CENet: Context Enhancement Network for Medical Image Segmentation

2025-05-23

AI Summary

To address the challenges of ambiguous boundaries, large anatomical variations, and information loss from downsampling in multi-domain medical image segmentation—which collectively limit accuracy and robustness—this paper proposes a novel encoder-decoder framework. Our method introduces two key components: (1) a Dual Selective Enhancement Block (DSEB) that jointly enhances boundary and small-organ features in skip connections via channel- and spatial-wise selective attention; and (2) a Contextual Feature Attention Module (CFAM) that adaptively fuses multi-level contextual features while suppressing redundant activations to preserve spatial integrity. Evaluated on multimodal datasets including radiological and dermoscopic images, our approach achieves significant improvements over state-of-the-art methods in multi-organ segmentation accuracy and boundary fidelity. The source code is publicly available.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Medical image segmentation, particularly in multi-domain scenarios, requires precise preservation of anatomical structures across diverse representations. While deep learning has advanced this field, existing models often struggle with accurate boundary representation, variability in organ morphology, and information loss during downsampling, limiting their accuracy and robustness. To address these challenges, we propose the Context Enhancement Network (CENet), a novel segmentation framework featuring two key innovations. First, the Dual Selective Enhancement Block (DSEB) integrated into skip connections enhances boundary details and improves the detection of smaller organs in a context-aware manner. Second, the Context Feature Attention Module (CFAM) in the decoder employs a multi-scale design to maintain spatial integrity, reduce feature redundancy, and mitigate overly enhanced representations. Extensive evaluations on both radiology and dermoscopic datasets demonstrate that CENet outperforms state-of-the-art (SOTA) methods in multi-organ segmentation and boundary detail preservation, offering a robust and accurate solution for complex medical image analysis tasks. The code is publicly available at https://github.com/xmindflow/cenet.

Problem

• Improves boundary representation in medical image segmentation
• Addresses variability in organ morphology across domains
• Reduces information loss during downsampling in segmentation models

Innovation

• DSEB enhances boundary details contextually
• CFAM maintains spatial integrity multi-scale
• CENet outperforms SOTA in segmentation