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.
翻译:我们展示了使用迭代的深深深学习模型组合,用胸部X光探测COVID-19的肺部表现,这种疾病是由新型严重急性呼吸综合症科罗纳病毒2 (SARS-COV-2)病毒(又称科罗纳病毒(2019-nCOV))造成的,又称科罗纳病毒(2019-nCOV),一种定制的进化神经网络和图像网预选的模型,在病人一级通过公开提供的CXR收藏进行训练和评价,以学习特定模式特征表现;所学知识的传授和微调,以改善CXR的正常性能和一般化,显示细菌肺炎或COVID-19病毒的正常性;最佳性能模型是迭接式的,以降低复杂性和提高记忆效率;最佳性能调整模型的预测,通过不同的元素组合战略来提高分类性能;最佳性能模型的加权平均值可以大大提高业绩,从而在CX-19R的常规性任务中,显示细菌肺部的精确度,在C-19997号双级预测中,在Sental-cal-legal Streal Streal Strealismalismal 中,在CV中采用这种改进了对CVI的预测,在CVI的模型和Breal-hal-hmal-hmal-hmludal-hismmmmalbalbal 中,在C-hismmmludhismmmmmmmmmmmmmmmmmmmmmmmmus中,在C-hmus中,在CV中利用了对CVI的预测中,在C-hismmmal 。