MS-NAS: Multi-Scale Neural Architecture Search for Medical Image Segmentation
This work addresses the need for more efficient architecture search in medical image segmentation, though it appears incremental by extending NAS with multi-scale features.
The paper tackles the problem of limited search space in neural architecture search for medical image segmentation by proposing a multi-scale NAS framework, achieving 0.6-5.4% mIOU and 0.4-3.5% DSC improvements while reducing computational resource consumption by 18.0-24.9%.
The recent breakthroughs of Neural Architecture Search (NAS) have motivated various applications in medical image segmentation. However, most existing work either simply rely on hyper-parameter tuning or stick to a fixed network backbone, thereby limiting the underlying search space to identify more efficient architecture. This paper presents a Multi-Scale NAS (MS-NAS) framework that is featured with multi-scale search space from network backbone to cell operation, and multi-scale fusion capability to fuse features with different sizes. To mitigate the computational overhead due to the larger search space, a partial channel connection scheme and a two-step decoding method are utilized to reduce computational overhead while maintaining optimization quality. Experimental results show that on various datasets for segmentation, MS-NAS outperforms the state-of-the-art methods and achieves 0.6-5.4% mIOU and 0.4-3.5% DSC improvements, while the computational resource consumption is reduced by 18.0-24.9%.