Ground-glass opacity is a hallmark of numerous lung diseases, including patients with COVID19 and pneumonia, pulmonary fibrosis, and tuberculosis. This brief note presents experimental results of a proof-of-concept framework that got implemented and tested over three days as driven by the third challenge entitled "COVID-19 Competition", hosted at the AI-Enabled Medical Image Analysis Workshop of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023). Using a newly built virtual environment (created on March 17, 2023), we investigated various pre-trained two-dimensional convolutional neural networks (CNN) such as Dense Neural Network, Residual Neural Networks (ResNet), and Vision Transformers, as well as the extent of fine-tuning. Based on empirical experiments, we opted to fine-tune them using ADAM's optimization algorithm with a standard learning rate of 0.001 for all CNN architectures and apply early-stopping whenever the validation loss reached a plateau. For each trained CNN, the model state with the best validation accuracy achieved during training was stored and later reloaded for new classifications of unseen samples drawn from the validation set provided by the challenge organizers. According to the organizers, few of these 2D CNNs yielded performance comparable to an architecture that combined ResNet and Recurrent Neural Network (Gated Recurrent Units). As part of the challenge requirement, the source code produced during the course of this exercise is posted at https://github.com/lisatwyw/cov19. We also hope that other researchers may find this light prototype consisting of few Python files based on PyTorch 1.13.1 and TorchVision 0.14.1 approachable.

翻译：磨玻璃影是多种肺部疾病的标志性特征，包括新冠肺炎、肺炎、肺纤维化及肺结核患者。本简报展示了一个概念验证框架的实验结果，该框架依据第三届"COVID-19挑战赛"的要求，在三天内完成实施与测试。该挑战赛于2023年IEEE国际声学、语音与信号处理会议（ICASSP 2023）的"人工智能医学影像分析研讨会"中举办。我们利用新建的虚拟环境（创建于2023年3月17日），研究了多种预训练的二维卷积神经网络，包括稠密神经网络、残差网络和Vision Transformer，并探索了不同程度的微调策略。基于实证实验，我们选择采用ADAM优化算法对所有CNN架构进行微调，标准学习率设为0.001，并在验证损失达到平台期时应用早停法。对于每个训练后的CNN，我们保存训练过程中验证准确率最优的模型状态，随后重新加载该状态，对挑战赛组织者提供的验证集中未标注样本进行新分类。据组织者反馈，部分二维CNN模型的性能可媲美结合ResNet与循环神经网络（门控循环单元）的混合架构。根据挑战赛要求，本工作生成的源代码已发布于https://github.com/lisatwyw/cov19。此外，我们期望这一由少量基于PyTorch 1.13.1和TorchVision 0.14.1的Python文件构成的轻量原型能为其他研究者提供借鉴。