A Mandibular Defect Dataset for Autonomous Reconstruction Planning in Oral and Maxillofacial Surgery

<b>The first</b> clinically derived Mandibular Defect Dataset, comprising <b>147</b> models of <b>various mandibular defects</b>. Each model is manually <b>annotated by experienced surgeons</b>, and all processing workflows strictly adhere to clinical standards. This dataset accurately represents the complexity of clinical defect boundaries and the diverse anatomical structures of individual patients, making it a valuable resource for <b>developing AI models</b> that exhibit improved generalizability and adaptability in <b>mandibular reconstruction</b>. Additionally, the dataset provides <b>HCL classification diagnoses</b> and relevant information for each defect model, thereby supporting more diverse clinical research in the future.首个源自临床的下颌骨缺损数据集（Mandibular Defect Dataset），共收录147例各类下颌骨缺损模型。每例模型均由资深外科医师完成手动标注，所有数据处理流程均严格遵循临床规范。该数据集精准呈现了临床缺损边界的复杂特征与不同患者个体的多样化解剖结构，可为开发在颌骨重建领域具备更优泛化能力与适配性的AI模型提供宝贵的研究资源。此外，该数据集为每例缺损模型提供了HCL分类诊断及相关配套信息，可为未来开展更多元化的临床研究提供有力支撑。