· 3D MRI Brain Tumor Segmentation Image Analysis Using Deep Learning, Encoder-Decoder Based TensorFlow, CNN Architecture, ResNet Blocks, Variational Autoencoder (VAE), Augmentation Techniques With 90% Dice Coefficient Accuracy for 2000 images.
· Using Transcriptome Sequencing (RNA-seq) Genomic Data to Analyze the Differences Between Gene Expression in Fetal and Adult Brains Using Tuxido Tools, R Bioconductor, BioPython, Unix Command Line Tools with 95% Significance Level.
· Detecting Parkinson's Disease with XGBoost Using XGBoost Machine Learning Algorithm, Scikit Learn, Numpy, Pandas with 95 % Accuracy.
· Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis Using Transfer Learning, Inception ResNetV2, CNN Network, Augmentation Techniques With 85 % Accuracy for 2400 Images.
· Brain Tumor Auto-Segmentation for Magnetic Resonance Imaging (MRI) Using Deep Learning, 3D U-net based TensorFlow, GPU, CNN Architecture, Augmentation Techniques With 87 % Dice Coefficient Accuracy for 2300 Images.
· Computational and Statistical Analysis of Microscopic Images Using ImageJ, Python and MATLAB Resulted in the prediction of Protein Functions with 95% Significance Level for 4500 Images.
· Genomic Data Science (Johns Hopkins University)
· Machine Learning (Stanford University)
· Data Science in Python (University of Michigan)
· Machine Learning with Python (University of Michigan)
· Deep Learning (deeplearning.ai)
· TensorFlow in Practice (deeplearning.ai)
· TensorFlow Data and Deployment (deeplearning.ai)
· Python 3 Programming (University of Michigan)
· R Programming (Johns Hopkins University)
· Statistics with Python (University of Michigan)
· Algorithmic Toolbox (University of California San Diego)
· SQL: Querying and Managing Data (Khan Academy)
· Getting and Cleaning Data - Data Wrangling (Johns Hopkins University)
Companies Worked For:
Job Titles Held: