M3D-NCA: Robust 3D Segmentation with Built-in Quality Control

TL;DR

M3D-NCA introduces a resource-efficient 3D medical image segmentation method using Neural Cellular Automata, with built-in quality control, outperforming larger models and suitable for deployment in low-resource settings.

Contribution

The paper presents M3D-NCA, a novel NCA-based segmentation approach with an automatic error detection metric, enabling effective 3D medical segmentation in resource-limited environments.

Findings

Outperforms larger UNet models by 2% Dice in hippocampus and prostate segmentation.

Can run on Raspberry Pi 4, demonstrating efficiency and practicality.

Provides a built-in quality metric for automatic error detection.

Abstract

Medical image segmentation relies heavily on large-scale deep learning models, such as UNet-based architectures. However, the real-world utility of such models is limited by their high computational requirements, which makes them impractical for resource-constrained environments such as primary care facilities and conflict zones. Furthermore, shifts in the imaging domain can render these models ineffective and even compromise patient safety if such errors go undetected. To address these challenges, we propose M3D-NCA, a novel methodology that leverages Neural Cellular Automata (NCA) segmentation for 3D medical images using n-level patchification. Moreover, we exploit the variance in M3D-NCA to develop a novel quality metric which can automatically detect errors in the segmentation process of NCAs. M3D-NCA outperforms the two magnitudes larger UNet models in hippocampus and prostate segmentation by 2% Dice and can be run on a Raspberry Pi 4 Model B (2GB RAM). This highlights the potential of M3D-NCA as an effective and efficient alternative for medical image segmentation in resource-constrained environments.