metadata
license: mit
library_name: pytorch
tags:
- Medical Vsion-Language Pre-Training
- BenchX
GLoRIA Checkpoint Model Card
A retrained GLoRIA model for benchmarking medical vision-language pre-training methods within the BenchX framework.
Model Details
- Model Type: GLoRIA
- Architecture: ResNet-50 image encoder and BERT text encoder
- Original Papers: GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-efficient Medical Image Recognition
- 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 GLoRIA for classification, run this command:
python bin/train.py config/classification/<dataset_name>/gloria.yml
2. Segmentation
To fine-tune GLoRIA for segmentation, run this command:
python mmsegmentation/tools/train.py config/benchmark/<dataset_name>/gloria.yml
3. Report Generation
To fine-tune GLoRIA for report generation, run this command:
python bin/train.py config/report_generation/<dataset_name>/gloria.yml
4. Evaluation
To evaluate fine-tuned GLoRIA models, run:
# For classification and report generation
python bin/test.py config/<task_name>/<dataset_name>/gloria.yml validator.splits=[test] ckpt_dir=<path_to_checkpoint>
# For segmentation
python mmsegmentation/tools/my_test.py mmsegmentation/config/<dataset_name>/gloria.yml <path_to_checkpoint>
Citations
@inproceedings{huang2021gloria,
title={GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition},
author={Huang, Shih-Cheng and Shen, Liyue and Lungren, Matthew P and Yeung, Serena},
booktitle={Proceedings of ICCV},
pages={3942--3951},
year={2021}
}
@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}
}