利用ViT與CNN架構從胸部X光影像診斷COVID-19嚴重程度

Diagnosing COVID-19 Severity from Chest X-Ray Images Using ViT and CNN Architectures

February 23, 2025

作者: Luis Lara, Lucia Eve Berger, Rajesh Raju, Shawn Whitfield

cs.AI

摘要

COVID-19疫情對醫療資源造成了巨大壓力，並引發了關於如何利用機器學習減輕醫生負擔、輔助診斷的討論。胸部X光片（CXRs）被用於COVID-19的診斷，但鮮有研究基於CXRs預測患者病情的嚴重程度。在本研究中，我們通過整合三個數據源創建了一個大型COVID嚴重程度數據集，並探討了基於ImageNet和CXR預訓練模型以及視覺Transformer（ViTs）在嚴重程度回歸和分類任務中的效果。在三分類嚴重程度預測問題上，預訓練的DenseNet161模型表現最佳，總體準確率達80%，在輕度、中度和重度病例上的準確率分別為77.3%、83.9%和70%。而ViT在回歸任務中表現最優，其預測的嚴重程度評分與放射科醫生的評分相比，平均絕對誤差為0.5676。本項目的源代碼已公開提供。

English

The COVID-19 pandemic strained healthcare resources and prompted discussion about how machine learning can alleviate physician burdens and contribute to diagnosis. Chest x-rays (CXRs) are used for diagnosis of COVID-19, but few studies predict the severity of a patient's condition from CXRs. In this study, we produce a large COVID severity dataset by merging three sources and investigate the efficacy of transfer learning using ImageNet- and CXR-pretrained models and vision transformers (ViTs) in both severity regression and classification tasks. A pretrained DenseNet161 model performed the best on the three class severity prediction problem, reaching 80% accuracy overall and 77.3%, 83.9%, and 70% on mild, moderate and severe cases, respectively. The ViT had the best regression results, with a mean absolute error of 0.5676 compared to radiologist-predicted severity scores. The project's source code is publicly available.