erjui/medgemma-4b-csrrg-findings

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

This model is a fine-tuned version of google/medgemma-4b-it for generating the FINDINGS section of contextualized 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 Contextualized Structured Radiology Report Generation (CSRRG) for chest X-rays, generating detailed findings sections with rich clinical context including patient history, imaging technique, comparison to prior studies, and temporal reasoning.

Key characteristics:

• Generates the FINDINGS section of radiology reports
• Incorporates clinical history/indication, technique, and comparison to prior studies
• Performs temporal reasoning across multiple examinations
• Produces structured, clinically relevant observations with contextual awareness
• Fine-tuned with LoRA for parameter-efficient adaptation

Intended Use

Primary Use Cases

• Research on contextualized radiology report generation
• Development of temporal reasoning systems for medical imaging
• Clinical decision support with longitudinal patient data
• 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 (csrrg_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 rich clinical context
• Context includes: Clinical history/indication, imaging technique, comparison to prior studies, current and prior images

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: 3

Hardware:

• GPU: NVIDIA H100
• Training framework: HuggingFace Transformers + PEFT

Usage

Loading the Model

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

# Load model and processor
model_name = "erjui/medgemma-4b-csrrg-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 images (current and prior studies)
# CSRRG models support multiple images for temporal comparison (max_images_per_sample: 3)
current_image = Image.open("current_xray.jpg")
prior_image = Image.open("prior_xray.jpg")

# Prepare input with clinical context
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. Consider the available clinical contexts when formulating your findings.

=== CLINICAL HISTORY/INDICATION ===
Male patient status post acetabular surgery with concern for pleural effusion.

=== TECHNIQUE ===
Portable semi-erect single frontal chest radiograph.

=== CURRENT IMAGES ==="""
            },
            {"type": "image"},  # Current image
            {"type": "image"}   # Prior image (supports multiple images for temporal comparison)
        ]
    }
]

# Process and generate
inputs = processor(images=[current_image, prior_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:

@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:

@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.