Multi-Task Generative Adversarial Network for Handling Imbalanced Clinical Data

Abstract

We propose a new generative adversarial architecture to mitigate imbalance data problem for the task of medical image semantic segmentation where the majority of pixels belong to a healthy region and few belong to lesion or non-health region. A model trained with imbalanced data tends to bias towards healthy data which is not desired in clinical applications. We design a new conditional GAN with two components: a generative model and a discriminative model to mitigate imbalanced data problem through selective weighted loss. While the generator is trained on sequential magnetic resonance images (MRI) to learn semantic segmentation and disease classification, the discriminator classifies whether a generated output is real or fake. The proposed architecture achieved state-of-the-art results on ACDC-2017 for cardiac segmentation and diseases classification. We have achieved competitive results on BraTS-2017 for brain tumor segmentation and brain diseases classification.

arXiv commentMachine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216. arXiv admin note: text overlap with arXiv:1810.03871

References in corpus (7)

• Conditional Generative Adversarial Nets
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Automatic Brain Tumor Segmentation using Cascaded Anisotropic Convolutional Neural Networks
• Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation
• Deep Neural Network with l2-norm Unit for Brain Lesions Detection
• Conditional Adversarial Network for Semantic Segmentation of Brain Tumor
• Conditional Generative Refinement Adversarial Networks for Unbalanced Medical Image Semantic Segmentation