BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
This work addresses computational efficiency for medical image segmentation tasks, representing an incremental improvement over existing methods.
The paper tackled the problem of high computational costs in recurrent U-Net architectures for medical image segmentation by proposing BiX-NAS, a two-phase neural architecture search method that sifts out ineffective multi-scale features. The result is a state-of-the-art performance with significantly lower computational cost, as evaluated on three medical image datasets.
The recurrent mechanism has recently been introduced into U-Net in various medical image segmentation tasks. Existing studies have focused on promoting network recursion via reusing building blocks. Although network parameters could be greatly saved, computational costs still increase inevitably in accordance with the pre-set iteration time. In this work, we study a multi-scale upgrade of a bi-directional skip connected network and then automatically discover an efficient architecture by a novel two-phase Neural Architecture Search (NAS) algorithm, namely BiX-NAS. Our proposed method reduces the network computational cost by sifting out ineffective multi-scale features at different levels and iterations. We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost.