medgemma-4b: Structured Radiology Report Generation (Findings)

Name: medgemma-4b-srrg-findings
Availability: InStock

This model is a fine-tuned version of google/medgemma-4b-it for generating the FINDINGS section of structured chest X-ray radiology reports. It was trained using LoRA (Low-Rank Adaptation) on the csrrg_ift_dataset containing instruction-following examples from MIMIC-CXR and CheXpert+ datasets.

Model Description

This model performs Structured Radiology Report Generation (SRRG) for chest X-rays, specifically generating detailed findings sections that describe anatomical observations organized by body regions (lungs, heart, mediastinum, bones, etc.).

Key characteristics:

Generates the FINDINGS section of radiology reports
Trained on single chest X-ray examinations
Produces structured, clinically relevant observations
Fine-tuned with LoRA for parameter-efficient adaptation

Intended Use

Primary Use Cases

Research on automated radiology report generation
Development of clinical decision support systems
Medical AI and multimodal model research
Educational tools for radiology training

Intended Users

Medical AI researchers
Healthcare technology developers
Clinical informatics specialists
Radiology departments (research use only)

Out-of-Scope Use

NOT intended for clinical diagnosis without physician review
Should not replace human radiologists in clinical practice
Requires validation before any clinical deployment

Training Details

Training Data

Dataset: csrrg_ift_dataset (srrg_ift_dataset_findings subset)
Training samples: ~181,874 instruction-following examples
Data sources: MIMIC-CXR and CheXpert+ chest X-ray datasets
Task format: Instruction fine-tuning with system-user-assistant conversations

Training Procedure

Fine-tuning method: LoRA (Low-Rank Adaptation)

LoRA Configuration:

Rank (r): 32
Alpha: 64
Dropout: 0.1
Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Training hyperparameters:

Learning rate: 2e-4
Batch size: 4 per device
Gradient accumulation steps: 32 (effective batch size: 128)
Epochs: 1
Optimizer: AdamW
Learning rate scheduler: Cosine with 3% warmup
Precision: bfloat16
Attention implementation: Flash Attention 2
Max sequence length: 2048
Max images per sample: 1

Hardware:

GPU: NVIDIA H100
Training framework: HuggingFace Transformers + PEFT

Usage

Loading the Model

python

from transformers import AutoProcessor, AutoModelForVision2Seq
from PIL import Image
import torch

# Load model and processor
model_name = "erjui/medgemma-4b-srrg-findings"
model = AutoModelForVision2Seq.from_pretrained(
    model_name,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
processor = AutoProcessor.from_pretrained("google/medgemma-4b-it", trust_remote_code=True)

# Load chest X-ray image (single image for SRRG)
image = Image.open("chest_xray.jpg")

# Prepare input
messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are an expert radiologist."}]
    },
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Analyze the chest X-ray images and write the FINDINGS section of a radiology report. Use standard medical terminology and organize findings by anatomical regions."},
            {"type": "image"}
        ]
    }
]

# Process and generate (max_images_per_sample: 1)
inputs = processor(images=image, text=messages, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
generated_text = processor.decode(outputs[0], skip_special_tokens=True)

print(generated_text)

Expected Output Format

FINDINGS:
Lungs and Airways:
- No pleural effusion or pneumothorax detected
- Bibasilar atelectasis present

Cardiovascular:
- Mild left ventricular enlargement

Musculoskeletal and Chest Wall:
- Bilateral rib fractures noted

Citation

If you use this model, please cite:

bibtex

@article{kang2025automated,
  title={Automated Structured Radiology Report Generation with Rich Clinical Context},
  author={Kang, Seongjae and Lee, Dong Bok and Jung, Juho and Kim, Dongseop and Kim, Won Hwa and Joo, Sunghoon},
  journal={arXiv preprint arXiv:2510.00428},
  year={2025}
}

Also cite the base model:

bibtex

@article{sellergren2025medgemma,
  title={Medgemma technical report},
  author={Sellergren, Andrew and Kazemzadeh, Sahar and Jaroensri, Tiam and Kiraly, Atilla and Traverse, Madeleine and Kohlberger, Timo and Xu, Shawn and Jamil, Fayaz and Hughes, C{\'\i}an and Lau, Charles and others},
  journal={arXiv preprint arXiv:2507.05201},
  year={2025}
}

Model Card Authors

Seongjae Kang (erjui)

Model Card Contact

For questions or issues, please open an issue on the model repository.