Ensembled Autoencoder Regularization for Multi-Structure Segmentation for Kidney Cancer Treatment

TL;DR

This paper introduces an ensemble of two convolutional neural networks with mixup augmentation to improve multi-structure segmentation of kidneys, tumors, veins, and arteries, aiding surgical planning for kidney cancer treatment.

Contribution

The novel approach combines SegResNet and nnU-Net architectures with mixup augmentation to enhance segmentation accuracy across multiple kidney-related structures.

Findings

SegResNet outperforms in tumor segmentation

nnU-Net provides more precise kidney and vessel segmentation

Ensemble with mixup boosts overall segmentation performance

Abstract

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.