Towards Automatic Identification of Missing Tissues using a Geometric-Learning Correspondence Model
This addresses a specific challenge in medical imaging for dose mapping in radiotherapy, though it is incremental as it applies an existing model to a new task.
The paper tackled the problem of identifying missing tissue on intra-patient structure meshes for dose mapping in reirradiation by proposing a pipeline using a geometric-learning correspondence model, achieving a balanced accuracy of 0.883 with a threshold of 5.5 mm on simulated mandible resections but failing in more extreme cases.
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.