Dastgir Aqsa, Bin Wang, Saeed Muhammad Usman, Sheng Jinfang, Site Luo, Hassan Haseeb
School of Computer Science and Engineering, Central South University, Changsha, 410083, China.
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen, 518118, China.
Sci Rep. 2025 Apr 16;15(1):13102. doi: 10.1038/s41598-025-95243-z.
Segmenting the spine from CT images is crucial for diagnosing and treating spine-related conditions but remains challenging due to the spine's complex anatomy and imaging artifacts. This study introduces a novel encoder-decoder-based deep learning approach, named LinkNet-152, tailored for automated spine segmentation. The model integrates a modified EfficientNetB7 encoder with attention modules to enhance feature extraction by focusing on regions of interest. The decoder leverages a modified LinkNet architecture, replacing ResNet34 with the deeper ResNet152 to improve feature extraction and segmentation accuracy. Additionally, gradient sensitivity-based pruning is applied to optimize the model's complexity and computational efficiency. Evaluated on the VerSe 2019 and VerSe 2020 datasets, the proposed model achieves superior performance, with a Dice coefficient of 96.85% and a Jaccard index of 95.37%, outperforming state-of-the-art methods. These results highlight the model's effectiveness in addressing the challenges of spine segmentation and its potential to advance clinical applications.
从CT图像中分割出脊柱对于诊断和治疗脊柱相关疾病至关重要，但由于脊柱解剖结构复杂以及成像伪影，这一过程仍然具有挑战性。本研究介绍了一种基于编码器-解码器的新型深度学习方法，名为LinkNet-152，专为脊柱自动分割量身定制。该模型将经过修改的EfficientNetB7编码器与注意力模块相结合，通过关注感兴趣区域来增强特征提取。解码器采用了经过修改的LinkNet架构，用更深的ResNet152取代ResNet34，以提高特征提取和分割精度。此外，还应用了基于梯度敏感性的剪枝来优化模型的复杂度和计算效率。在VerSe 2019和VerSe 2020数据集上进行评估时，所提出的模型表现卓越，Dice系数为96.85%，Jaccard指数为95.37%，优于现有最先进的方法。这些结果凸显了该模型在应对脊柱分割挑战方面的有效性及其推动临床应用的潜力。
