🤖 AI Summary
While nnUNet automatically optimizes training hyperparameters, its fixed internal architecture—particularly static convolutional kernel sizes—limits its capacity to model multi-organ, multi-scale anatomical features. To address this, we propose MSA2-Net: an encoder-decoder framework integrating adaptive convolution modules that dynamically adjust kernel sizes to accommodate organ-scale variations; incorporating CSWin Transformer for long-range dependency modeling; and introducing multi-scale convolutional bridges with optimized skip connections to synergistically enhance global-local feature interaction. Evaluated on Synapse, ACDC, Kvasir, and ISIC2017, MSA2-Net achieves Dice scores of 86.49%, 92.56%, 93.37%, and 92.98%, respectively, demonstrating substantial improvements in generalization and segmentation accuracy. The core contributions are a structural adaptive convolution mechanism and a novel multi-scale Transformer fusion architecture.
📝 Abstract
The nnUNet segmentation framework adeptly adjusts most hyperparameters in training scripts automatically, but it overlooks the tuning of internal hyperparameters within the segmentation network itself, which constrains the model's ability to generalize. Addressing this limitation, this study presents a novel Self-Adaptive Convolution Module that dynamically adjusts the size of the convolution kernels depending on the unique fingerprints of different datasets. This adjustment enables the MSA2-Net, when equipped with this module, to proficiently capture both global and local features within the feature maps. Self-Adaptive Convolution Module is strategically integrated into two key components of the MSA2-Net: the Multi-Scale Convolution Bridge and the Multi-Scale Amalgamation Decoder. In the MSConvBridge, the module enhances the ability to refine outputs from various stages of the CSWin Transformer during the skip connections, effectively eliminating redundant data that could potentially impair the decoder's performance. Simultaneously, the MSADecoder, utilizing the module, excels in capturing detailed information of organs varying in size during the decoding phase. This capability ensures that the decoder's output closely reproduces the intricate details within the feature maps, thus yielding highly accurate segmentation images. MSA2-Net, bolstered by this advanced architecture, has demonstrated exceptional performance, achieving Dice coefficient scores of 86.49%, 92.56%, 93.37%, and 92.98% on the Synapse, ACDC, Kvasir, and Skin Lesion Segmentation (ISIC2017) datasets, respectively. This underscores MSA2-Net's robustness and precision in medical image segmentation tasks across various datasets.