Abstract

Motivation: Convolutional Neural Networks (CNNs) have long been the go-to deep-learning architecture for medical image segmentation, but in recent years transformer-based architectures adapted from large language models are setting a new standard. Goal(s): The aim of this study was to test if transformers are suitable for 3D kidney segmentation on high-resolution MRI. Approach: A transformer-based deep-learning architecture (UNETR) was trained and tested against a supervised method on 82 patient datasets from the iBEAt study on diabetic kidney disease. Results: UNETR provides fast segmentation with comparable results to the supervised method, but additional refinement is needed to reduce the limits of agreement. Impact: Novel transformer-based architectures for medical image segmentation may be useful for fast 3D segmentation of individual kidneys.