Bio

I am an Assistant Professor in the Department of Cognitive Sciences and Artificial Intelligence. My research focuses on artificial intelligence for image and video analysis.  In particular, I am interested in segmentation of biomedical images and tracking of multiple agents to automatically extract insightful information and to create computational models.

Prior to joining Tilburg University, I was a Research Scientist at the Singapore-MIT Alliance for Research and Technology (SMART) Centre in the BioSystems and Micromechanics (BioSyM) interdisciplinary research group. I received my PhD degree in Field Robotics from the University of Sydney, Australia in 2008. I received a Bachelor of Engineering (Mechatronics) from the University of Sydney in 2003. 

Expertise

Image Analysis, Object Tracking, Information Fusion, Machine Learning, Stochastic Filtering, Bayesian Estimation

Courses

Recent publications

  1. Genetic Classification of Accented Speech from Audio Recordings of Sp…

    Go, G., Roncaglia, P., & Ong, S. (2023). Genetic Classification of Accented Speech from Audio Recordings of Spoken Nonsense Words. Abstract from 35rd Benelux Conference on Artificial Intelligence and the 32th Belgian Dutch Conference on Machine Learning, Delft , Netherlands. https://bnaic2023.tudelft.nl/static/media/BNAICBENELEARN_2023_paper_127.a170261bf03a53c463a6.pdf
  2. Musculoskeletal radiologist-level performance by using deep learning …

    Hendrix, N., Hendrix, W., van Dijke, K., Maresch, B., Maas, M., Bollen, S., Scholtens, A., de Jonge, M., Ong, L. L. S., van Ginneken, B., & Rutten, M. (2023). Musculoskeletal radiologist-level performance by using deep learning for detection of scaphoid fractures on conventional multi-view radiographs of hand and wrist. European Radiology, 33(3), 1575-1588.
  3. Deep Learning Classifiers to Reduce False Positives in Osteolytic Les…

    Jadikar, M., van Leeuwen, M., van Oudheusden, T., Oei, S., Steunenberg, B., Kint, R., Ranschaert, E., Bosma, G., Saygili, G., & Ong, S. (2023). Deep Learning Classifiers to Reduce False Positives in Osteolytic Lesion Segmentation Results from Low-dose CT Scans of Multiple Myeloma. Paper presented at 35rd Benelux Conference on Artificial Intelligence and the 32th Belgian Dutch Conference on Machine Learning, Delft , Netherlands. https://bnaic2023.tudelft.nl/static/media/BNAICBENELEARN_2023_paper_65.7e5de9cf01a9bf3f4bc8.pdf
  4. Predicting Vasovagal Reactions to Needles from Facial Action Units

    Rudokaite, J., Ertugrul, I. O., Ong, S., Janssen, M. P., & Huis in 't Veld, E. (2023). Predicting Vasovagal Reactions to Needles from Facial Action Units. Journal of Clinical Medicine, 12(4), 1-14. Article 1644.
  5. A deep learning-based approach to detect and segment osteolytic bone …

    Ong, S., van Leeuwen, M., Saygili, G., Hoff , W., Heres, M., van Oudheusden, T., Steunenberg, B., Kint, R., Bosma, G., & Ranschaert, E. (2022). A deep learning-based approach to detect and segment osteolytic bone lesions in whole-body, low-dose CT imaging of multiple myeloma patients. Poster session presented at EuSoMII Annual Meeting 2022 ‘Your portal to AI’, Valencia, Spain.

Find an expert or expertise