🧠 MedScan AI

MedScan AI is a modular, multimodal medical assistant built to streamline clinical data processing. It intelligently integrates and interprets information from diverse sources:

• 🖼️ Radiology images (e.g., X-rays, CT scans)
• ✍️ Handwritten doctor notes
• 🎙️ Audio transcripts

By leveraging state-of-the-art open-source models like Qwen2.5-VL, Whisper, and Qwen-Omni, MedScan AI generates comprehensive and accurate clinical summaries.

---

🚀 Features

• 🔬 Advanced Image Analysis
  Uses Qwen2.5-VL to interpret radiology images with medical-grade accuracy.

• 📝 Accurate Handwriting OCR
  Employs Tesseract to digitize and extract insights from handwritten doctor notes.

• 🎧 Robust Audio Transcription
  Converts medical conversations into text using Whisper.

• 🧩 Intelligent Medical Reasoning
  Integrates and analyzes multimodal data with Qwen-Omni to generate clinical insights.

• ⚙️ Seamless Orchestration
  Orchestrated by orchestrator.py pipelines for streamlined and efficient data processing.