基于对比与重构的无监督多粒度眼底图像分割

Unsupervised Multi-granularity Segmentation of Fundus Images Based on Comparison and Reconstruction

摘要:

针对眼底图像分割任务对大规模标注数据依赖强、特征表达不足以及分割结果单一的问题,提出了一种无监督多粒度视网膜图像分割方法。构建了新型的全卷积编码器-解码器结构,用以充分捕捉图像的局部细节与全局语义特征,实现多层次特征的高效重构。在此基础上,设计了一种综合损失函数,将像素级补丁对比损失、表征级对比学习损失与全局重构损失进行联合优化,通过多尺度特征约束强化模型的表征能力,使特征空间更适配分割任务的结构分布。在得到的表征空间中引入扩散凝聚算法,以聚合多尺度语义信息,提升分割边界的精确性与整体结构的连贯性,并生成具有层次性和多粒度特征的分割结果。在公开的视网膜眼底数据集上对提出的方法进行验证,结果显示,该方法在无监督条件下的Dice系数较当前主流无监督分割模型平均提升3.7%,在分割细节保真度与结构一致性方面均表现出显著优势,该方法能够有效实现眼底图像的高精度、多粒度分割。

Abstract:

To address the challenges of strong dependence on large-scale labeled data, insufficient feature representation, and single-granularity segmentation results in retinal fundus image segmentation, an unsupervised multi-granularity segmentation method for retinal images is proposed. A novel fully convolutional encoder-decoder architecture was designed to effectively capture local details and global semantic features of images, achieving efficient reconstruction of multi-level representations. On this basis, a comprehensive loss function was constructed by integrating pixel-level patch contrastive loss, representation-level contrastive learning loss, and global reconstruction loss. This joint optimization constrained the model across multiple feature scales, enhancing the representation capability and aligning the feature space with the structural distribution of the segmentation task. Subsequently, a diffusion-condensation algorithm was applied within the representation space to aggregate multi-scale semantic information, improving boundary precision and structural coherence, and generating segmentation results with hierarchical and multi-granular characteristics. Experiments conducted on publicly available retinal fundus datasets demonstrated that the proposed method achieved a 3.7% improvement in Dice coefficient compared with state-of-the-art unsupervised segmentation approaches, showing superior performance in both detail fidelity and structural consistency. The results indicated that this method enabled accurate and multi-granularity segmentation of retinal fundus images.