COVID-CT-Mask-Net: prediction of COVID-19 from CT scans using regional features.

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 9 0 . 8 0 % COVID-19 sensitivity, 9 1 . 6 2 % Common Pneumonia sensitivity and 9 2 . 1 0 % true negative rate (Control sensitivity), an overall accuracy of 9 1 . 6 6 % and F1-score of 9 1 . 5 0 % 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.

One Shot Model For The Prediction of COVID-19 And Lesions Segmentation In Chest CT Scans Through The Affinity Among Lesion Mask Features.

We present a novel framework that integrates segmentation of lesion masks and prediction of COVID-19 in chest CT scans in one shot. In order to classify the whole input image, we introduce a type of associations among lesion mask features extracted from the scan slice that we refer to as affinities. First, we map mask features to the affinity space by training an affinity matrix. Next, we map them back into the feature space through a trainable affinity vector. Finally, this feature representation is used for the classification of the whole input scan slice. We achieve a 93.55% COVID-19 sensitivity, 96.93% common pneumonia sensitivity, 99.37% true negative rate and 97.37% F1-score on the test split of CNCB-NCOV dataset with 21192 chest CT scan slices. We also achieve a 0.4240 mean average precision on the lesion segmentation task. All source code, models and results are publicly available on https://github.com/AlexTS1980/COVID-Affinity-Model.

Classification and Visualisation of Normal and Abnormal Radiographs; A Comparison between Eleven Convolutional Neural Network Architectures.

This paper investigates the classification of radiographic images with eleven convolutional neural network (CNN) architectures (GoogleNet, VGG-19, AlexNet, SqueezeNet, ResNet-18, Inception-v3, ResNet-50, VGG-16, ResNet-101, DenseNet-201 and Inception-ResNet-v2). The CNNs were used to classify a series of wrist radiographs from the Stanford Musculoskeletal Radiographs (MURA) dataset into two classes-normal and abnormal. The architectures were compared for different hyper-parameters against accuracy and Cohen's kappa coefficient. The best two results were then explored with data augmentation. Without the use of augmentation, the best results were provided by Inception-ResNet-v2 (Mean accuracy = 0.723, Mean kappa = 0.506). These were significantly improved with augmentation to Inception-ResNet-v2 (Mean accuracy = 0.857, Mean kappa = 0.703). Finally, Class Activation Mapping was applied to interpret activation of the network against the location of an anomaly in the radiographs.