@article{ZHANG2025, 
author = {Ying ZHANG and XiaoQi PU and HaiJiang ZHU},
title = {A method for segmentation of lumbar spine CT images based on an improved Rolling U-Net},
year = {2025},
journal = {Journal of Beijing University of Chemical Technology (Natural Science Edition)},
volume = {52},
number = {6},
pages = {99-108},
keywords = {lumbar spine segmentation, CT images, Rolling U-Net, multilayer perceptron (MLP)},
url = {https://www.sciopen.com/article/10.13543/j.bhxbzr.2025.06.012},
doi = {10.13543/j.bhxbzr.2025.06.012},
abstract = {Segmentation of lumbar vertebrae in CT images has significant importance in the auxiliary diagnosis and treatment of lumbar diseases. The U-Net architecture and its extended models have attracted extensive attention in the field of medical image segmentation. By addressing issues such as the loss of fine-grained features in lumbar segmentation using the Rolling U-Net model, an improved Rolling U-Net model is proposed for segmenting lumbar CT images. This model integrates a convolutional neural network (CNN) with a multi-layer perceptron (MLP). Feature excitation modules are inserted at the fourth convolutional layer and the bottleneck layer to increase the weight of key anatomical structures. By constructing long-range-local blocks (Lo2 blocks), it achieves the fusion of local feature information with long-range dependencies. The core R-MLP module within the Lo2 block learns long-range dependencies across the entire image in a single direction. By controlling and combining R-MLP modules oriented in different directions, OR-MLP and DOR-MLP modules are constructed to capture long-range dependencies in multiple directions. Finally, residual convolutions are integrated to restore segmentation details in the lumbar spine. Simultaneously, a MultiClassDiceCE loss function is designed by combining the pixel classification advantages of the Dice loss function and the cross-entropy loss function. Experimental results indicate that the number of categories and sampling strategies significantly impact the segmentation performance of the improved Rolling U-Net model. For binary segmentation tasks, the division strategy based on the total number of images is recommended to balance accuracy and stability, whereas the division strategy based on the total number of instances is better suited for multi-classification tasks. When performing multi-class segmentation tasks on the JST_LV and VerSe datasets, the improved Rolling U-Net model outperformed segmentation models such as U-Net, Attention U-Net, and Rolling U-Net in terms of average Intersection over Union (IoU), Dice coefficient, recall, specificity, and precision. This demonstrates that the improved model effectively enhances the accuracy, integrity of detail, and classification robustness of lumbar spine CT image segmentation.}
}