Abstract
We present COVID-CT-Mask-Net model that predicts COVID-19 in chest CT scans. The model works in two stages: in the first stage, Mask R-CNN is trained to localize and detect two types of lesions in images. In the second stage, these detections are fused to classify the whole input image. To develop the solution for the three-class problem (COVID-19, Common Pneumonia and Control), we used the COVIDx-CT data split derived from the dataset of chest CT scans collected by China National Center for Bioinformation. We use 3000 images (about 5% of the train split of COVIDx-CT) to train the model. Without any complicated data normalization, balancing and regularization, and training only a small fraction of the model’s parameters, we achieve a 90.80% COVID-19 sensitivity, 91.62% Common Pneumonia sensitivity and 92.10% true negative rate (Control sensitivity), an overall accuracy of 91.66% and F1-score of 91.50% on the test data split with 21192 images, bringing the ratio of test to train data to 7.06. We also establish an important result that regional predictions (bounding boxes with confidence scores) detected by Mask R-CNN can be used to classify whole images. The full source code, models and pretrained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.
Highlights
Since the start of COVID-19 pandemic a large number of deep learning models predicting COVID-19 from chest CT scans and x-rays has been developed
This model is converted to COVID-CT-Mask-Net by augmenting it with a classification module S that uses ranked bounding box predictions to classify the whole input image (Fig. 4) and the weights are copied from Mask R-CNN to COVIDCT-Mask-Net
One of the strongest features of COVID-CT-MaskNet’s methodology is the ability to train on very small training split relative to the test split, without any balancing and augmentation tweaks due to the functionality of Mask R-CNN
Summary
Since the start of COVID-19 pandemic a large number of deep learning models predicting COVID-19 from chest CT scans and x-rays has been developed. One of the biggest challenges in this area is a three class problem: COVID-19 vs Common Pneumonia vs Control/Negative. Solutions for this problem include COVID Net-CT [1], that consists of a single feature extractor trained on COVIDx-CT dataset split, COVNet (augmented Res Net50) [2], ResNet18 [3] and LightCNN [4]. COVID-CT concatenates lung masks predicted by UNet with deep image features extracted using DenseNet169 and ResNet to predict the class, achieving an overall accuracy of 89% on the test data of about 350 images. JCS uses a similar approach, but with additional loss functions at deep layers (multiscale training), achieving an F1 score of 0.783 on the test data of about 120K images. Advanced methodology based on convnets and wavelets optimized using biogeography-based optimization was introduced in [11] to
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.