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.
Figures & tables
Figure 1: Representative COVID-positive CT slices from three different data centers in the validation set, each showing ground-glass opacities and multi-focal involvement with differing scanner characteristics and acquisition protocols.
Source
Train COVID
Train non-COVID
Validation COVID
Validation non-COVID
0
175
165
43
45
1
175
165
43
45
2
39
165
0
45
3
175
165
42
45
Total
564
660
128
180
Table 1: Number of CT scans per source and split in the PHAROS multi-source COVID-19 dataset.
Backbone
F1
EffNet-B3
0.856
DenseNet-121
0.865
ConvNeXt-T
0.869
EffNetV2-S
0.877
DINOv2 ViT-B/14
0.910
Ensemble Model
0.928
Table 2: Best validation F1 scores by pre-trained model family.
Figure 2: Ensemble approach vs. baseline ResNet50 on a similar dataset.
Figure 3: Phase-by-phase F1 progression of different models
Figure 4: COVID-positive CT slices with subtle ground-glass opacities (GGO). These faint, poorly-contrasted regions are easily overlooked during rapid human screening but are consistently detected by the attention mechanism across multiple slices.
Figure 5: Non-COVID CT slices from Centre 1 that the model tends to misclassify as COVID-positive. Scanner-specific artifacts, contrast variations, and protocol differences create patterns that confuse the model but are easily recognized as non-pathological by trained radiologists.
Deep learning models for COVID-19 detection from chest CT scans generally perform well when the training and test data originate from the same institution, but they often struggle when scans are drawn from multiple centres with differing scanners, imaging protocols, and patient populations. One key reason is that existing methods treat COVID-19 classification as the sole training objective, without accounting for the data source of each scan. As a result, the learned representations tend to be biased toward centres that contribute more training data. To address this, we propose a multi-task learning approach in which the model is trained to predict both the COVID-19 diagnosis and the originating data centre. The two tasks share an EfficientNet-B7 backbone, which encourages the feature extractor to learn representations that hold across all four participating centres. Since the training data is not evenly distributed across sources, we apply a logit-adjusted cross-entropy loss [1] to the source classification head to prevent underrepresented centres from being overlooked. Our pre-processing follows the SSFL framework with KDS [2], selecting eight representative slices per scan. Our method achieves an F1 score of 0.9098 and an AUC-ROC of 0.9647 on a validation set of 308 scans. The code is publicly available at https://github.com/Purdue-M2/-multisource-covid-ct.
Asmita Yuki Pritha, Jason Xu, Daniel Ding +4
Capstone School Dhaka, Bangladesh · Carmel High School, Carmel, Indiana, USA · Clarkstown High School South, West Nyack, New York, USA +2
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
Tuan-Anh Yang, Bao V. Q. Bui, Chanh-Quang Vo-Van +1
VNUHCM University of Science, Vietnam National University, Vietnam · Ho Chi Minh University of Technology, Vietnam National University, Vietnam · The University of Alabama at Birmingham, United States
Robust detection of COVID-19 from chest CT remains challenging in multi-institutional settings due to substantial source shift, source imbalance, and hidden test-source identities. In this work, we propose a three-stage source-aware multi-expert framework for multi-source COVID-19 CT classification. First, we build a lung-aware 3D expert by combining original CT volumes and lung-extracted CT volumes for volumetric classification. Second, we develop two MedSigLIP-based experts: a slice-wise representation and probability learning module, and a Transformer-based inter-slice context modeling module for capturing cross-slice dependency. Third, we train a source classifier to predict the latent source identity of each test scan. By leveraging the predicted source information, we perform model fusion and voting based on different experts. On the validation set covering all four sources, the Stage 1 model achieves the best macro-F1 of 0.9711, ACC of 0.9712, and AUC of 0.9791. Stage2a and Stage2b achieve the best AUC scores of 0.9864 and 0.9854, respectively. Stage~3 source classifier reaches 0.9107 ACC and 0.9114 F1. These results demonstrate that source-aware expert modeling and hierarchical voting provide an effective solution for robust COVID-19 CT classification under heterogeneous multi-source conditions.
Jianfa Bai, Kejin Lu, Runtian Yuan +5
College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University · University of Oxford · The Hong Kong University of Science and Technology