Balanced-MixUp for Highly Imbalanced Medical Image Classification
arXiv:2109.09850 · doi:10.1007/978-3-030-87240-3_31
Abstract
Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases, typically resulting in poor performance of machine learning algorithms due to overfitting in the learning process. In this paper, we propose a novel mechanism for sampling training data based on the popular MixUp regularization technique, which we refer to as Balanced-MixUp. In short, Balanced-MixUp simultaneously performs regular (i.e., instance-based) and balanced (i.e., class-based) sampling of the training data. The resulting two sets of samples are then mixed-up to create a more balanced training distribution from which a neural network can effectively learn without incurring in heavily under-fitting the minority classes. We experiment with a highly imbalanced dataset of retinal images (55K samples, 5 classes) and a long-tail dataset of gastro-intestinal video frames (10K images, 23 classes), using two CNNs of varying representation capabilities. Experimental results demonstrate that applying Balanced-MixUp outperforms other conventional sampling schemes and loss functions specifically designed to deal with imbalanced data. Code is released at https://github.com/agaldran/balanced_mixup .
Accepted at MICCAI 2021, International Conference on Medical Image Computing and Computer Assisted Intervention
References in corpus (6)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Decoupling Representation and Classifier for Long-Tailed Recognition
- DRGRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images
- Medical-based Deep Curriculum Learning for Improved Fracture Classification
- Iterative Augmentation of Visual Evidence for Weakly-Supervised Lesion Localization in Deep Interpretability Frameworks: Application to Color Fundus Images
- MixBoost: Synthetic Oversampling with Boosted Mixup for Handling Extreme Imbalance