Singapore, Singapore
Hi Linkedin community! I'm currently pursuing a Master's degree in Biomedical Engineering at the National University of Singapore, with an expected graduation date in 2025. I am a highly motivated and enthusiastic individual. Possessing a multidisciplinary engineering background, I have developed core competencies in programming languages such as Python, Java, C, and MATLAB, as well as proficiency in and various software tools. My professional experiences include significant contributions to deep learning and computational modeling projects, showcasing a capacity for innovative research in medical imaging. With a solid foundation in both theoretical knowledge and practical application, I seek an full time job opportunity to further explore and contribute to the field of biomedical engineering and data analytics.
Pathology Image Analysis Framework Development: Contributed to UnPuzzle, a unified framework for computational pathology research. Successfully implemented 7 slide-level deep learning models (e.g., ABMIL, DSMIL, DTFD) as backbone architectures for pathology image analysis. Assisted in integrating pre-processing pipelines and benchmarking workflows to ensure model reproducibility and standardization across different datasets. Multi-Task Learning & Model Pruning for WSI Analysis: Investigated the hierarchical labeling challenge in whole-slide imaging (WSI) and applied multi-task learning (MTL) to improve model generalization across multiple pathology tasks. Implemented model pruning techniques to optimize computational efficiency while preserving predictive accuracy, reducing redundant parameters to enhance training convergence with limited labeled data. Autophagy State Classification in Lung Cancer Cells (UCL Collaboration): Collaborated with University College London (UCL) on a deep learning-based study to classify autophagy states in A549 lung cancer cells. Processed and analyzed morphological patterns from non-specific stain images, and contributed to model validation using expert-labeled datasets.
Industry Analysis: Conducted market research on AI-driven medical imaging, analyzing market trends, competitive landscape, and key commercialization challenges. Expert Interviews: Engaged with senior physicians, AI product specialists, and industry leaders through structured interviews to identify core technological bottlenecks and market demands. Regulatory & Policy Research: Examined healthcare policies, public procurement data, and industry regulations to evaluate adoption barriers and future development opportunities.