# Observation-Anchored Selective Assimilation for Longitudinal Tumor-State Proxy Forecasting in Post-Treatment Glioma

arXiv: https://arxiv.org/abs/2609.12435 · HTML: https://mlsanity.com/paper/2609.12435/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation](https://mlsanity.com/paper/2401.13560/) (2024)
- [Learn-Morph-Infer: a new way of solving the inverse problem for brain tumor modeling](https://mlsanity.com/paper/2111.04090/) (2021)
- [A Learnable Prior Improves Inverse Tumor Growth Modeling](https://mlsanity.com/paper/2403.04500/) (2024)
- [PREDICT-GBM: A multi-center platform to advance personalized glioblastoma radiotherapy planning](https://mlsanity.com/paper/2509.13360/) (2025)
- [TumorFlow: Physics-Guided Longitudinal MRI Synthesis of Glioblastoma Growth](https://mlsanity.com/paper/2603.04058/) (2026)

## Abstract (arXiv)

Post-treatment MRI in patients with glioma provides serial observations for updating patient-specific tumor-state proxy estimates, but variable appearances and trajectories complicate forecasting. We formulate forecasting as an observation-aware digital-twin update in which an intermediate observation anchors the patient-specific state. Among 203 patients and 594 follow-up time points, a predefined no-new-treatment criterion retained 120 of 236 candidate triplets, split into 81/24/15 training/validation/test triplets at the patient level. Each time point was represented by a continuous voxel-wise tumor-state proxy map in [0,1] derived from MRI lesion labels. A SegMamba-based single-step forecaster predicted update proposals from multimodal source-state tensors. Observation-Anchored Selective Assimilation (OASA) retained the observed intermediate proxy as the state anchor and selectively applied updates through a validation-selected tiered case-level rule and voxel-wise soft gate. We compared initial-scan forecasting, rollout without assimilation, latest-observation persistence, direct prediction, OASA, OASA + calibration, and morphological dilation. Checkpoints, OASA rules, and calibration thresholds were selected using validation data only. Across three seeds on 15 held-out test triplets, OASA maintained Dice at τ = 0.2 comparable to persistence (0.6071 ± 0.0025 vs. 0.6070) while yielding numerically higher Dice at τ = 0.5 (0.4269 ± 0.0079 vs. 0.3981), with a small RMSE increase. Calibration increased Dice at τ = 0.2 to 0.6178 ± 0.0025, increased false-positive (FP) support (11,836rightarrow18,663), and reduced false-negative (FN) support (22,107rightarrow17,536). This reflects near-threshold support calibration rather than improved biological predictive capability. Code is publicly available at https://github.com/jsudg436/longitudinal-proxy-forecasting.