Interactive Deep Refinement Network for Medical Image Segmentation
This addresses the need for improved segmentation in computer-aided diagnosis for medical imaging, though it appears incremental as it builds on existing networks.
The paper tackles the problem of low-contrast medical image segmentation by proposing an interactive deep refinement framework that enhances traditional networks like U-Net, achieving higher accuracy than state-of-the-art methods on a public dataset.
Deep learning techniques have successfully been employed in numerous computer vision tasks including image segmentation. The techniques have also been applied to medical image segmentation, one of the most critical tasks in computer-aided diagnosis. Compared with natural images, the medical image is a gray-scale image with low-contrast (even with some invisible parts). Because some organs have similar intensity and texture with neighboring organs, there is usually a need to refine automatic segmentation results. In this paper, we propose an interactive deep refinement framework to improve the traditional semantic segmentation networks such as U-Net and fully convolutional network. In the proposed framework, we added a refinement network to traditional segmentation network to refine the segmentation results.Experimental results with public dataset revealed that the proposed method could achieve higher accuracy than other state-of-the-art methods.