Name: abdulkader helwan
Type: User
Company: Linkoping University
Bio: R&D Biomedical Engineer(PhD): Medical Intelligence, Deep Learning, Image Processing, Data Science, Nuclear Radiation Detection
Twitter: helwan90
Location: Sweden
abdulkader helwan's Projects
Config files for my GitHub profile.
Ct Scans of Normal and Hemorrhagic images from Near East University Hospital, Cyprus.
Identification of the three types of Pre-cancerous Cervical Colposcopy raw images
The DeepFashion dataset is a large-scale clothes database, which has several appealing features: Clothing Category and Attribute Prediction, In-shop Clothes Retrieval Benchmark, Consumer-to-Shop Clothes Retrieval Benchmark, and Fashion Landmark Detection Benchmark, collected by the Multimedia Lab at the Chinese University of Hong Kong. However, for our project, we’ll use only the Category and Attributes Prediction dataset because we’re going to work on detecting and classifying clothing in existing images, and even generating new similar images. To follow along, download the dataset. Category and Attributes Prediction is a huge dataset that contains images of clothes segregated into highly specific categories by different attributes. For example, blouses with sleeves are considered different from sleeveless ones. For this project, we made our own data subset, reducing the volume of images and category specificity, for simplicity and lower computation costs. We reduced our classification from DeepFashion’s original 46 categories to 15 categories. Then, we selected 500-700 images from each of our simplified categories.
Designing a model for generating Fairouz-like music
Knee Osteoarthritis (KOA) is the most common types of Osteoarthritis (OA) and it is diagnosed by physicians using the widely used 0–4 Kellgren Lawrence (KL) grading system which places the KOA in a spectrum of 5 grades; starting from normal (0) to Severe OA (4). In this paper, we propose a transfer learning approach of a very deep residual learning based network (Wide ResNet-50-2) which is fine-tuned using X-ray plain radiographs from the Osteoarthritis Initiative (OAI) dataset to learn the KL severity grading of KOA. In addition, we propose a data augmentation approach of OAI data to avoid imbalance and reduce overfitting by applying it only to certain KL grades depending on their number of plain radiographs. Experimentally, we tested the model on original and augmented x-rays and it showed good generalization power in predicting the KL grade of knee x-rays with an accuracy of 72% and F1-Score of 74%. Moreover, using Grad-Cam, we also showed that network is selecting some correct features when predicting a KL grade of a knee radiograph. Such achieved results showed that our such a model outperformed several other related works, and it can be further improved to be used to help radiologists make more accurate and precise diagnosis.
Summarize and simplify medical reports generated by doctors or medical devices
In this series of articles, we’ll present a Mobile Image-to-Image Translation system based on a Cycle-Consistent Adversarial Networks (CycleGAN). We’ll build a CycleGAN that can perform unpaired image-to-image translation, as well as show you some entertaining yet academically deep examples.
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)
Gamma Ray Nuclides Identification Using Mixture of Experts
Highway network implemented in pytorch
Using Deep Learning to detect AI-Generated Faces
Example Streamlit app that you can fork to test out share.streamlit.io