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.

翻译：医学图像分割严重依赖于大规模深度学习模型，例如基于UNet的架构。然而，此类模型在实际中的应用受限于其高计算需求，这使得它们在资源受限环境（如基层医疗机构和冲突区域）中难以实用。此外，成像域的变化可能使这些模型失效，甚至如果此类错误未被检测到，则可能危及患者安全。为应对这些挑战，我们提出M3D-NCA，一种利用神经细胞自动机（NCA）通过n级分块化进行三维医学图像分割的新方法。此外，我们利用M3D-NCA的方差开发了一种新型质量度量，可自动检测NCA分割过程中的错误。在海马体和前列腺分割任务中，M3D-NCA以2%的Dice系数优于参数规模大两个数量级的UNet模型，且可在树莓派4B型号（2GB内存）上运行。这凸显了M3D-NCA作为资源受限环境中医学图像分割有效且高效替代方案的潜力。