[论文解读] Multi-Channel Transfer Learning of Chest X-ray Images for Screening of COVID-19

Sampa Misra, Seungwan Jeon+3 more|arXiv (Cornell University)|May 12, 2020

COVID-19 diagnosis using AI参考文献 22被引用 11

一句话总结

本文提出了一种基于ResNet模型的多通道迁移学习框架，以提升通过胸部X光片进行COVID-19筛查的性能。通过在三个不同数据集（正常/患病、肺炎/非肺炎、COVID-19/非COVID-19）上分别训练并集成三个专用模型，随后在合并数据集上进行微调，该方法在多分类数据集上实现了94%的精确率和100%的召回率，优于单一模型基线。

ABSTRACT

The 2019 novel coronavirus (COVID-19) has spread rapidly all over the world and it is affecting the whole society. The current gold standard test for screening COVID-19 patients is the polymerase chain reaction test. However, the COVID-19 test kits are not widely available and time-consuming. Thus, as an alternative, chest X-rays are being considered for quick screening. Since the presentation of COVID-19 in chest X-rays is varied in features and specialization in reading COVID-19 chest X-rays are required thus limiting its use for diagnosis. To address this challenge of reading chest X-rays by radiologists quickly, we present a multi-channel transfer learning model based on ResNet architecture to facilitate the diagnosis of COVID-19 chest X-ray. Three ResNet-based models (Models a, b, and c) were retrained using Dataset_A (1579 normal and 4429 diseased), Dataset_B (4245 pneumonia and 1763 non-pneumonia), and Dataset_C (184 COVID-19 and 5824 Non-COVID19), respectively, to classify (a) normal or diseased, (b) pneumonia or non-pneumonia, and (c) COVID-19 or non-COVID19. Finally, these three models were ensembled and fine-tuned using Dataset_D (1579 normal, 4245 pneumonia, and 184 COVID-19) to classify normal, pneumonia, and COVID-19 cases. Our results show that the ensemble model is more accurate than the single ResNet model, which is also re-trained using Dataset_D as it extracts more relevant semantic features for each class. Our approach provides a precision of 94 % and a recall of 100%. Thus, our method could potentially help clinicians in screening patients for COVID-19, thus facilitating immediate triaging and treatment for better outcomes.

研究动机与目标

• 为应对PCR检测在COVID-19检测中可用性有限且周转时间慢的问题，通过胸部X光片实现实时、自动化的筛查。
• 克服放射科医生因缺乏专业性而难以准确解读X光片中变异且细微的COVID-19特征的困难。
• 开发一种深度学习模型，通过在多个专用任务之间迁移学习，以提升诊断性能。
• 通过集成学习和微调，提升对三种类别（正常、肺炎、COVID-19）的分类准确性。

提出的方法

• 在三个独立数据集上分别训练了三个基于ResNet的模型（a、b、c）：数据集_A（正常 vs. 患病）、数据集_B（肺炎 vs. 非肺炎）和数据集_C（COVID-19 vs. 非COVID-19）。
• 每个模型均在ImageNet上进行预训练，随后在各自的数据集上进行微调，以专门化于特定的诊断任务。
• 将三个专用模型进行集成，并在数据集_D上联合微调，该数据集结合了正常、肺炎和COVID-19病例，用于多类别分类。
• 集成模型利用各通道学习到的互补特征，提升了所有三类的泛化能力和特征表示能力。
• 通过使用ImageNet权重初始化模型，并将其适应于标注数据有限的医学影像任务，应用了迁移学习。

实验结果

研究问题

• RQ1 与单模型方法相比，多通道迁移学习是否能提升胸部X光片中COVID-19检测的准确性？
• RQ2 在不同诊断任务（如肺炎 vs. 非肺炎）上训练专用模型，是否能增强下游多类别分类的特征学习？
• RQ3 集成并微调多个专用模型是否能优于在合并数据集上重新训练单个模型？
• RQ4 迁移学习在缓解如COVID-19等罕见疾病医学影像中的数据稀缺问题方面，其作用程度如何？

主要发现

• 集成的多通道迁移学习模型在通过胸部X光片对正常、肺炎和COVID-19病例进行分类时，实现了94%的精确率和100%的召回率。
• 所提出的方法优于在合并数据集_D上重新训练的单个ResNet模型，证明了专用预训练和集成学习的优势。
• 该模型达到100%的召回率，表明其成功识别出所有实际的COVID-19病例，最大限度减少了假阴性。
• 使用多个专用通道使模型能够提取每种类别更相关且更具判别性的语义特征。