Academic Project: Interactive Platform for Synthetic Flow Cytometry Data Generation for Education

Developed web-based platforms to generate and analyze synthetic flow cytometry (FCM) data for educational use ..
Researcher turned data science enthusiast
specialized in Data Science (M.Sc.), Physical Oceanography (Ph.D.), and Environmental Science (M.Eng.)
Developed web-based platforms to generate and analyze synthetic flow cytometry (FCM) data for educational use ..
Developed machine learning models, non-NN (SVM) and NN (CNN), to classify heart vs abdominal ultrasound images and train the best-performing model architecture to detect mitral valve states (open/closed) of heart images. Evaluated results using standard metrics and 5-fold cross-validation. Enhanced performance with data augmentation and transfer learning (ResNet152V2 Model). Implemented a U-Net model to segment heart chambers to distinguish between open and closed mitral valve states, improving classification accuracy by using clinician-annotated masks for added clinical insight.
This was conducted as part of an academic module at RGU, where the goal was to apply machine learning techniques to medical imaging data classification and segmentation tasks.
Software/packages:
Python, TensorFlow, Keras, Scikit-learn, OpenCV, NumPy, Pandas, Matplotlib, Seaborn, scikit-image, PIL (Pillow), imutils
Description of project-3