Timepoint-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI

TL;DR

This study benchmarks various deep learning models for differentiating tumor progression from pseudoprogression in glioblastoma follow-up MRI, revealing stage-dependent performance and highlighting the need for standardized protocols and larger datasets.

Contribution

First stage-specific benchmarking of deep learning models for glioblastoma follow-up MRI, analyzing architecture performance at different time points with a unified pipeline.

Findings

Discrimination improves at second follow-up stage.

Mamba+CNN hybrid offers best accuracy-efficiency trade-off.

Performance is sensitive to training batch size.

Abstract

Differentiating true tumor progression (TP) from treatment-related pseudoprogression (PsP) in glioblastoma remains challenging, especially at early follow-up. We present the first stage-specific, cross-sectional benchmarking of deep learning models for follow-up MRI using the Burdenko GBM Progression cohort (n = 180). We analyze different post-RT scans independently to test whether architecture performance depends on time-point. Eleven representative DL families (CNNs, LSTMs, hybrids, transformers, and selective state-space models) were trained under a unified, QC-driven pipeline with patient-level cross-validation. Across both stages, accuracies were comparable (~0.70-0.74), but discrimination improved at the second follow-up, with F1 and AUC increasing for several models, indicating richer separability later in the care pathway. A Mamba+CNN hybrid consistently offered the best accuracy-efficiency trade-off, while transformer variants delivered competitive AUCs at substantially higher computational cost and lightweight CNNs were efficient but less reliable. Performance also showed sensitivity to batch size, underscoring the need for standardized training protocols. Notably, absolute discrimination remained modest overall, reflecting the intrinsic difficulty of TP vs. PsP and the dataset's size imbalance. These results establish a stage-aware benchmark and motivate future work incorporating longitudinal modeling, multi-sequence MRI, and larger multi-center cohorts.