to provide an in-depth analysis of different AMRG methodologies. Finally, key achievements and future research directions in the field are summarized, highlighting challenges such as cross-modal fusion, model interpretability, and data privacy protection, while suggesting potential future trends in the development of this technology.
- 30 January 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3474
Open AccessAutomatic medical report generation: a comprehensive review of methodologies and applications
The increasing demand for medical imaging has significantly challenged healthcare systems, emphasizing the need for efficient and accurate diagnostic support tools. Recent advancements in computer vision (CV) and natural language processing (NLP) have demonstrated great promise in addressing these challenges, particularly through the automation of medical report generation. Automatic medical report generation (AMRG) has become a pivotal application of artificial intelligence (AI) in the medical domain, which involves extracting critical information from medical images and generating textual reports. These reports aid clinicians in analyzing image content more efficiently and accurately, thereby improving diagnostic precision. This article provides a comprehensive review of recent advancements in AMRG, with a particular focus on the commonly—employed methodologies, including convolutional neural network (CNN), recurrent neural network (RNN), Transformers and their variants, and large language model (LLM) into AMRG. Moreover, this review also examines both widely—used and less frequently-used datasets and compares various evaluation metrics to provide an in-depth analysis of different AMRG methodologies. Finally, key achievements and future research directions in the field are summarized, highlighting challenges such as cross-modal fusion, model interpretability, and data privacy protection, while suggesting potential future trends in the development of this technology.
- Open Access
- 27 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 26-33
Lightweight Deep Learning for Real-Time Multi-Task Analysis of Upper Endoscopic Videos
- 27 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 26-33
Open AccessLightweight Deep Learning for Real-Time Multi-Task Analysis of Upper Endoscopic Videos