Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation
This addresses data scarcity in medical image segmentation, which is a critical bottleneck for deep learning applications in healthcare, though it appears incremental relative to existing diffusion-based approaches.
The paper tackles the problem of limited annotated medical image datasets for segmentation by proposing Siamese-Diffusion, a dual-component diffusion model that generates synthetic image-mask pairs with improved morphological fidelity. The method boosts SANet's mDice and mIoU by 3.6% and 4.4% on Polyps data and UNet's by 1.52% and 1.64% on ISIC2018.
Deep learning has revolutionized medical image segmentation, yet its full potential remains constrained by the paucity of annotated datasets. While diffusion models have emerged as a promising approach for generating synthetic image-mask pairs to augment these datasets, they paradoxically suffer from the same data scarcity challenges they aim to mitigate. Traditional mask-only models frequently yield low-fidelity images due to their inability to adequately capture morphological intricacies, which can critically compromise the robustness and reliability of segmentation models. To alleviate this limitation, we introduce Siamese-Diffusion, a novel dual-component model comprising Mask-Diffusion and Image-Diffusion. During training, a Noise Consistency Loss is introduced between these components to enhance the morphological fidelity of Mask-Diffusion in the parameter space. During sampling, only Mask-Diffusion is used, ensuring diversity and scalability. Comprehensive experiments demonstrate the superiority of our method. Siamese-Diffusion boosts SANet's mDice and mIoU by 3.6% and 4.4% on the Polyps, while UNet improves by 1.52% and 1.64% on the ISIC2018. Code is available at GitHub.