Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification

TL;DR

This paper presents UPMI, a novel probabilistic meta-imputation method that enhances pediatric pancreatitis classification by augmenting multimodal MRI data in a low-dimensional feature space, improving diagnostic accuracy.

Contribution

The paper introduces UPMI, a lightweight augmentation strategy operating in meta-feature space, which improves classification performance on limited multimodal pediatric MRI data.

Findings

UPMI achieves a mean AUC of 0.908, outperforming real-only baseline.

Synthetic meta-features improve classifier robustness.

Method demonstrates effectiveness on pediatric pancreatitis data.

Abstract

Pediatric pancreatitis is a progressive and debilitating inflammatory condition, including acute pancreatitis and chronic pancreatitis, that presents significant clinical diagnostic challenges. Machine learning-based methods also face diagnostic challenges due to limited sample availability and multimodal imaging complexity. To address these challenges, this paper introduces Upstream Probabilistic Meta-Imputation (UPMI), a light-weight augmentation strategy that operates upstream of a meta-learner in a low-dimensional meta-feature space rather than in image space. Modality-specific logistic regressions (T1W and T2W MRI radiomics) produce probability outputs that are transformed into a 7-dimensional meta-feature vector. Class-conditional Gaussian mixture models (GMMs) are then fit within each cross-validation fold to sample synthetic meta-features that, combined with real meta-features, train a Random Forest (RF) meta-classifier. On 67 pediatric subjects with paired T1W/T2W MRIs, UPMI achieves a mean AUC of 0.908 $\pm$ 0.072, a $\sim$5% relative gain over a real-only baseline (AUC 0.864 $\pm$ 0.061).