Few-shot Diagnosis of Chest x-rays Using an Ensemble of Random Discriminative Subspaces
This work addresses the challenge of medical image analysis with limited annotated data, though it appears incremental as it builds on existing few-shot learning techniques.
The authors tackled the problem of few-shot learning for chest x-ray diagnosis by designing an ensemble of random discriminative subspaces, resulting in a method that is 1.8 times faster than a baseline using truncated singular value decomposition.
Due to the scarcity of annotated data in the medical domain, few-shot learning may be useful for medical image analysis tasks. We design a few-shot learning method using an ensemble of random subspaces for the diagnosis of chest x-rays (CXRs). Our design is computationally efficient and almost 1.8 times faster than method that uses the popular truncated singular value decomposition (t-SVD) for subspace decomposition. The proposed method is trained by minimizing a novel loss function that helps create well-separated clusters of training data in discriminative subspaces. As a result, minimizing the loss maximizes the distance between the subspaces, making them discriminative and assisting in better classification. Experiments on large-scale publicly available CXR datasets yield promising results. Code for the project will be available at https://github.com/Few-shot-Learning-on-chest-x-ray/fsl_subspace.