LM-PCVMNet for pediatric CVM analysis in cephalometric radiographs; state-of-the-art accuracy and PCVM+ with 1,800 images
LM-PCVMNet for pediatric CVM analysis in cephalometric radiographs; state-of-the-art accuracy and PCVM+ with 1,800 images LM-PCVMNet: Pediatric Cervical Vertebral Maturation Analysis with Deep Fusion of Landmarks and Metadata LM-PCVMNet: Pediatric Cervical Vertebral Maturation Analysis with Deep Fusion of Landmarks and Metadata Peng Wanga,b, Wanzhen Songb,d, Anli Wangc, Xueshuo Xied, Xiaohang Guanc,∗, Tao Lia,d,∗ aCollege of Cryptology and Cyber Science, Nankai University, Tianjin, 300350, China bCollege of Engineering, Yanbian University, Yanji, 133002, Jilin, China cTianjin Stomatological Hospital, Tianjin, 300350, China dHaihe Lab of ITAI, Tianjin, 300350, China Abstract Cervical vertebral maturation (CVM) assessment plays a pivotal role in orthodontic diagnosis and determining the optimal timing of treatment, especially for pediatric patients. In this paper, we propose LM-PCVMNet, a novel deep learning framework for automatic pediatric CVM staging. Specifically, our method integrates vertebral anatomical landmark information, heatmap-guided feature modulation, and metadata-informed similarity modeling into a unified learning framework. We introduce a heatmap-guided feature modulation module that enhances feature extraction by leveraging landmark-centered heatmaps to highlight morphologically relevant vertebral regions. A vertebral landmark-prompting block is designed to incorporate anatomical geometry into the representation learning process. Furthermore, we develop a learnable metadata supervised contrastive loss that adaptively modulates positive-pair similarity based on metadata similarity, enabling the model to learn more biologically consistent and discriminative features. To facilitate further research in pediatric orthodontic treatment, we additionally release PCVM+. It contains 1,800 lateral cephalometric radiographs from real-world patients aged 3–15 years, with expert-annotated CVM stages, 13 vertebral anatomical landmarks, and corresponding metadata. We perform comprehensive experiments on two datasets, and the results show that our method achieves state-of-the-art performance, effectively improving landmark localization and classification accuracy over existing models. Code and dataset will be available at https://github.com/ybupengwang/LM-PCVMNet. Keywords: Cervical vertebral maturation, Pediatric orthodontics, Landmark detection, Vision transformer, Deep fusion. ...