STRIDE: Spatial-Temporal Representation for Interval-conditioned Disease Evolution in Longitudinal Glioblastoma MRI

2026-10-01

AI Summary

This study addresses the clinical challenge of distinguishing stable disease, pseudoprogression, and true progression in glioma MRI by proposing the STRIDE framework. This approach integrates lesion-prior spatial representations with temporal conditional latent transitions to predict disease evolution states. Its core innovations include the first interval-conditioned temporal modeling coupled with an observation-transition fusion mechanism to precisely capture longitudinal change characteristics, alongside the introduction of SoftGate, an adaptive window hierarchical Transformer, and multi-dataset transfer learning. Experimental results demonstrate that the proposed method achieves a macro ROC-AUC of 0.816 and an F1 score of 0.796 on the Burdenko dataset, significantly enhancing the reliability of glioma progression assessment.

Abstract

Glioblastoma (GBM), an aggressive primary brain tumor, is routinely monitored with longitudinal MRI after treatment. Distinguishing stable disease (SD), pseudoprogression (PsP), and true progression (TP) remains challenging because these states can show overlapping MRI appearances despite different temporal trajectories. Existing longitudinal methods still face challenges in modeling scan-specific spatial variability, variable follow-up intervals, and complementary information from the observed follow-up state and its longitudinal change. We propose STRIDE, a framework for spatial-temporal representation of interval-conditioned disease evolution that takes paired post-treatment MRI scans and their inter-scan interval as input and predicts SD, PsP, or TP. The lesion-prior-guided spatial representation combines SoftGate and an Adaptive-window Hierarchical Transformer (AWHT) to emphasize lesion-related regions while preserving surrounding context. The time-conditioned latent transition uses pair-level context and the actual inter-scan interval to estimate interval-dependent representation changes between visits. The observed--transition fusion integrates the transition-estimated follow-up representation with the directly observed follow-up representation to jointly characterize the follow-up state and its longitudinal change. BraTS2024 is used to develop and evaluate the lesion-prior generator, while longitudinal pretraining on LUMIERE supports transfer before downstream adaptation to Burdenko. On the Burdenko three-class task, STRIDE achieves a macro ROC--AUC of 0.816 and a macro F1-score of 0.796. These results support its potential for more reliable longitudinal post-treatment GBM state assessment.

Problem

• Glioblastoma
• Longitudinal MRI
• Disease progression
• Pseudoprogression
• Spatial-temporal modeling

Innovation

• Spatial-Temporal Representation
• Adaptive-window Hierarchical Transformer
• Interval-conditioned Transition
• Glioblastoma
• Longitudinal MRI