Improved HER2 Tumor Segmentation with Subtype Balancing using Deep Generative Networks. (arXiv:2211.06150v1 [eess.IV])

Tumor segmentation in histopathology images is often complicated by its
composition of different histological subtypes and class imbalance.
Oversampling subtypes with low prevalence features is not a satisfactory
solution since it eventually leads to overfitting. We propose to create
synthetic images with semantically-conditioned deep generative networks and to
combine subtype-balanced synthetic images with the original dataset to achieve
better segmentation performance. We show the suitability of Generative
Adversarial Networks (GANs) and especially diffusion models to create realistic
images based on …

arxiv deep generative networks networks segmentation