English

Implicit Neural Representations for Multimodal Longitudinal Image Imputation and Interpolation

Computer Vision and Pattern Recognition 2026-08-03 v1

Abstract

Longitudinal multiparametric MRI is central to follow-up imaging in oncology, yet real-world clinical data are characterised by missing sequences, heterogeneous acquisition protocols, and varying spatial resolutions across time points. We propose a patient-specific conditional implicit neural representation (INR) that models multimodal longitudinal MRI as a continuous function of world coordinates, time, and modality conditioning. The model is trained with stochastic modality dropout to handle incomplete data, and its continuous coordinate-space formulation enables both spatial and temporal interpolation without resampling to a fixed voxel grid. A self-consistency-based confidence estimator is derived from cross-modal reconstruction performance at inference time. We evaluate the framework on longitudinal MRI from paediatric brain tumour patients, demonstrating statistically significant improvements over linear interpolation for T1CE and FLAIR (p < 0.05), with mean MS-SSIM of 0.95 ±\pm 0.02 for T1CE. Predicted confidence correlates strongly with true reconstruction quality (Pearson r up to 0.996), suggesting reliable deployment potential in heterogeneous clinical settings.

Cite

@article{arxiv.2608.02324,
  title  = {Implicit Neural Representations for Multimodal Longitudinal Image Imputation and Interpolation},
  author = {Sina Wendrich and Lukas Förner and Zoe Reinke and Kartikay Tehlan and Ansgar Berlis and Michael Frühwald and Matthias Wagner and Thomas Wendler},
  journal= {arXiv preprint arXiv:2608.02324},
  year   = {2026}
}