Unmasking Interstitial Lung Diseases: Leveraging Masked Autoencoders for Diagnosis
This work addresses the challenge of scarce labeled data in medical imaging for lung disease diagnosis, though it is incremental as it applies an existing method to a new domain.
The researchers tackled the problem of diagnosing interstitial lung diseases with limited annotated CT scans by training a masked autoencoder on over 5,000 chest CT scans and fine-tuning it for classification, resulting in improved diagnostic performance.
Masked autoencoders (MAEs) have emerged as a powerful approach for pre-training on unlabelled data, capable of learning robust and informative feature representations. This is particularly advantageous in diffused lung disease research, where annotated imaging datasets are scarce. To leverage this, we train an MAE on a curated collection of over 5,000 chest computed tomography (CT) scans, combining in-house data with publicly available scans from related conditions that exhibit similar radiological patterns, such as COVID-19 and bacterial pneumonia. The pretrained MAE is then fine-tuned on a downstream classification task for diffused lung disease diagnosis. Our findings demonstrate that MAEs can effectively extract clinically meaningful features and improve diagnostic performance, even in the absence of large-scale labelled datasets. The code and the models are available here: https://github.com/eedack01/lung_masked_autoencoder.