Unbalanced optimal transport for robust longitudinal lesion evolution with registration-aware and appearance-guided priors

2026-02-10

AI Summary

This work addresses the challenge of lesion matching in longitudinal CT scans, where lesion appearance, disappearance, merging, or splitting renders conventional geometry-based proximity methods ineffective. To overcome this, the authors propose a registration-aware unbalanced optimal transport (UOT) framework that constructs a composite cost function by integrating size-normalized geometric distance, local registration reliability derived from the Jacobian determinant of the deformation field, and an optional appearance consistency prior. A relative pruning strategy is introduced to generate a sparse transport plan that explicitly models diverse lesion evolution events. The method requires neither retraining nor heuristic rules and demonstrates significant improvements over distance-based baselines on real longitudinal CT data, achieving higher performance in boundary detection precision and recall, lesion state recall, and lesion graph component F1 score.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Computer Vision: Motion & Tracking

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• longitudinal lesion evolution
• lesion correspondence
• unbalanced optimal transport
• CT scans
• treatment response assessment

Innovation

• unbalanced optimal transport
• longitudinal lesion tracking
• registration-aware matching
• appearance-guided priors
• lesion evolution modeling