# Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-rays

arXiv: https://arxiv.org/abs/2004.08379 · HTML: https://mlsanity.com/paper/2004.08379/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2020.

## Built on by (most cited first, 21 of 21)

- [COVID-19 Infection Localization and Severity Grading from Chest X-ray Images](https://mlsanity.com/paper/2103.07985/) (2021)
- [Self-supervised deep convolutional neural network for chest X-ray classification](https://mlsanity.com/paper/2103.03055/) (2021)
- [TDA-Net: Fusion of Persistent Homology and Deep Learning Features for COVID-19 Detection in Chest X-Ray Images](https://mlsanity.com/paper/2101.08398/) (2021)
- [Multi-objective optimization determines when, which and how to fuse deep networks: an application to predict COVID-19 outcomes](https://mlsanity.com/paper/2204.03772/) (2022)
- [An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networks](https://mlsanity.com/paper/2201.11440/) (2022)
- [Diagnosis of COVID-19 Using Machine Learning and Deep Learning: A review](https://mlsanity.com/paper/2110.14910/) (2021)
- [BIO-CXRNET: A Robust Multimodal Stacking Machine Learning Technique for Mortality Risk Prediction of COVID-19 Patients using Chest X-Ray Images and Clinical Data](https://mlsanity.com/paper/2206.07595/) (2022)
- [COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing](https://mlsanity.com/paper/2102.06169/) (2021)
- [Deep Learning Models May Spuriously Classify Covid-19 from X-ray Images Based on Confounders](https://mlsanity.com/paper/2102.04300/) (2021)
- [CoRSAI: A System for Robust Interpretation of CT Scans of COVID-19 Patients Using Deep Learning](https://mlsanity.com/paper/2105.11863/) (2021)
- [A Survey of Machine Learning Techniques for Detecting and Diagnosing COVID-19 from Imaging](https://mlsanity.com/paper/2108.04344/) (2021)
- [Classification of COVID-19 from CXR Images in a 15-class Scenario: an Attempt to Avoid Bias in the System](https://mlsanity.com/paper/2109.12453/) (2021)
- [Multi-loss ensemble deep learning for chest X-ray classification](https://mlsanity.com/paper/2109.14433/) (2021)
- [Secure Federated Learning Approaches to Diagnosing COVID-19](https://mlsanity.com/paper/2401.12438/) (2024)
- [A Data Augmented Approach to Transfer Learning for Covid-19 Detection](https://mlsanity.com/paper/2108.02870/) (2021)
- [POTHER: Patch-Voted Deep Learning-Based Chest X-ray Bias Analysis for COVID-19 Detection](https://mlsanity.com/paper/2201.09360/) (2022)
- [Pick up the PACE: Fast and Simple Domain Adaptation via Ensemble Pseudo-Labeling](https://mlsanity.com/paper/2205.13508/) (2022)
- [Machine learning approaches for COVID-19 detection from chest X-ray imaging: A Systematic Review](https://mlsanity.com/paper/2206.05615/) (2022)
- [MEDNC: Multi-ensemble deep neural network for COVID-19 diagnosis](https://mlsanity.com/paper/2304.13135/) (2023)
- [Sculpting Efficiency: Pruning Medical Imaging Models for On-Device Inference](https://mlsanity.com/paper/2309.05090/) (2023)
- [A Comprehensive Analysis of COVID-19 Detection Using Bangladeshi Data and Explainable AI](https://mlsanity.com/paper/2506.07234/) (2025)

## Abstract (arXiv)

We demonstrate use of iteratively pruned deep learning model ensembles for detecting pulmonary manifestation of COVID-19 with chest X-rays. This disease is caused by the novel Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus, also known as the novel Coronavirus (2019-nCoV). A custom convolutional neural network and a selection of ImageNet pretrained models are trained and evaluated at patient-level on publicly available CXR collections to learn modality-specific feature representations. The learned knowledge is transferred and fine-tuned to improve performance and generalization in the related task of classifying CXRs as normal, showing bacterial pneumonia, or COVID-19-viral abnormalities. The best performing models are iteratively pruned to reduce complexity and improve memory efficiency. The predictions of the best-performing pruned models are combined through different ensemble strategies to improve classification performance. Empirical evaluations demonstrate that the weighted average of the best-performing pruned models significantly improves performance resulting in an accuracy of 99.01% and area under the curve of 0.9972 in detecting COVID-19 findings on CXRs. The combined use of modality-specific knowledge transfer, iterative model pruning, and ensemble learning resulted in improved predictions. We expect that this model can be quickly adopted for COVID-19 screening using chest radiographs.