[论文解读] A Heterogeneous Ensemble for Multi-Center COVID-19 Classification from Chest CT Scans

Aadit Nilay, Bhavesh Thapar+2 more|arXiv (Cornell University)|Mar 15, 2026

COVID-19 diagnosis using AI被引用 0

一句话总结

本论文提出一个由九个模型组成的异质集成，横跨三种推理范式，能够在多中心的胸部CT扫描中对COVID-19进行分类，在四个医院中心实现宏F1为0.9280，并比最佳单模型高出0.031。

ABSTRACT

The COVID-19 pandemic exposed critical limitations in diagnostic workflows: RT-PCR tests suffer from slow turnaround times and high false-negative rates, while CT-based screening offers faster complementary diagnosis but requires expert radiological interpretation. Deploying automated CT analysis across multiple hospital centres introduces further challenges, as differences in scanner hardware, acquisition protocols, and patient populations cause substantial domain shift that degrades single-model performance. To address these challenges, we present a heterogeneous ensemble of nine models spanning three inference paradigms: (1) a self-supervised DINOv2 Vision Transformer with slice-level sigmoid aggregation, (2) a RadImageNet-pretrained DenseNet-121 with slice-level sigmoid averaging, and (3) seven Gated Attention Multiple Instance Learning models using EfficientNet-B3, ConvNeXt-Tiny, and EfficientNetV2-S backbones with scan-level softmax classification. Ensemble diversity is further enhanced through random-seed variation and Stochastic Weight Averaging. We address severe overfitting, reducing the validation-to-training loss ratio from 35x to less than 3x, through a combination of Focal Loss, embedding-level Mixup, and domain-aware augmentation. Model outputs are fused via score-weighted probability averaging and calibrated with per-source threshold optimization. The final ensemble achieves an average macro F1 of 0.9280 across four hospital centres, outperforming the best single model (F1=0.8969) by +0.031, demonstrating that heterogeneous architectures combined with source-aware calibration are essential for robust multi-site medical image classification.

研究动机与目标

• 解决因扫描仪、协议和患者人群差异导致的跨多医院中心的领域偏移。
• 开发鲁棒的异质集成以提升胸部CT中的COVID-19分类。
• 通过先进的训练和增强策略降低过拟合、提高泛化能力。
• 使用按源头阈值对模型输出进行校准，以提升多站点性能。

提出的方法

• 使用三种推理范式：(1) 自监督DINOv2 Vision Transformer，采用切片级sigmoid聚合；(2) 使用RadImageNet预训练的DenseNet-121，采用切片级sigmoid求平均；(3) 七种门控注意力MIL模型，骨干网络为EfficientNet-B3、ConvNeXt-Tiny和EfficientNetV2-S，进行扫描级softmax分类。
• 通过随机种子变异和随机权重均化提升集成多样性。
• 用Focal损失、嵌入级Mixup和领域感知增强来抑制过拟合。
• 用分数加权概率平均融合模型输出，并使用按源阈值优化进行校准。

实验结果

研究问题

• RQ1 异质集成是否能够在域移位下改善多中心COVID-19 CT分类？
• RQ2 在多站点评估中，使用按源头的阈值校准是否优于统一校准？
• RQ3 多样化的架构与训练策略如何提升对中心特异性变异的鲁棒性？

主要发现

• 该集成在四个医院中心的平均宏F1为0.9280。
• 该集成的表现优于最佳单一模型（F1 = 0.8969），提升0.031。
• 通过减少过拟合，验证集/训练集损失比从35倍降至小于3倍。
• 来自多种架构与训练范式的多样性，加上校准，是实现鲁棒的多站点性能的关键。