Ensembled Autoencoder Regularization for Multi-Structure Segmentation for Kidney Cancer Treatment
This work addresses the challenge of precise organ delineation to enhance surgical planning for kidney cancer patients, representing an incremental improvement in medical image segmentation.
The authors tackled the problem of multi-structure segmentation for kidney cancer treatment by proposing an ensemble of two fully convolutional networks (SegResNet and nnU-Net) combined with mixup augmentation, resulting in improved segmentation performance for kidney, tumor, veins, and arteries.
The kidney cancer is one of the most common cancer types. The treatment frequently include surgical intervention. However, surgery is in this case particularly challenging due to regional anatomical relations. Organ delineation can significantly improve surgical planning and execution. In this contribution, we propose ensemble of two fully convolutional networks for segmentation of kidney, tumor, veins and arteries. While SegResNet architecture achieved better performance on tumor, the nnU-Net provided more precise segmentation for kidneys, arteries and veins. So in our proposed approach we combine these two networks, and further boost the performance by mixup augmentation.