Improving Mitosis Detection Via UNet-based Adversarial Domain Homogenizer
This addresses the domain bias issue in histology imaging for pathologists, but it is incremental as it builds on existing U-Net and adversarial methods.
The paper tackles the problem of automated mitosis detection failing on unseen patient data due to domain biases in histology images by proposing a U-Net-based adversarial domain homogenizer, which reduces domain differences and, when combined with a RetinaNet object detector, outperforms baselines in the 2021 MIDOG challenge in terms of average precision.
The effective localization of mitosis is a critical precursory task for deciding tumor prognosis and grade. Automated mitosis detection through deep learning-oriented image analysis often fails on unseen patient data due to inherent domain biases. This paper proposes a domain homogenizer for mitosis detection that attempts to alleviate domain differences in histology images via adversarial reconstruction of input images. The proposed homogenizer is based on a U-Net architecture and can effectively reduce domain differences commonly seen with histology imaging data. We demonstrate our domain homogenizer's effectiveness by observing the reduction in domain differences between the preprocessed images. Using this homogenizer, along with a subsequent retina-net object detector, we were able to outperform the baselines of the 2021 MIDOG challenge in terms of average precision of the detected mitotic figures.