HyM-UNet: Synergizing Local Texture and Global Context via Hybrid CNN-Mamba Architecture for Medical Image Segmentation

TL;DR

HyM-UNet introduces a hybrid CNN-Mamba architecture that combines local texture features with global context modeling, significantly improving medical image segmentation accuracy while reducing model complexity.

Contribution

This paper presents a novel hybrid CNN-Mamba architecture with a hierarchical encoder and Mamba-Guided Fusion skip connections for enhanced global and local feature integration in medical segmentation.

Findings

Outperforms state-of-the-art methods on ISIC 2018 dataset

Achieves higher Dice coefficient and IoU scores

Maintains lower parameter count and faster inference

Abstract

Accurate organ and lesion segmentation is a critical prerequisite for computer-aided diagnosis. Convolutional Neural Networks (CNNs), constrained by their local receptive fields, often struggle to capture complex global anatomical structures. To tackle this challenge, this paper proposes a novel hybrid architecture, HyM-UNet, designed to synergize the local feature extraction capabilities of CNNs with the efficient global modeling capabilities of Mamba. Specifically, we design a Hierarchical Encoder that utilizes convolutional modules in the shallow stages to preserve high-frequency texture details, while introducing Visual Mamba modules in the deep stages to capture long-range semantic dependencies with linear complexity. To bridge the semantic gap between the encoder and the decoder, we propose a Mamba-Guided Fusion Skip Connection (MGF-Skip). This module leverages deep semantic features as gating signals to dynamically suppress background noise within shallow features, thereby enhancing the perception of ambiguous boundaries. We conduct extensive experiments on public benchmark dataset ISIC 2018. The results demonstrate that HyM-UNet significantly outperforms existing state-of-the-art methods in terms of Dice coefficient and IoU, while maintaining lower parameter counts and inference latency. This validates the effectiveness and robustness of the proposed method in handling medical segmentation tasks characterized by complex shapes and scale variations.