I'm Jakub Dobrzański, a final-year Computer Science student at Wrocław University of Science and Technology (PWr), passionate about Machine Learning with a particular focus on healthcare and medicine. I'm fascinated by the potential of artificial intelligence to solve real-world medical problems and improve healthcare quality.

• Medical Imaging: Analysis of medical images (X-ray, MRI, CT)
• AI-Assisted Diagnostics: Systems supporting doctors in diagnosis
• Predictive Healthcare: Predictive models for patient outcomes

Core Libraries:

• Deep Learning: TensorFlow, PyTorch, Keras
• NLP: Hugging Face Transformers
• Computer Vision: OpenCV, PIL, scikit-image
• Data Science: Pandas, NumPy, CuPy, SciPy
• Visualization: Matplotlib, Seaborn, Plotly
• ML Tools: scikit-learn, XGBoost
• Development: Jupyter, Git, Docker

Advanced Medical RAG application enabling PDF document upload and natural language querying

• Tech Stack: Python, Streamlit, ChromaDB, OpenAI API, sentence-transformers
• Features:
  • PDF processing with intelligent text cleaning
  • Vector database (ChromaDB) for similarity search
  • Medical context awareness with specialized prompt engineering
  • Source attribution - always cites sources
  • Medical term normalization - automatic abbreviation expansion
  • Interactive web interface with batch processing
• Architecture: Modular design (PDFProcessor, VectorStore, LLMClient, RAGSystem)
• View Code

Convolutional Neural Network implementation from scratch using CuPy

• Tech Stack: CuPy, NumPy, Python
• Features: Low-level CNN implementation, GPU acceleration, educational approach
• Achievement: Deep understanding of CNN architecture through ground-up implementation
• View Code

CNN for lung cancer detection with custom vs pretrained model comparison

• Tech Stack: TensorFlow, Keras, VGG16 (transfer learning)
• Features: Custom CNN architecture, transfer learning comparison, medical image preprocessing
• Achievement: Implementation and comparison of different approaches to medical image classification
• View Code

Currently working on additional healthcare ML projects including:

• Medical NLP Pipeline: Clinical text analysis and entity extraction
• Vet LLM finetuning: Using LoRA on MLX (Apple silicon)

I'm excited to discuss collaboration opportunities on ML healthcare projects!

• Email: jakubdobrzanski@icloud.com
• LinkedIn: linkedin.com/in/jakub-dobrzanski-261baa228
• GitHub: github.com/Doberman12