You can also find my articles on Google Scholar. * means equal contribution.


  1. W. Chen, K. Mehta, B. D. Bhanushali, J. Galeotti, Ultrasound-based Tracking of Partially In-plane, Curved Needles. 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, 2021, pp. 939-943. link

    We propose a novel curve needle tracking method which utilizes a novel weighted RANSAC and probabilistic Hough transform with kinematics reference to track a curved and partially visible needle in ultrasound images. The method works robustly and outperforms RANSAC, probabilistic Hough transform, and deep-learning based model in tracking a pre-bent needle in ultrasound phantom, and in tracking a naturally bent needle in actual tissue.

  2. A. L. Y. Hung, W. Chen, J. Galeotti, Ultrasound Confidence Maps of Intensity and Structure Based on Directed Acyclic Graphs and Artifact Models. 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, 2021, pp. 697-701. link

    We use a direct acyclic graph-based method to analyize the pixel confidence in ultrasound images. We demonstrate unique capabilities of our approach and compare it against previous confidence-measurement algorithms for shadow-detection and image-compounding tasks.

  3. J. Mai, W. Chen, S. Zhang, D. Xu and Q. Wang, Performance analysis of hardware acceleration for locomotion mode recognition in robotic prosthetic control. 2018 IEEE International Conference on Cyborg and Bionic Systems (CBS), Shenzhen, China, 2018, pp. 607-611. link

    We analyze the computing performance of an on-board locomotion mode recognition system which was designed for robotic transtibial prosthesis. We implemented FPGA on-board support vector machine, back-propagation neural network, quadratic discriminant analysis and linear discriminant analysis, and the experiments demonstrated that the proposed system can provide satisfactory acceleration effects on the four applied algorithms.


  1. Q. Wang et al., An Underwater Lower-Extremity Soft Exoskeleton for Breaststroke Assistance. IEEE Transactions on Medical Robotics and Bionics, vol. 2, no. 3, pp. 447-462, Aug. 2020. link

    We designed an underwater lower-extremity soft exoskeleton called Powered Swimsuit to assist the wearer in breaststroke with fins. The assistive force was applied to the bottom of the fins via soft cables. During the propelling period of the stroke cycle, the cables pulled the ankle joints to provide assistance to plantar flexion.

  2. Y. Feng*, W. Chen*, and Q. Wang, A strain gauge based locomotion mode recognition method using convolutional neural network. Advanced Robotics, vol. 33, no. 5, pp. 254-263, Jan. 2019. link

    We propose a novel locomotion mode recognition method based on convolutional neural network and strain gauge signals. The overall three-class locomotion mode recognition accuracy shows that the strain gauge contains information of locomotion modes, and the convolutional neural network has the capacity of extracting features from raw signals.


  1. A. L. Y. Hung, Z. Sun, W. Chen, J. Galeotti, Hierarchical Probabilistic Ultrasound Image Inpainting via Variational Inference. Deep Generative Models, and Data Augmentation, Labelling, and Imperfections (DGM4MICCAI), 2021, pp. 83-92. link

  2. G. R. Gare*, W. Chen*, A. L. Y. Hung, E. Chen, H. V. Tran, T. Fox, P. Lowery, K. Zamora, B. P. deBoisblanc, R. L. Rodriguez, J. Galeotti, The Role of Pleura and Adipose in Lung Ultrasound AI. MICCAI 2021 workshop on Lessons Learned from the development and application of medical imaging-based AI technologies for combating COVID-19, 2021, PP. 141-149. link

Master Thesis

  1. W. Chen, Ultrasound-based Needle Tracking and Lateral Manipulation Planning for Common Needle Steering. Carnegie Mellon University, 2021. link