Journal of applied clinical medical physics · 2026
SpineMAE: A bone-window self-supervised and structure-aware framework for 3D cervical vertebra segmentation and fracture classification.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Liang Qing, Zhao Jingding, Yang Fang, Shi Lin, Song Yang, Chen Xianjun, Shi Zewen, Pang Qingjiang
Аннотация
INTRODUCTION: Accurate segmentation and classification of cervical spine fractures are essential for timely diagnosis and clinical decision-making in trauma care. Existing deep learning approaches often require extensive manual annotations and struggle to maintain anatomical consistency across vertebral levels, limiting their reliability and generalization.
METHODS: We propose a unified three-stage framework that integrates self-supervised representation learning, structure-aware segmentation, and vertebra-level classification. A bone-window 3D masked autoencoder first pretrains the encoder to learn bone-sensitive volumetric features from unlabeled CT scans. The pretrained encoder is then transferred to a structure-aware 3D U-Net that incorporates bone-likelihood and edge priors with geometry-consistency regularization for anatomically coherent vertebral segmentation. Finally, a vertebra-level classification head performs fracture prediction using ROI features with positional embeddings to encode anatomical context.
RESULTS: Evaluated on the RSNA Cervical Spine Fracture Detection dataset, the proposed method achieved a Dice score of 89.23% for cervical vertebra segmentation. For vertebra-level fracture classification, it achieved an AUC of 0.969 with sensitivity of 0.788 and specificity of 0.962 (macro-averaged across C1-C7), outperforming CNN- and transformer-based baselines.
CONCLUSIONS: The proposed framework provides a robust, interpretable, and data-efficient solution for automated cervical spine fracture detection and localization. By combining self-supervised 3D pretraining with anatomy-aware modeling, it offers a practical pathway toward clinically reliable AI-assisted diagnosis in spinal imaging.
METHODS: We propose a unified three-stage framework that integrates self-supervised representation learning, structure-aware segmentation, and vertebra-level classification. A bone-window 3D masked autoencoder first pretrains the encoder to learn bone-sensitive volumetric features from unlabeled CT scans. The pretrained encoder is then transferred to a structure-aware 3D U-Net that incorporates bone-likelihood and edge priors with geometry-consistency regularization for anatomically coherent vertebral segmentation. Finally, a vertebra-level classification head performs fracture prediction using ROI features with positional embeddings to encode anatomical context.
RESULTS: Evaluated on the RSNA Cervical Spine Fracture Detection dataset, the proposed method achieved a Dice score of 89.23% for cervical vertebra segmentation. For vertebra-level fracture classification, it achieved an AUC of 0.969 with sensitivity of 0.788 and specificity of 0.962 (macro-averaged across C1-C7), outperforming CNN- and transformer-based baselines.
CONCLUSIONS: The proposed framework provides a robust, interpretable, and data-efficient solution for automated cervical spine fracture detection and localization. By combining self-supervised 3D pretraining with anatomy-aware modeling, it offers a practical pathway toward clinically reliable AI-assisted diagnosis in spinal imaging.