Multi-Task Generative Adversarial Network for Handling Imbalanced Clinical Data
This addresses data imbalance issues in medical imaging for clinical applications, but it is incremental as it builds on existing GAN methods.
The paper tackles the problem of imbalanced clinical data in medical image semantic segmentation, where models bias towards healthy regions, by proposing a multi-task generative adversarial network with selective weighted loss, achieving state-of-the-art results on ACDC-2017 and competitive results on BraTS-2017.
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.