Imaging/computer vision scientist on applying artificial intelligence to cancer precision medicine. My research includes applying machine learning & deep learning techniques to optical coherence tomography (OCT) spectral analysis and clinical imaging applications, demonstrating in vivo multi-functional imaging by visible and infrared light OCT, and modeling & simulating light-tissue interactions in physiological environment. • Professional in deep/machine learning techniques including fully-connected neural networks (FCN), convolutional neural networks (CNN), residual neural network (ResNet), generative adversarial networks (GAN), CNN model interpretations, strongly/weakly supervised learning, expectation-maximization (EM) algorithms, random forest, large-scale data analysis, data cleaning, anomaly detection, similarity analysis, and predicative modeling. • Skilled in Python, Pytorch, OpenCV, Keras, TensorFlow, Scikit-learn, Pandas, NumPy, Seaborn, Matplotlib, Docker, AWS, SQL, Matlab, and Mathematica. • Expertise in developing and optimizing algorithms for OCT angiography and vessel segmentation, OCT spectral analysis, OCT functional imaging (e.g., oxygen saturation, blood flow rate, oxygen delivery rate, oxygen metabolic rate, etc.), and OCT ultrastructure imaging. • Experienced in modeling and simulating light scattering and absorption in discrete particles and continuous media like biological tissues. • Hands-on experimental experience with optical imaging system and small animal models.