BACKGROUND
Chest X-ray imaging based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. Recent advances in deep learning, especially self-supervised learning, offer promising solutions to enhance image analysis efficiency, accuracy and reliability.
OBJECTIVE
This study aims to improve autonomic abnormality localization performance of chest X-ray image analysis, particularly in detecting abnormalities, using a self-supervised learning method called BarlowTwins-CXR.
METHODS
We utilized two publicly available datasets: the NIH Chest X-ray Dataset and the VinDr-CXR. The BarlowTwins-CXR approach was conducted in a two-stage training process. Initially, self-supervised pre-training was performed using an adjusted Barlow Twins algorithm on the NIH dataset with a Resnet50 backbone pre-trained on ImageNet. This was followed by supervised fine-tuning on the VinDr-CXR dataset using Faster R-CNN with Feature Pyramid Network (FPN). The study employed mean Average Precision (mAP) at an Intersection over Union (IoU) of 50% and Area Under the Curve (AUC) for performance evaluation.
RESULTS
Our experiments showed a significant improvement in model performance with BarlowTwins-CXR. The approach achieved a 3% increase in mAP50 accuracy compared to traditional ImageNet pre-trained models. In addition, the Ablation CAM method revealed enhanced precision in localizing chest abnormalities. The study involved 112,120 images from the NIH dataset and 18,000 images from the VinDr-CXR dataset, indicating robust training and testing samples.
CONCLUSIONS
BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image base abnormality localization, outperforming traditional transfer learning methods. Its ability to adapt to various imaging conditions and regional variations demonstrates the potential of self-supervised learning in medical diagnostics. This approach can be instrumental in aiding radiologists, particularly in high-workload environments, offering a promising direction for future AI-driven healthcare solutions.