Boosting medical image segmentation via conditional-synergistic convolution and lesion decoupling. (October 2022)

• Record Type: Journal Article
• Authors: Yang, Huakun; Chen, Qian; Fu, Keren; Zhu, Lei; Jin, Lujia; Qiu, Bensheng; Ren, Qiushi; Du, Hongwei; Lu, Yanye
• Is Part Of: Computerized medical imaging and graphics. Volume 101(2022)
• Publication Date: 2022-10
• Subjects: Medical image segmentation -- Dynamic convolution -- Decoupling strategy -- Transformer backbone; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2022.102110
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: Medical image segmentation is a critical step in pathology assessment and monitoring. Extensive methods tend to utilize a deep convolutional neural network for various medical segmentation tasks, such as polyp segmentation, skin lesion segmentation, etc . However, due to the inherent difficulty of medical images and tremendous data variations, they usually perform poorly in some intractable cases. In this paper, we propose an input-specific network called conditional-synergistic convolution and lesion decoupling network (CCLDNet) to solve these issues. First, in contrast to existing CNN-based methods with stationary convolutions, we propose the conditional synergistic convolution (CSConv) that aims to generate a specialist convolution kernel for each lesion. CSConv has the ability of dynamic modeling and could be leveraged as a basic block to construct other networks in a broad range of vision tasks. Second, we devise a lesion decoupling strategy (LDS) to decouple the original lesion segmentation map into two soft labels, i.e., lesion center label and lesion boundary label, for reducing the segmentation difficulty. Besides, we use a transformer network as the backbone, further erasing the fixed structure of the standard CNN and empowering dynamic modeling capability of the whole framework. Our CCLDNet outperforms state-of-the-art approaches by a large margin on a variety of benchmarks, including polyp segmentation (89.22% dice score on EndoScene) and skin lesion segmentation (91.15% dice score on ISIC2018). Our code is available at https://github.com/QianChen98/CCLD-Net . Highlights: In contrast to existing CNN-based methods with stationary convolutions, we propose a novel dynamic operator called conditional synergistic convolution (CSConv) that aims to generate a specialist convolution kernel for each lesion. In order to reduce the difficulty of medical image segmentation, we propose a lesion decoupling strategy and combine it with dynamic convolution. The proposed network outperforms state-of-the-art segmentation algorithms by a large margin on six benchmarks, including polyp segmentation and skin lesion segmentation.