MedSegDiffNCA: Diffusion Models With Neural Cellular Automata for Skin Lesion Segmentation
This provides a more efficient solution for skin lesion segmentation in low-resource medical settings, though it is incremental as it builds on existing diffusion and NCA methods.
The paper tackled the high computational overhead of Unet-based diffusion models in medical image segmentation by proposing NCA-based improvements, resulting in a model that matches Unet performance with a dice score of 87.84% while using 60-110 times fewer parameters.
Denoising Diffusion Models (DDMs) are widely used for high-quality image generation and medical image segmentation but often rely on Unet-based architectures, leading to high computational overhead, especially with high-resolution images. This work proposes three NCA-based improvements for diffusion-based medical image segmentation. First, Multi-MedSegDiffNCA uses a multilevel NCA framework to refine rough noise estimates generated by lower level NCA models. Second, CBAM-MedSegDiffNCA incorporates channel and spatial attention for improved segmentation. Third, MultiCBAM-MedSegDiffNCA combines these methods with a new RGB channel loss for semantic guidance. Evaluations on Lesion segmentation show that MultiCBAM-MedSegDiffNCA matches Unet-based model performance with dice score of 87.84% while using 60-110 times fewer parameters, offering a more efficient solution for low resource medical settings.