Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qahqaie, Melika, Neumann, Dominik, Heimann, Tobias, Maier, Andreas, Zimmer, Veronika A.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.09933
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912894582521856
author Qahqaie, Melika
Neumann, Dominik
Heimann, Tobias
Maier, Andreas
Zimmer, Veronika A.
author_facet Qahqaie, Melika
Neumann, Dominik
Heimann, Tobias
Maier, Andreas
Zimmer, Veronika A.
contents Evaluating lesion evolution in longitudinal CT scans of can cer patients is essential for assessing treatment response, yet establishing reliable lesion correspondence across time remains challenging. Standard bipartite matchers, which rely on geometric proximity, struggle when lesions appear, disappear, merge, or split. We propose a registration-aware matcher based on unbalanced optimal transport (UOT) that accommodates unequal lesion mass and adapts priors to patient-level tumor-load changes. Our transport cost blends (i) size-normalized geometry, (ii) local registration trust from the deformation-field Jacobian, and (iii) optional patch-level appearance consistency. The resulting transport plan is sparsified by relative pruning, yielding one-to-one matches as well as new, disappearing, merging, and splitting lesions without retraining or heuristic rules. On longitudinal CT data, our approach achieves consistently higher edge-detection precision and recall, improved lesion-state recall, and superior lesion-graph component F1 scores versus distance-only baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2602_09933
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unbalanced optimal transport for robust longitudinal lesion evolution with registration-aware and appearance-guided priors
Qahqaie, Melika
Neumann, Dominik
Heimann, Tobias
Maier, Andreas
Zimmer, Veronika A.
Computer Vision and Pattern Recognition
Artificial Intelligence
Evaluating lesion evolution in longitudinal CT scans of can cer patients is essential for assessing treatment response, yet establishing reliable lesion correspondence across time remains challenging. Standard bipartite matchers, which rely on geometric proximity, struggle when lesions appear, disappear, merge, or split. We propose a registration-aware matcher based on unbalanced optimal transport (UOT) that accommodates unequal lesion mass and adapts priors to patient-level tumor-load changes. Our transport cost blends (i) size-normalized geometry, (ii) local registration trust from the deformation-field Jacobian, and (iii) optional patch-level appearance consistency. The resulting transport plan is sparsified by relative pruning, yielding one-to-one matches as well as new, disappearing, merging, and splitting lesions without retraining or heuristic rules. On longitudinal CT data, our approach achieves consistently higher edge-detection precision and recall, improved lesion-state recall, and superior lesion-graph component F1 scores versus distance-only baselines.
title Unbalanced optimal transport for robust longitudinal lesion evolution with registration-aware and appearance-guided priors
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2602.09933