echogemma / README.md
milosvuk's picture
Update README.md
28ec6e6 verified
metadata
license: apache-2.0
tags:
  - echocardiography
  - medical
  - report-generation
  - multimodal
  - cardiology
  - ultrasound
library_name: pytorch
pipeline_tag: text-generation
base_model: google/medgemma-1.5-4b-it

EchoGemma

Multimodal echocardiography report generation from DICOM studies. EchoGemma combines an EchoPrime video encoder and a LoRA-fine-tuned MedGemma language model to process full echocardiographic studies and generate clinical text reports.

Input

A folder of DICOM echocardiography video files (a complete study). The model processes all video clips, extracts embeddings and view classifications, then generates a structured clinical report.

Output

A structured echocardiography text report.

Requirements

  • Python >= 3.10
  • PyTorch 2.10+
  • CUDA-capable GPU (recommended)
  • ~18 GB disk space for model weights