Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans


  • Xin He Hong Kong Baptist University
  • Shihao Wang Hong Kong Baptist University
  • Xiaowen Chu Hong Kong Baptist University
  • Shaohuai Shi Hong Kong University of Science and Technology
  • Jiangping Tang Hangzhou Dianzi University
  • Xin Liu Hangzhou Dianzi University
  • Chenggang Yan Hangzhou Dianzi University
  • Jiyong Zhang Hangzhou Dianzi University
  • Guiguang Ding Tsinghua University



AI Responses to the COVID-19 Pandemic (Covid19), Classification and Regression, Transfer/Adaptation/Multi-task/Meta/Automated Learning


The COVID-19 pandemic has spread globally for several months. Because its transmissibility and high pathogenicity seriously threaten people's lives, it is crucial to accurately and quickly detect COVID-19 infection. Many recent studies have shown that deep learning (DL) based solutions can help detect COVID-19 based on chest CT scans. However, most existing work focuses on 2D datasets, which may result in low quality models as the real CT scans are 3D images. Besides, the reported results span a broad spectrum on different datasets with a relatively unfair comparison. In this paper, we first use three state-of-the-art 3D models (ResNet3D101, DenseNet3D121, and MC3\_18) to establish the baseline performance on three publicly available chest CT scan datasets. Then we propose a differentiable neural architecture search (DNAS) framework to automatically search the 3D DL models for 3D chest CT scans classification and use the Gumbel Softmax technique to improve the search efficiency. We further exploit the Class Activation Mapping (CAM) technique on our models to provide the interpretability of the results. The experimental results show that our searched models (CovidNet3D) outperform the baseline human-designed models on three datasets with tens of times smaller model size and higher accuracy. Furthermore, the results also verify that CAM can be well applied in CovidNet3D for COVID-19 datasets to provide interpretability for medical diagnosis. Code:




How to Cite

He, X., Wang, S., Chu, X., Shi, S., Tang, J., Liu, X., Yan, C., Zhang, J., & Ding, G. (2021). Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans. Proceedings of the AAAI Conference on Artificial Intelligence, 35(6), 4821-4829.



AAAI Technical Track Focus Area on AI Responses to the COVID-19 Pandemic