DCFFSNet: Deep Connectivity Feature Fusion Separation Network for Medical Image Segmentation

2025-07-24

AI Summary

To address edge ambiguity and regional discontinuity in medical image segmentation, existing methods forcibly embed topological connectivity into feature extraction modules, resulting in coupled features and the absence of intensity quantification mechanisms. This paper proposes the Deep Connectivity Feature Fusion-Separation Network (DCFS-Net), which introduces a novel feature-space decoupling strategy to explicitly model and quantify the relative strength of connectivity features against other multi-scale features. A dynamic fusion-separation architecture is further designed to enable adaptive balancing of feature representations. Evaluated on ISIC2018, DSB2018, and MoNuSeg benchmarks, DCFS-Net consistently outperforms state-of-the-art models, achieving up to 1.3% and 1.2% improvements in Dice and IoU scores, respectively. The method significantly suppresses segmentation fragmentation while enhancing edge continuity and regional coherence, thereby improving clinical utility.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Medical image segmentation leverages topological connectivity theory to enhance edge precision and regional consistency. However, existing deep networks integrating connectivity often forcibly inject it as an additional feature module, resulting in coupled feature spaces with no standardized mechanism to quantify different feature strengths. To address these issues, we propose DCFFSNet (Dual-Connectivity Feature Fusion-Separation Network). It introduces an innovative feature space decoupling strategy. This strategy quantifies the relative strength between connectivity features and other features. It then builds a deep connectivity feature fusion-separation architecture. This architecture dynamically balances multi-scale feature expression. Experiments were conducted on the ISIC2018, DSB2018, and MoNuSeg datasets. On ISIC2018, DCFFSNet outperformed the next best model (CMUNet) by 1.3% (Dice) and 1.2% (IoU). On DSB2018, it surpassed TransUNet by 0.7% (Dice) and 0.9% (IoU). On MoNuSeg, it exceeded CSCAUNet by 0.8% (Dice) and 0.9% (IoU). The results demonstrate that DCFFSNet exceeds existing mainstream methods across all metrics. It effectively resolves segmentation fragmentation and achieves smooth edge transitions. This significantly enhances clinical usability.

Problem

• Decouples connectivity and other features in medical image segmentation
• Quantifies relative feature strengths to improve segmentation accuracy
• Reduces segmentation fragmentation for smoother edge transitions

Innovation

• Feature space decoupling strategy for connectivity
• Dynamic multi-scale feature expression balancing
• Deep connectivity fusion-separation architecture design