Mixed-GGNAS: Mixed Search-space NAS based on genetic algorithm combined with gradient descent for medical image segmentation

• Published in: Expert systems with applications Vol. 289; p. 128338
• Main Authors: Hu, Mengxiang, Li, Junchi, Dong, Yongquan, Zhang, Zichen, Liu, Weifan, Zhang, Peilin, Ping, Yuchao, Jiang, Le, Yu, Zekuan
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.09.2025
• Subjects: Genetic Al-gorithm; Gradient descent; Neural architecture search; Vision Transformer; Gradient descent; Genetic Al-gorithm; Neural architecture search; Vision Transformer
• ISSN: 0957-4174
• DOI: 10.1016/j.eswa.2025.128338

Medical images segmentation is a pivotal procedure, playing a fundamental role in computer-assisted diagnosis and treatment. Despite the significant advancements in methods leveraging deep learning for this purpose, many networks still face challenges related to efficiency, often requiring substantial time and manual efforts. Neural architecture search (NAS) has gained considerable attention in the automated design of neural networks. This study introduces a new NAS method, Mixed-GGNAS, a Mixed Search-space NAS method based on Genetic algorithm combined with Gradient descent. Our approach creatively combines manually designed network blocks with DARTS blocks to construct a mixed search space. We then employ a method that integrates genetic algorithms and gradient descent to concurrently search for both block types and internal operations within the block. Within a U-shaped network framework, we propose a Multi-feature fusion strategy based on Vision Transformer (ViT) and search for hyperparameters of it. Additionally, we employ a Multi-scale mixed loss function to enhance the model’s ability to learn features at various scales. Experimental results demonstrate that the proposed approach outperforms or is comparable to the state-of-the-art NAS methods and manually designed Networks. Ablation studies conducted on two datasets further validate the method’s efficacy in enhancing model performance. The code is available at https://github.com/Hmxki/Mixed-GGNAS.