SSHNN: Semi-Supervised Hybrid NAS Network for Echocardiographic Image Segmentation
This addresses the problem of limited labeled data and poor feature aggregation in medical image segmentation for echocardiography, though it is incremental in combining existing techniques like NAS, Transformers, and semi-supervised learning.
The paper tackled accurate segmentation of noisy echocardiographic images by proposing SSHNN, a semi-supervised hybrid NAS network that integrates convolution for feature fusion and Transformers for global context, achieving state-of-the-art results on the CAMUS dataset.
Accurate medical image segmentation especially for echocardiographic images with unmissable noise requires elaborate network design. Compared with manual design, Neural Architecture Search (NAS) realizes better segmentation results due to larger search space and automatic optimization, but most of the existing methods are weak in layer-wise feature aggregation and adopt a ``strong encoder, weak decoder" structure, insufficient to handle global relationships and local details. To resolve these issues, we propose a novel semi-supervised hybrid NAS network for accurate medical image segmentation termed SSHNN. In SSHNN, we creatively use convolution operation in layer-wise feature fusion instead of normalized scalars to avoid losing details, making NAS a stronger encoder. Moreover, Transformers are introduced for the compensation of global context and U-shaped decoder is designed to efficiently connect global context with local features. Specifically, we implement a semi-supervised algorithm Mean-Teacher to overcome the limited volume problem of labeled medical image dataset. Extensive experiments on CAMUS echocardiography dataset demonstrate that SSHNN outperforms state-of-the-art approaches and realizes accurate segmentation. Code will be made publicly available.