用几何学习模型自动识别头颈癌放疗中缺失的下颌骨组织。
Towards Automatic Identification of Missing Tissues using a Geometric-Learning Correspondence Model
- 基于正反向对应误差检测缺失点，利用cICE量化不一致性。
- 阈值5.5毫米在35例模拟切除中达到0.883准确率。
- 适用于约25%切除病例，对更严重缺失效果有限。
缺失组织给剂量映射带来重大挑战，尤其在再放疗场景中。本文提出一种基于已训练几何学习对应模型的流程，通过分析输入结构网格的正向与反向对应预测差异，使用基于对应关系的逆一致性误差（cICE）进行量化。在35例模拟下颌骨切除的数据集中，优化得到5.5毫米的阈值，结合集成方法在训练数据上实现0.883的平衡准确率。该流程在真实病例中成功识别出约25%下颌骨缺失的情况，但在更极端的约50%缺失案例中失败。这是首次将几何学习建模应用于解剖对应中缺失点的自动识别。
原文摘要 · Abstract (English)
Missing tissue presents a big challenge for dose mapping, e.g., in the reirradiation setting. We propose a pipeline to identify missing tissue on intra-patient structure meshes using a previously trained geometric-learning correspondence model. For our application, we relied on the prediction discrepancies between forward and backward correspondences of the input meshes, quantified using a correspondence-based Inverse Consistency Error (cICE). We optimised the threshold applied to cICE to identify missing points in a dataset of 35 simulated mandible resections. Our identified threshold, 5.5 mm, produced a balanced accuracy score of 0.883 in the training data, using an ensemble approach. This pipeline produced plausible results for a real case where ~25% of the mandible was removed after a surgical intervention. The pipeline, however, failed on a more extreme case where ~50% of the mandible was removed. This is the first time geometric-learning modelling is proposed to identify missing points in corresponding anatomy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。