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

Abstract

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 PCsubj, MAEsubj, and RMSEsubj, 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.

SEnsembleNet: A Squeeze and Excitation based Ensemble Network for COVID-19 Infection Percentage Estimation from CT-Scans

“…We did not test the performance of models on validation with constant learning rate as constant learning rate performed poor in 5 fold cross-validation. Our proposed approach reduced the error rate by 0.64 from baseline [6].…”

“…The dataset is comprised of three sets: train, validation and test set [6]. Train set consists of 132 CT-scans among 128 are labelled as COVID infected and 4 CT-scans are infection-free.…”

“…al. proposed a dataset and a baseline approach to overcome this limitation that resulted in a 5.10 mean absolute error [6].…”

EffViT-COVID: A dual-path network for COVID-19 percentage estimation

“…The data have CT scans of both male and female COVID-19 patients of different age groups ranging from 27–70 years. As reported in Bougourzi et al (2021) the COVID-19 CT scans were collected from two hospitals of Algeria from June to December 2020. Each CT-scan comprises around 40–70 slices, and there are 150 CT-scans taken with Hitachi ECLOS CT-Scanner having 5 mm slice thickness and 33 CT-scans of 3 mm slice thickness with Toshiba Alexion CT-Scanner collected from Hakim Saidane Biskra and Ziouch Mohamed Tolga hospital, respectively.…”

CNN based facial aesthetics analysis through dynamic robust losses and ensemble regression

“…Motivation Over the past decade, CNNs have become the dominant solution for most computer vision and machine learning tasks [9,10]. Despite these tremendous advances in deep learning methods, FBP has not been able to benefit much from deep learning.…”