中文标题#
MLRU++：具有注意力机制的多尺度轻量级残差 UNETR++ 用于高效的三维医学图像分割
英文标题#
MLRU++: Multiscale Lightweight Residual UNETR++ with Attention for Efficient 3D Medical Image Segmentation
中文摘要#
准确且高效的医学图像分割由于解剖学的变异性以及对体积数据的高计算需求而具有挑战性。最近的混合卷积神经网络 - Transformer 架构取得了最先进的结果，但增加了显著的复杂性。在本文中，我们提出了 MLRU++，一种多尺度轻量级残差 UNETR++ 架构，旨在平衡分割精度和计算效率。它引入了两个关键创新：一个轻量级通道和瓶颈注意力模块（LCBAM），以最小的开销增强上下文特征编码，以及解码器中的多尺度瓶颈块（M2B），通过多分辨率特征聚合捕捉细粒度细节。在四个公开可用的基准数据集（Synapse、BTCV、ACDC 和 Decathlon Lung）上的实验表明，MLRU++ 取得了最先进的性能，平均 Dice 分数分别为 87.57%（Synapse）、93.00%（ACDC）和 81.12%（Lung）。与现有领先模型相比，MLRU++ 在 Synapse 和 ACDC 上的 Dice 分数分别提高了 5.38% 和 2.12%，同时显著减少了参数数量和计算成本。评估 LCBAM 和 M2B 的消融研究进一步证实了所提出架构组件的有效性。结果表明，MLRU++ 为 3D 医学图像分割任务提供了一个实用且高性能的解决方案。源代码可在以下位置获取：https://github.com/1027865/MLRUPP
英文摘要#
Accurate and efficient medical image segmentation is crucial but challenging due to anatomical variability and high computational demands on volumetric data. Recent hybrid CNN-Transformer architectures achieve state-of-the-art results but add significant complexity. In this paper, we propose MLRU++, a Multiscale Lightweight Residual UNETR++ architecture designed to balance segmentation accuracy and computational efficiency. It introduces two key innovations: a Lightweight Channel and Bottleneck Attention Module (LCBAM) that enhances contextual feature encoding with minimal overhead, and a Multiscale Bottleneck Block (M2B) in the decoder that captures fine-grained details via multi-resolution feature aggregation. Experiments on four publicly available benchmark datasets (Synapse, BTCV, ACDC, and Decathlon Lung) demonstrate that MLRU++ achieves state-of-the-art performance, with average Dice scores of 87.57% (Synapse), 93.00% (ACDC), and 81.12% (Lung). Compared to existing leading models, MLRU++ improves Dice scores by 5.38% and 2.12% on Synapse and ACDC, respectively, while significantly reducing parameter count and computational cost. Ablation studies evaluating LCBAM and M2B further confirm the effectiveness of the proposed architectural components. Results suggest that MLRU++ offers a practical and high-performing solution for 3D medical image segmentation tasks. Source code is available at: https://github.com/1027865/MLRUPP
PDF 获取#
抖音扫码查看更多精彩内容