Towards Automatic Identification of Missing Tissues using a Geometric-Learning Correspondence Model

• DOI: 10.48550/arxiv.2502.11265
• Publication Date: 2025-01-01
• Authors: Osorio, Eliana M....; Henderson, Edward
• Keywords: FOS: Computer and information sciences; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; FOS: Physical sciences; Medical Physics (physics.med-ph); Physics - Medical Physics

Presented in XXth International Conference on the use of Computers in Radiation therapy. Pages 759-762 in XXth ICCR Proceedings, found in https://udl.hal.science/hal-04720234v1<br/>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.<br/>