Deep learning is the mainstream method for medical image segmentation, and neural architecture search (NAS) has also been developed for this task. However, existing NAS methods remain limited in their ability to search for high-performance yet lightweight network architectures due to the high computational cost of NAS and the low fidelity of performance evaluation during the search process. In this paper, we propose a novel once-for-all NAS method for medical image segmentation to address these challenges. A carefully designed search space (supernet) incorporating key components of U-shape networks is constructed specifically for medical image segmentation. An effective and efficient hybrid two-stage supernet training scheme is then designed to enhance supernet training while maintaining a balance between performance and computational cost. A multi-objective evolutionary algorithm is leveraged to search for sets of network architectures, which produces high-performing architectures with varying computational complexities, optimized under multiple objectives. We conduct experiments on six widely used medical image segmentation datasets. Compared with existing methods, the proposed method achieves state-of-the-art performance on all six datasets. The searched architectures exhibit an excellent trade-off between performance and computational complexity, which is attributed to the effective multi-objective search. Our source codes are available at https://github.com/jiahongwei21-lang/MOOFA4MIS.

Recently, deep learning-based methods have become the mainstream for medical image segmentation. Since manually designing deep neural networks (DNNs) is laborious and time-consuming, neural architecture search (NAS) becomes a popular stream for automatically designing DNNs for medical image segmentation. However, existing NAS work for medical image segmentation is still computationally expensive. Given the limited computation power, it is not always applicable to search for a well-performing model from an enlarged search space. In this paper, we propose EZUAS, a novel method of evolutionary zero-shot NAS for medical image segmentation, to address these issues. First, a new search space is designed for the automated design of DNNs. A genetic algorithm (GA) with an aligned crossover operation is then leveraged to search the network architectures under the model complexity constraints to get performant and lightweight models. In addition, a variable-length integer encoding scheme is devised to encode the candidate U-shaped DNNs with different stages. We conduct experiments on two commonly used medical image segmentation datasets to verify the effectiveness of the proposed EZUAS. Compared with the state-of-the-art methods, the proposed method can find a model much faster (about 0.04 GPU day) and achieve the best performance with lower computational complexity.

Recently, many methods based on hand-designed convolutional neural networks (CNNs) have achieved promising results in automatic retinal vessel segmentation. However, these CNNs remain constrained in capturing retinal vessels in complex fundus images. To improve their segmentation performance, these CNNs tend to have many parameters, which may lead to overfitting and high computational complexity. Moreover, the manual design of competitive CNNs is time-consuming and requires extensive empirical knowledge. Herein, a novel automated design method, called Genetic U-Net, is proposed to generate a U-shaped CNN that can achieve better retinal vessel segmentation but with fewer architecture-based parameters, thereby addressing the above issues. First, we devised a condensed but flexible search space based on a U-shaped encoder-decoder. Then, we used an improved genetic algorithm to identify better-performing architectures in the search space and investigated the possibility of finding a superior network architecture with fewer parameters. The experimental results show that the architecture obtained using the proposed method offered a superior performance with less than 1% of the number of the original U-Net parameters in particular and with significantly fewer parameters than other state-of-the-art models. Furthermore, through in-depth investigation of the experimental results, several effective operations and patterns of networks to generate superior retinal vessel segmentations were identified. The codes of this work are available at https://github.com/96jhwei/Genetic-U-Net.