بعد أكاديمية كاوست
Rahaf works at the National Center for Government Resources Systems. Rahaf graduated in February 2025 from the University of Jeddah with first-class honors in artificial intelligence, earned the Junior Data Science Certification, and was a teaching assistant for KAUST Academy's Introduction to AI program.
المشروع الصيفي
تخصص الذكاء الاصطناعي · دفعة 2024
(Pneumonia Diagnosis Assistant) – Customized Hybrid Deep Learning Approach for Symptom-Driven Pneumonia Diagnosis
This project presents a hybrid deep-learning approach for diagnosing pneumonia, integrating image and text-based data. A VGG16-based U-Net model was developed to analyze chest X-rays, effectively detecting pneumonia with high precision. Simultaneously, a pre-trained BioBERT model was employed to extract symptoms and relevant medical history from patient records. Although BioBERT was used without fine-tuning, it served as a baseline for symptom analysis, with future work aimed at fine-tuning to enhance accuracy. The integrated model demonstrated a strong performance, achieving an Intersection over Union (loU) of 0.88 and an accuracy of 95%. This dual-modality approach allows for a more accurate diagnosis by combining the strengths of image segmentation and natural language processing. showcasing the potential of hybrid models in improving diagnostic tools for healthcare professionals, offering faster, more reliable, and context-aware medical diagnosis.
مع أكاديمية كاوست
- دفعة 2024
جامعة الملك عبدالله للعلوم والتقنية (كاوست) · المدرسة الصيفية للذكاء الاصطناعي
هل تريد تحديث بياناتك أو حذفها؟ تواصل معنا.