vision language models finetuning notebooks & use cases (Medgemma - paligemma - florence .....)
A multi agent healthcare assistant system implemented using Python and Langgraph. The agents include icd10 code extractor, SOAP document generator and medical image report generator. This project uses one of the latest LLMs, MedGemma model.
Gradio-based web UI for medical image interpretation using Google's MedGemma vision-language model.
brain-network-chart
Convert DICOM medical images to JPEG for easy viewing, sharing, and AI model input (e.g. Google's MedGemma).
CardioGuard is an end-to-end health technology platform that collects real-time cardiac data from Holter ECG devices, performs anomaly detection using a multi-layer AI pipeline (CNN + Rule Engine + MedGemma), and provides clinical-grade monitoring for patients and doctors.
Smart pharmacy assistant for ViaPharma customers. Provides personalized OTC product recommendations based on symptoms using medical AI and safety-first approach.
MedFlow AI — FastAPI/React microservices for medical triage and imaging analysis with Google MedGemma (Gradio/API); Dockerized, analytics-ready, and suitable for demo/research use.
Privacy-first menopause assistant: local symptom tracking, RAG-backed chat, and clinician-style summaries powered by MedGemma.
A medical symptom-checker AI chat application with user managed RAG. Candata/Ontario healthcare localization.
Python Backend for the Solve for Healthcare & Life Sciences with Gemma Hackathon
This project aims to support neurologists in monitoring patients undergoing anti-amyloid therapy for Alzheimer's disease — treatments that, while promising, can cause side effects such as Amyloid-Related Imaging Abnormalities with edema (ARIA-E), which leads to brain edema visible on FLAIR MRI scans.
🏥 Making medical annotation faster, better, and more accessible.
Agentic health triage system built for the Kaggle MedGemma Impact Challenge to support risk classification in low-resource rural healthcare settings.
MedGemma 1.5 Instruct LoRA fine-tuning + Gradio app for Real-time Interaction on CT-Scan, MRI, X-RAY images
Family medicine documentation assistant built from survey insights from practicing doctors in Poland. Structures pre-visit intake and drafts clinician notes (no diagnosis/treatment), reducing routine paperwork time.
On-device surgical navigation assistant using MedGemma 1.5 4B with ground truth scaffolding
Early detection, accessible to everyone.
Add a description, image, and links to the medgemma topic page so that developers can more easily learn about it.
To associate your repository with the medgemma topic, visit your repo's landing page and select "manage topics."