# Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification

arXiv: https://arxiv.org/abs/2009.07652 · HTML: https://mlsanity.com/paper/2009.07652/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2020.

## Built on by (most cited first, 22 of 22)

- [Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images](https://mlsanity.com/paper/2101.07563/) (2021)
- [Memory-aware curriculum federated learning for breast cancer classification](https://mlsanity.com/paper/2107.02504/) (2021)
- [Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation](https://mlsanity.com/paper/2109.03478/) (2021)
- [Clinically Labeled Contrastive Learning for OCT Biomarker Classification](https://mlsanity.com/paper/2305.15154/) (2023)
- [Deep learning-based COVID-19 pneumonia classification using chest CT images: model generalizability](https://mlsanity.com/paper/2102.09616/) (2021)
- [Data Augmentation and CNN Classification For Automatic COVID-19 Diagnosis From CT-Scan Images On Small Dataset](https://mlsanity.com/paper/2108.07148/) (2021)
- [Weakly Supervised Contrastive Learning for Better Severity Scoring of Lung Ultrasound](https://mlsanity.com/paper/2201.07357/) (2022)
- [COVID-19 Detection from Respiratory Sounds with Hierarchical Spectrogram Transformers](https://mlsanity.com/paper/2207.09529/) (2022)
- [Classification of COVID-19 via Homology of CT-SCAN](https://mlsanity.com/paper/2102.10593/) (2021)
- [Explainability Guided Multi-Site COVID-19 CT Classification](https://mlsanity.com/paper/2103.13677/) (2021)
- [Mixing-AdaSIN: Constructing a De-biased Dataset using Adaptive Structural Instance Normalization and Texture Mixing](https://mlsanity.com/paper/2103.14255/) (2021)
- [Multi-scale alignment and Spatial ROI Module for COVID-19 Diagnosis](https://mlsanity.com/paper/2207.01345/) (2022)
- [Improving COVID-19 CT Classification of CNNs by Learning Parameter-Efficient Representation](https://mlsanity.com/paper/2208.04718/) (2022)
- [Diagnosis of COVID-19 disease using CT scan images and pre-trained models](https://mlsanity.com/paper/2208.07829/) (2022)
- [Supervised Dimensionality Reduction and Image Classification Utilizing Convolutional Autoencoders](https://mlsanity.com/paper/2208.12152/) (2022)
- [CoVid-19 Detection leveraging Vision Transformers and Explainable AI](https://mlsanity.com/paper/2307.16033/) (2023)
- [Unleashing Modified Deep Learning Models in Efficient COVID19 Detection](https://mlsanity.com/paper/2310.14081/) (2023)
- [Empowering Medical Imaging with Artificial Intelligence: A Review of Machine Learning Approaches for the Detection, and Segmentation of COVID-19 Using Radiographic and Tomographic Images](https://mlsanity.com/paper/2401.07020/) (2024)
- [Semantic-Aware Representation of Multi-Modal Data for Data Ingress: A Literature Review](https://mlsanity.com/paper/2407.12438/) (2024)
- [LEARNER: Contrastive Pretraining for Learning Fine-Grained Patient Progression from Coarse Inter-Patient Labels](https://mlsanity.com/paper/2411.01144/) (2024)
- [A Multi-Centric Anthropomorphic 3D CT Phantom-Based Benchmark Dataset for Harmonization](https://mlsanity.com/paper/2507.01539/) (2025)
- [Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis](https://mlsanity.com/paper/2605.18878/) (2026)

## Abstract (arXiv)

The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performances on both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.