Balanced-mixup for highly imbalanced medical image classification

Citació

  • Galdran A, Carneiro G, González Ballester MA. Balanced-mixup for highly imbalanced medical image classification. In: de Bruijne M, Cattin PC, Cotin S, Padoy N, Speidel S, Zheng Y, Essert C, editors. Medical Image Computing and Computer Assisted Intervention (MICCAI 2021): 24th International Conference; 2021 Sep 27-Oct 01; Strasbourg, France. Cham: Springer; 2021. p. 323-33. DOI: 10.1007/978-3-030-87240-3_31

Enllaç permanent

Descripció

  • Resum

    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
  • Descripció

    Comunicació presentada a 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021), celebrat del 27 de setembre a l'1 d'octubre de 2021 de manera virtual.
  • Mostra el registre complet