metadata

license: mit
library_name: pytorch
tags:
  - Medical Vsion-Language Pre-Training
  - BenchX

MGCA-ViT Checkpoint Model Card

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

Model Details

Model Type: MGCA-ViT
Architecture: ViT-Base image encoder and BioClinicalBERT text encoder
Original Papers: Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning
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 MGCA-ViT for classification, run this command:

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

2. Segmentation

To fine-tune MGCA-ViT for segmentation, run this command:

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

3. Report Generation

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

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

4. Evaluation

To evaluate fine-tuned MGCA-ViT models, run:

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

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

Citations

@article{wang2022multi,
  title={Multi-granularity cross-modal alignment for generalized medical visual representation learning},
  author={Wang, Fuying and Zhou, Yuyin and Wang, Shujun and Vardhanabhuti, Varut and Yu, Lequan},
  journal={Advances in NeurIPS},
  volume={35},
  pages={33536--33549},
  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}
}