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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Osorio, Eliana M. Vasquez, Henderson, Edward
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913692499574784
author Osorio, Eliana M. Vasquez
Henderson, Edward
author_facet Osorio, Eliana M. Vasquez
Henderson, Edward
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11265
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Automatic Identification of Missing Tissues using a Geometric-Learning Correspondence Model
Osorio, Eliana M. Vasquez
Henderson, Edward
Computer Vision and Pattern Recognition
Medical Physics
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.
title Towards Automatic Identification of Missing Tissues using a Geometric-Learning Correspondence Model
topic Computer Vision and Pattern Recognition
Medical Physics
url https://arxiv.org/abs/2502.11265