Per-COVID-19: A Benchmark Dataset for COVID-19 Percentage Estimation from CT-Scans

Journal of Imaging

Fares Bougourzi¹  Cosimo Distante¹  Abdelkrim Ouafi²  Abdenour Hadid³  Abdelmalik Taleb-Ahmed³  Fadi Dornaika⁴ 

[1] Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy, 73100 Lecce, Italy;Laboratory of LESIA, University of Biskra, Biskra 7000, Algeria;University Polytechnique Hauts-de-France, University Lille, CNRS, Centrale Lille, UMR 8520-IEMN, F-59313 Valenciennes, France;University of the Basque Country UPV/EHU, 20018 San Sebastian, Spain;

关键词: COVID-19;    deep learning;    convolutional neural network;    CT-scans;    dataset generation;   

DOI  :  10.3390/jimaging7090189

来源: DOAJ

【 摘 要 】

COVID-19 infection recognition is a very important step in the fight against the COVID-19 pandemic. In fact, many methods have been used to recognize COVID-19 infection including Reverse Transcription Polymerase Chain Reaction (RT-PCR), X-ray scan, and Computed Tomography scan (CT- scan). In addition to the recognition of the COVID-19 infection, CT scans can provide more important information about the evolution of this disease and its severity. With the extensive number of COVID-19 infections, estimating the COVID-19 percentage can help the intensive care to free up the resuscitation beds for the critical cases and follow other protocol for less severity cases. In this paper, we introduce COVID-19 percentage estimation dataset from CT-scans, where the labeling process was accomplished by two expert radiologists. Moreover, we evaluate the performance of three Convolutional Neural Network (CNN) architectures: ResneXt-50, Densenet-161, and Inception-v3. For the three CNN architectures, we use two loss functions: MSE and Dynamic Huber. In addition, two pretrained scenarios are investigated (ImageNet pretrained models and pretrained models using X-ray data). The evaluated approaches achieved promising results on the estimation of COVID-19 infection. Inception-v3 using Dynamic Huber loss function and pretrained models using X-ray data achieved the best performance for slice-level results: 0.9365, 5.10, and 9.25 for Pearson Correlation coefficient (PC), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE), respectively. On the other hand, the same approach achieved 0.9603, 4.01, and 6.79 for $P{C}_{subj}$, $MA{E}_{subj}$, and $RMS{E}_{subj}$, respectively, for subject-level results. These results prove that using CNN architectures can provide accurate and fast solution to estimate the COVID-19 infection percentage for monitoring the evolution of the patient state.

【 授权许可】

Unknown