Gu Zhongzheng, Wang Xuan, Chen Baojun
Department of Spine and Spinal Cord Surgery, Henan Provincial People's Hospital, Zhengzhou, Henan, China.
Department of Medical Imaging, The Third Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
Front Physiol. 2025 Aug 29;16:1651296. doi: 10.3389/fphys.2025.1651296. eCollection 2025.
Spinal X-ray image segmentation faces several challenges, such as complex anatomical structures, large variations in scale, and blurry or low-contrast boundaries between vertebrae and surrounding tissues. These factors make it difficult for traditional models to achieve accurate and robust segmentation. To address these issues, this study proposes MDWC-Net, a novel deep learning framework designed to improve the accuracy and efficiency of spinal structure identification in clinical settings.
MDWC-Net adopts an encoder-decoder architecture and introduces three modules-MSCAW, DFCB, and BIEB-to address key challenges in spinal X-ray image segmentation. The network is trained and evaluated on the Spine Dataset, which contains 280 X-ray images provided by Henan Provincial People's Hospital and is randomly divided into training, validation, and test sets with a 7:1:2 ratio. In addition, to evaluate the model's generalizability, further validation was conducted on the Chest X-ray dataset for lung field segmentation and the ISIC2016 dataset for melanoma boundary delineation.
MDWC-Net outperformed other mainstream models overall. On the Spine Dataset, it achieved a Dice score of 89.86% ± 0.356, MIoU of 90.53% ± 0.315, GPA of 96.82% ± 0.289, and Sensitivity of 96.77% ± 0.212. A series of ablation experiments further confirmed the effectiveness of the MSCAW, DFCB, and BIEB modules.
MDWC-Net delivers accurate and efficient segmentation of spinal structures, showing strong potential for integration into clinical workflows. Its high performance and generalizability suggest broad applicability to other medical image segmentation tasks.
脊柱X线图像分割面临诸多挑战，如解剖结构复杂、尺度变化大以及椎骨与周围组织之间的边界模糊或对比度低。这些因素使得传统模型难以实现准确且稳健的分割。为解决这些问题，本研究提出了MDWC-Net，这是一种新型深度学习框架，旨在提高临床环境中脊柱结构识别的准确性和效率。
MDWC-Net采用编码器-解码器架构，并引入了三个模块——MSCAW、DFCB和BIEB，以应对脊柱X线图像分割中的关键挑战。该网络在脊柱数据集上进行训练和评估，该数据集包含河南省人民医院提供的280张X线图像，并以7:1:2的比例随机分为训练集、验证集和测试集。此外，为评估模型的通用性，还在用于肺野分割的胸部X线数据集和用于黑色素瘤边界描绘的ISIC2016数据集上进行了进一步验证。
MDWC-Net总体上优于其他主流模型。在脊柱数据集上，它的Dice分数达到89.86%±0.356，MIoU为90.53%±0.315，GPA为96.82%±0.289，灵敏度为96.77%±0.212。一系列消融实验进一步证实了MSCAW、DFCB和BIEB模块的有效性。
MDWC-Net能够对脊柱结构进行准确且高效的分割，显示出在临床工作流程中集成的强大潜力。其高性能和通用性表明它在其他医学图像分割任务中具有广泛的适用性。
