mlsanityData to 14 Oct 2026

Implicit Neural Representations for Multimodal Longitudinal Image Imputation and Interpolation

arXiv 2608.02324 ↗First posted 3 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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 ± 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 13 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

9 of 13 references.

References · 9

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 146
  4. 2019Automated brain extraction of multi-sequence MRI using artificial neural networkscited by 134
  5. 2020Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesiscited by 86
  6. 2019Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentationcited by 68
  7. 2022One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputationcited by 40
  8. 2022Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstructioncited by 36
  9. 2023CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Accelerating MRI with Longitudinally-informed Latent Posterior Sampling
  2. 2026How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?
  3. 2026Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion
  4. 2026Unified Multimodal Model for Brain MRI Imputation and Understanding
  5. 2024INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstruction
  6. 2026Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models
  7. 2026LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts
  8. 2026Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with glioma