Halfway to 3D: Ensembling 2.5D and 3D Models for Robust COVID-19 CT Diagnosis

TL;DR

This paper introduces a deep learning framework combining 2.5D and 3D models to improve COVID-19 detection and classification from chest CT scans, achieving state-of-the-art results on a benchmark dataset.

Contribution

It presents a novel ensemble approach integrating multi-view 2.5D and volumetric 3D models with advanced training strategies for robust COVID-19 diagnosis.

Findings

Ensemble achieves 94.48% accuracy in binary COVID detection.

2.5D DINOv3 model attains 79.35% accuracy in multi-class classification.

Combining slice-based and volumetric models improves robustness across sources.

Abstract

We propose a deep learning framework for COVID-19 detection and disease classification from chest CT scans that integrates both 2.5D and 3D representations to capture complementary slice-level and volumetric information. The 2.5D branch processes multi-view CT slices (axial, coronal, sagittal) using a DINOv3 vision transformer to extract robust visual features, while the 3D branch employs a ResNet-18 architecture to model volumetric context and is pretrained with Variance Risk Extrapolation (VREx) followed by supervised contrastive learning to improve cross-source robustness. Predictions from both branches are combined through logit-level ensemble inference. Experiments on the PHAROS-AIF-MIH benchmark demonstrate the effectiveness of the proposed approach: for binary COVID-19 detection, the ensemble achieves 94.48% accuracy and a 0.9426 Macro F1-score, outperforming both individual models, while for multi-class disease classification the 2.5D DINOv3 model achieves the best performance with 79.35% accuracy and a 0.7497 Macro F1-score. These results highlight the benefit of combining pretrained slice-based representations with volumetric modeling for robust multi-source medical imaging analysis. Code is available at https://github.com/HySonLab/PHAROS-AIF-MIH