<p>LM-UNet encoder input and output dimensions.</p>

Accurate segmentation of lesions in prostate magnetic resonance images (MRI) is important for assessing patient health and personalized treatment in the clinic. However, the traditional UNet segmentation network has low segmentation accuracy because of the fuzzy boundary and low contrast. Therefore, we propose a Lightweight Mamba-UNet (LM-UNet) prostate MRI image segmentation method. Initially, the encoder-decoder backbone structure consists of parallel vision mamba (PV-Mamba) and efficient multi-scale attention (EMA). The number of model parameters is reduced by constructing PV-Mamba while extracting the correlation between features over long distances. The EMA is then used to learn different spatial features in groups and construct cross-spatial information aggregation methods for richer feature aggregation. Subsequently, we construct the edge feature extraction (EFE) and the edge feature fusion (EFF) to achieve different levels of feature fusion in the encoder. Ultimately, we suggest a multi-stage and multi-level skip connections (MMSC) to achieve multi-level fusion between the encoder and decoder, there reducing semantic discrepancies between contextual features and improving segmentation accuracy. Experimental results demonstrate that on the PROMISE12 dataset, LM-UNet outperforms seven comparative segmentation methods in terms of parameter count, computational memory requirements, and precise segmentation of lesion margins.

前列腺磁共振成像（MRI）病灶的精准分割，对于临床患者的健康评估与个性化治疗具有重要意义。然而，传统U型网络（UNet）分割网络因病灶边界模糊、图像对比度较低，分割精度欠佳。为此，本文提出一种轻量级Mamba-UNet（LM-UNet）前列腺MRI图像分割方法。该方法的编解码主干结构由并行视觉Mamba（PV-Mamba）与高效多尺度注意力（EMA）模块构成：通过构建并行视觉Mamba模块，在提取特征长距离相关性的同时降低模型参数量；随后利用高效多尺度注意力模块实现分组学习不同空间特征，并构建跨空间信息聚合机制以实现更丰富的特征融合。后续，本文构建边缘特征提取（EFE）与边缘特征融合（EFF）模块，实现编码器内不同层级的特征融合。最终，本文提出多阶段多级跳跃连接（MMSC）机制，实现编解码间的多级特征融合，进而缩小上下文特征间的语义差异，提升分割精度。实验结果表明，在PROMISE12数据集上，LM-UNet在参数量、计算内存占用以及病灶边缘精准分割方面，均优于7种对比分割方法。