Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content
Fig. 7 | BMC Medical Informatics and Decision Making

Fig. 7

From: BarlowTwins-CXR: enhancing chest X-ray abnormality localization in heterogeneous data with cross-domain self-supervised learning

Fig. 7

AUC Scores with Error Bars for NIH-CXR Classification - This figure displays the AUC scores of models fine-tuned end-to-end with Barlow Twins-CXR versus ImageNet weights across various dataset sizes (1%, 10%, 100%). Higher AUC scores indicate that models using Barlow Twins-CXR consistently outperform those with ImageNet pre-training. Error bars represent the range of scores across five experiments

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us