An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation

2025-08-23

AI Summary

To address the trade-off between accuracy and efficiency in multi-organ segmentation of medical images, this paper proposes a lightweight and efficient dual-path decoding network. Our method introduces three key innovations: (1) a noise-robust dual-decoder architecture—during training, a noisy branch enhances generalization; during inference, only the clean branch is activated, drastically reducing computational overhead; (2) a multi-scale convolutional attention module (MSCAM) that integrates attention gates (AG) and uncertainty-aware channel boosting (UCB) to strengthen cross-scale feature selection and fusion; and (3) a mutation-aware loss function to further improve model generalization. Evaluated on the Synapse dataset, our method achieves a Dice score of 84.00%, outperforming U-Net by 13.89% while reducing MACs by 89.7%. It also establishes new state-of-the-art performance across multiple public benchmarks, simultaneously achieving superior segmentation accuracy and real-time inference capability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• 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
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Proper segmentation of organs-at-risk is important for radiation therapy, surgical planning, and diagnostic decision-making in medical image analysis. While deep learning-based segmentation architectures have made significant progress, they often fail to balance segmentation accuracy with computational efficiency. Most of the current state-of-the-art methods either prioritize performance at the cost of high computational complexity or compromise accuracy for efficiency. This paper addresses this gap by introducing an efficient dual-line decoder segmentation network (EDLDNet). The proposed method features a noisy decoder, which learns to incorporate structured perturbation at training time for better model robustness, yet at inference time only the noise-free decoder is executed, leading to lower computational cost. Multi-Scale convolutional Attention Modules (MSCAMs), Attention Gates (AGs), and Up-Convolution Blocks (UCBs) are further utilized to optimize feature representation and boost segmentation performance. By leveraging multi-scale segmentation masks from both decoders, we also utilize a mutation-based loss function to enhance the model's generalization. Our approach outperforms SOTA segmentation architectures on four publicly available medical imaging datasets. EDLDNet achieves SOTA performance with an 84.00% Dice score on the Synapse dataset, surpassing baseline model like UNet by 13.89% in Dice score while significantly reducing Multiply-Accumulate Operations (MACs) by 89.7%. Compared to recent approaches like EMCAD, our EDLDNet not only achieves higher Dice score but also maintains comparable computational efficiency. The outstanding performance across diverse datasets establishes EDLDNet's strong generalization, computational efficiency, and robustness. The source code, pre-processed data, and pre-trained weights will be available at https://github.com/riadhassan/EDLDNet .

Problem

• Balancing segmentation accuracy with computational efficiency
• Improving multi-organ segmentation in medical imaging
• Reducing computational cost while maintaining high performance

Innovation

• Dual-line decoder network for efficient segmentation
• Multi-scale convolutional attention modules optimize features
• Mutation-based loss function enhances model generalization