Saved in:
Bibliographic Details
Main Authors: Nelson, Max A., Keles, Elif, Tasci, Eminenur Sen, Yazol, Merve, Aktas, Halil Ertugrul, Hong, Ziliang, Bejar, Andrea Mia, Durak, Gorkem, Boyunaga, Oznur Leman, Bagci, Ulas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.17635
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912724331528192
author Nelson, Max A.
Keles, Elif
Tasci, Eminenur Sen
Yazol, Merve
Aktas, Halil Ertugrul
Hong, Ziliang
Bejar, Andrea Mia
Durak, Gorkem
Boyunaga, Oznur Leman
Bagci, Ulas
author_facet Nelson, Max A.
Keles, Elif
Tasci, Eminenur Sen
Yazol, Merve
Aktas, Halil Ertugrul
Hong, Ziliang
Bejar, Andrea Mia
Durak, Gorkem
Boyunaga, Oznur Leman
Bagci, Ulas
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2511_17635
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification
Nelson, Max A.
Keles, Elif
Tasci, Eminenur Sen
Yazol, Merve
Aktas, Halil Ertugrul
Hong, Ziliang
Bejar, Andrea Mia
Durak, Gorkem
Boyunaga, Oznur Leman
Bagci, Ulas
Computer Vision and Pattern Recognition
Machine Learning
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).
title Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2511.17635