用概率生成方法增强儿科胰腺炎分类数据，提升诊断准确率。
Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification
- 在低维特征空间生成合成数据，替代图像层面的复杂增强
- 在67名患儿数据上实现0.908的平均AUC，比真实数据提升5%
- 适合处理小样本、多模态医学影像分类问题的研究者
儿科胰腺炎是一种进行性且严重的炎症性疾病，包括急性与慢性胰腺炎，临床诊断面临巨大挑战。由于样本量有限及多模态影像复杂，基于机器学习的方法也难以有效应用。为此，本文提出上游概率元插补（UPMI），一种轻量级数据增强策略，该策略在低维元特征空间中而非图像空间内操作。利用特定模态的逻辑回归（T1W和T2W MRI放射组学）输出概率，生成7维元特征向量；在每个交叉验证折中，对每类条件拟合高斯混合模型（GMM），采样合成元特征，与真实元特征结合训练随机森林（RF）元分类器。在67名患儿的配对T1W/T2W MRI数据上，UPMI实现平均AUC 0.908 ± 0.072，相比仅使用真实数据的基线（AUC 0.864 ± 0.061）有约5%相对提升。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。