ConVIRT Checkpoint Model Card

A retrained ConVIRT model for benchmarking medical vision-language pre-training methods within the BenchX framework.

Model Details

• Model Type: ConVIRT
• Architecture: ResNet-50 image encoder and BioMed-RoBERTa-base text encoder
• Original Papers: Contrastive Learning of Medical Visual Representations from Paired Images and Text
• Benchmark Paper: BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
• Benchmark Framework: https://github.com/yangzhou12/BenchX

Intended Use

• Primary Use Cases:
  • Benchmarking performance for Medical Image Classification
  • Benchmarking performance for Medical Image Segmentation
  • Benchmarking performance for Medical Report Generation

Pre-Training Data

• Dataset:
  • Data source(s): MIMIC-CXR
  • Types of medical images: Frontal chest X-rays
  • Text data type: Associated radiology reports

Prerequisites

Please follow the instruction to install BenchX.

Training & Evaluation

1. Classification

To fine-tune ConVIRT for classification, run this command:

python bin/train.py config/classification/<dataset_name>/convirt.yml

2. Segmentation

To fine-tune ConVIRT for segmentation, run this command:

python mmsegmentation/tools/train.py config/benchmark/<dataset_name>/convirt.yml

3. Report Generation

To fine-tune ConVIRT for report generation, run this command:

python bin/train.py config/report_generation/<dataset_name>/convirt.yml

4. Evaluation

To evaluate fine-tuned ConVIRT models, run:

# For classification and report generation
python bin/test.py config/<task_name>/<dataset_name>/convirt.yml validator.splits=[test] ckpt_dir=<path_to_checkpoint>

# For segmentation
python mmsegmentation/tools/my_test.py mmsegmentation/config/<dataset_name>/convirt.yml <path_to_checkpoint>

Citations

@inproceedings{zhang2020contrastive,
  title={Contrastive Learning of Medical Visual Representations from Paired Images and Text},
  author={Zhang, Yuhao and Jiang, Hang and Miura, Yasuhide and Manning, Christopher D and Langlotz, Curtis P},
  booktitle={Proceedings of Machine Learning for Healthcare Conference},
  pages={2--25},
  year={2022},
}

@inproceedings{zhou2024benchx,
  title={BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays},
  author={Yang Zhou, Tan Li Hui Faith, Yanyu Xu, Sicong Leng, Xinxing Xu, Yong Liu, Rick Siow Mong Goh},
  booktitle={Proceedings of NeurIPS},
  year={2024}
}