Beyond Random Partitioning: Unsupervised Spatio-Temporal Stratification for Cohort Balancing in Longitudinal Medical Imaging

• URL: http://arxiv.org/abs/2608.00073v1
• Date: Wed, 29 Jul 2026 09:33:19 GMT
• Title: Beyond Random Partitioning: Unsupervised Spatio-Temporal Stratification for Cohort Balancing in Longitudinal Medical Imaging
• Abstract summary: We formalize an unsupervised-temporal cohort-balancing standard operating procedure (SOP) that combines elbow-cluster K-means clustering over a standardized, six-dimensional joint intensity-temporal feature space.<n>On a longitudinal, contrast-enhanced $T1$-izable brain MRI cohort, the protocol reduces the maximum cross-subset intensity bias from 34.1% under conventional random shuffling to under 2.1%.
• Score: 0.9530026127073782
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Rigorous dataset partitioning is a foundational, yet frequently overlooked, prerequisite for reliable deep learning in longitudinal medical imaging. Naively shuffling small clinical cohorts routinely introduces covariate shifts and temporal sampling imbalances across training, validation, and test subsets, exposing downstream models to out-of-distribution evaluation. We address this vulnerability with an auditable Tripartite Dataset Analytics Framework that systematically characterizes spatial grid integrity, multi-parametric intensity fingerprints, and longitudinal temporal trajectories, quantifying the heavy-tailed feature dispersion and irregular, episodic sampling intervals typical of real-world clinical cohorts. Building on this characterization, we formalize an unsupervised spatio-temporal cohort-balancing standard operating procedure (SOP) that combines elbow-optimized K-means clustering over a standardized, six-dimensional joint intensity-temporal feature space with intra-cluster proportionate stratified sampling. On a longitudinal, contrast-enhanced $T1$-weighted brain MRI cohort (N=149), the protocol reduces the maximum cross-subset intensity bias from 34.1% under conventional random shuffling to under 2.1%, while aligning longitudinal follow-up intervals closely around the population mean. Monte Carlo stress testing across ten random seeds and three split configurations confirms that this alignment remains tightly bounded, in clear contrast to the substantial variability of random partitioning. The resulting protocol offers a reproducible, generalizable procedure for cohort engineering in variable-length longitudinal clinical imaging workflows.

Related papers

• From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts [61.695980784491475]
  Test-time scaling produces cohorts of reasoning rollouts, yet there is no standard label-free account of how their internal computation reorganizes as inference unfolds.<n>We introduce routing effective rank deff, the entropy-effective dimensionality of a cross-rollout graph built from MoE expert-routing similarity.
  arXiv  Detail & Related papers  (2026-09-06T05:43:22Z)
• Implicit Neural Representations for Multimodal Longitudinal Image Imputation and Interpolation [0.43554874937871363]
  Longitudinal multiparametric MRI is central to follow-up imaging in oncology.<n>Real-world clinical data are characterised by missing sequences, heterogeneous acquisition protocols, and varying resolutions across time points.<n>We propose a patient-specific conditional implicit neural representation (INR) that models longitudinal MRI as a continuous function of world coordinates, time, and modality conditioning.
  arXiv  Detail & Related papers  (2026-08-03T14:47:10Z)
• I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals [14.944883272011445]
  Cross-subject EEG stress detection is challenging because discriminative stress-related patterns are both subject-dependent and frequency-specific.<n>We propose method, an Intra-Inter Riemannian Manifold Attention Network for EEG-based stress detection.<n>method consistently outperforms five state-of-the-art baselines, achieving up to 82.78% balanced accuracy while remaining efficient with only 1.60M parameters and 31.95M FLOPs.
  arXiv  Detail & Related papers  (2026-07-01T07:23:32Z)
• From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint [0.0]
  Adaptive biomechanical systems may show similar observable gait performance while differing in latent organization and longitudinal behavior.<n>This study examines whether an observed longitudinal transformation of gait organization can be approximated within a predictive latent-space framework.
  arXiv  Detail & Related papers  (2026-05-15T11:23:44Z)
• PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities [86.63247982275396]
  PRIME is a missing-aware multimodal self-supervised pretraining framework.<n>It learns robust and transferable representations from partially observed cohorts.<n>We evaluate PRIME on The Cancer Genome Atlas with label-free pretraining on 32 cancer types.
  arXiv  Detail & Related papers  (2026-04-05T21:14:27Z)
• Enhancing ALS Progression Tracking with Semi-Supervised ALSFRS-R Scores Estimated from Ambient Home Health Monitoring [3.210027230758067]
  Self-attention achieved the lowest prediction error for subscale-level models.<n>We identified distinct homogeneity-hegeneity profiles across functional domains.
  arXiv  Detail & Related papers  (2025-07-13T02:56:40Z)
• Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis [56.442307356162864]
  We study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework.<n>We introduce a discrete-time sampling algorithm in the general state space $[S]d$ that utilizes score estimators at predefined time points.<n>Our convergence analysis employs a Girsanov-based method and establishes key properties of the discrete score function.
  arXiv  Detail & Related papers  (2024-10-03T09:07:13Z)
• Risk and cross validation in ridge regression with correlated samples [72.59731158970894]
  We provide training examples for the in- and out-of-sample risks of ridge regression when the data points have arbitrary correlations.<n>We demonstrate that in this setting, the generalized cross validation estimator (GCV) fails to correctly predict the out-of-sample risk.<n>We further extend our analysis to the case where the test point has nontrivial correlations with the training set, a setting often encountered in time series forecasting.
  arXiv  Detail & Related papers  (2024-08-08T17:27:29Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations [84.42837346400151]
  Estimating counterfactual outcomes over time has the potential to unlock personalized healthcare. Existing causal inference approaches consider regular, discrete-time intervals between observations and treatment decisions. We propose a controllable simulation environment based on a model of tumor growth for a range of scenarios.
  arXiv  Detail & Related papers  (2022-06-16T17:15:15Z)
• Tolerance and Prediction Intervals for Non-normal Models [0.0]
  A prediction interval covers a future observation from a random process in repeated sampling. A tolerance interval covers a population percentile in repeated sampling and is often based on a pivotal quantity.
  arXiv  Detail & Related papers  (2020-11-23T17:48:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.