3D MFA：一种基于自动3D多特征注意力的方法，用于使用多阶段网络剪枝的脊柱分割。

3D MFA: An automated 3D Multi-Feature Attention based approach for spine segmentation using a multi-stage network pruning.

作者信息

Saeed Muhammad Usman, Bin Wang, Sheng Jinfang, Saleem Salman

机构信息

School of Computer Science and Engineering, Central South University, Changsha, 410083, Hunan, China.

出版信息

Comput Biol Med. 2025 Feb;185:109526. doi: 10.1016/j.compbiomed.2024.109526. Epub 2024 Dec 20.

DOI:10.1016/j.compbiomed.2024.109526

PMID:39708496

Abstract

Spine segmentation poses significant challenges due to the complex anatomical structure of the spine and the variability in imaging modalities, which often results in unclear boundaries and overlaps with surrounding tissues. In this research, a novel 3D Multi-Feature Attention (MFA) model is proposed for spine segmentation. The standard MobileNetv3 is modified by adding the RCBAM (Reverse Convolution Block Attention Module) module, and FPP (Feature Pyramid Pooling) for feature enhancement. Each modified MobileNetv3 is trained separately on axial, coronal, and sagittal views of 3D images. The features are concatenated to form a 3D feature map and given to the decoder part for spine segmentation. The results show that the 3D MFA outperforms from state-of-the-art method with DCS (dice coefficient score), and IoU (Intersection over Union) of 96.52%, and 95.84% on VerSe 2020 dataset while 94.64% and 93.69% on VerSe 2019 dataset with less computational cost.

摘要

由于脊柱复杂的解剖结构以及成像方式的多样性，脊柱分割面临重大挑战，这常常导致边界不清晰以及与周围组织重叠。在本研究中，提出了一种用于脊柱分割的新型3D多特征注意力（MFA）模型。通过添加RCBAM（反向卷积块注意力模块）模块和用于特征增强的FPP（特征金字塔池化）对标准MobileNetv3进行修改。每个修改后的MobileNetv3分别在3D图像的轴向、冠状和矢状视图上进行训练。将这些特征连接起来形成一个3D特征图，并将其输入到解码器部分进行脊柱分割。结果表明，在VerSe 2020数据集上，3D MFA在骰子系数得分（DCS）和交并比（IoU）方面优于现有方法，分别达到96.52%和95.84%，而在VerSe 2019数据集上，在计算成本较低的情况下，分别为94.64%和93.69%。