Projects

My research focuses on advancing artificial intelligence in medical imaging applications to improve patient diagnosis, with a particular emphasis on vision-language and foundation models, text generation, image classification, segmentation techniques and medical image registration.

(MSc Thesis) MMG-CLIP: Automated Mammography Reporting through Image-to-Text Translation

2D Mammograms to reports with CLIP-based architecture and image-reports datasets

ISIC2019 Skin Lesion Image Classification and Segmentation

An ensemble pipeline using VGG16_BN architecture and attention blocks

IBSR 2018 Brain Tissue Segmentation

Brain tissue (WM, GM, CSF) segmentation using both multi-atlas and nnUNet

COPDgene CT Image Registration

Lung segmentation, pre-processing and image registration on 4DCT dataset

Brain Tissue Segmentation using Expectation Maximization and Atlases

Expectation Maximization algorithm using intinsity and position atlas information

U-Net Architecture PyTorch Implementation for Medical Image Segmentation

U-Net architecture pipeline using PyTorch for medical image segmentation

Breast Mass Detection and Segmentation Using Multi-scale Morphological Sifting and K-Means Clustering

Multi-scale morphological sifting & K-means for mass detection and segmentation

Magnification Specific Breast Histopathology Image Classification Using Machine Learning and Deep Learning

Malignancy classification pipelines using machine and deep learning approaches

Alzheimer Disease Classification using MRIs and Gene Expression Data

Using MRI and GE features, we classify between AD (macro-)stages

(BEng Thesis) A 6-Minute Walk Test (6MWT) Monitoring and Tracking System for Home-based Rehabilitation

An implementation of a 6MWT monitoring algorithm on an Andoid application that utilize multiple sensors, with a web tracking interface that allows post-test consultation and remote-monitoring using WebRTC technology.

Motion Compensated Pulse Rate Estimation

Building a regression model to predict the estimated hospitalization time for a patient in order to help select/filter patients and evaluate model bias and uncertainty

Hippocampal Volume Quantification in Alzheimer’s Progression

Measuring the hippocampal volumes using a U-net trained model, integrated into a clinical-grade viewer and automatically measures hippocampal volumes, and generate reports.

Pneumonia Detection from Chest X-Rays 2D Images

Exploratoring a chest x-rays dataset and train a model that can predict the presence of pneumonia with human radiologist-level accuracy

Abdelrahman Habib

Projects