COVID-19 detection in CT images with deep learning: A voting-based scheme and cross-datasets analysis

Abstract

Early detection and diagnosis are critical factors to control the COVID-19 spreading. A number of deep learning-based methodologies have been recently proposed for COVID-19 screening in CT scans as a tool to automate and help with the diagnosis. These approaches, however, suffer from at least one of the following problems: (i) they treat each CT scan slice independently and (ii) the methods are trained and tested with sets of images from the same dataset. Treating the slices independently means that the same patient may appear in the training and test sets at the same time which may produce misleading results. It also raises the question of whether the scans from the same patient should be evaluated as a group or not. Moreover, using a single dataset raises concerns about the generalization of the methods. Different datasets tend to present images of varying quality which may come from different types of CT machines reflecting the conditions of the countries and cities from where they come from. In order to address these two problems, in this work, we propose an Efficient Deep Learning Technique for the screening of COVID-19 with a voting-based approach. In this approach, the images from a given patient are classified as group in a voting system. The approach is tested in the two biggest datasets of COVID-19 CT analysis with a patient-based split. A cross dataset study is also presented to assess the robustness of the models in a more realistic scenario in which data comes from different distributions. The cross-dataset analysis has shown that the generalization power of deep learning models is far from acceptable for the task since accuracy drops from 87.68% to 56.16% on the best evaluation scenario. These results highlighted that the methods that aim at COVID-19 detection in CT-images have to improve significantly to be considered as a clinical option and larger and more diverse datasets are needed to evaluate the methods in a realistic scenario.

RETRACTED ARTICLE: GraphCovidNet: A graph neural network based model for detecting COVID-19 from CT scans and X-rays of chest

“…Overall, they have achieved best accuracy as 89.1%. Pedro et al 15 have utilized the EfficientNet 16 model along with transfer learning citetranferlearning and have achieved accuracies 87.60% and 98.99% for COVID-CT dataset 11 and SARS-CoV-2 CT-scan dataset 8 respectively. Sharma et al 17 have applied ResNet 14 on the database consisting of datasets: (i) GitHub COVID-CT dataset 11 , (ii) COVID dataset provided by Italian Society of Medical and Interventional Radiology 18 , (iii) dataset provided by hospitals of Moscow, Russia 19 , (iv) dataset provided by SAL Hospital, Ahmedabad, India 20 and have obtained almost 91% accuracy.…”

Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning

“…In the context of the COVID-19 pandemic, extensive research has been conducted to develop automated image-based COVID-19 detection and diagnostic systems [ 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ]. We hereafter review the proposed approaches for reliable detection systems based on chest X-ray and CT-scan imaging modalities.…”

COVIDC: An expert system to diagnose COVID-19 and predict its severity using chest CT scans: Application in radiology

“…We have searched existing techniques in the online literature using different keywords such as “Machine learning and COVID-19”, “COVID-19 diagnosis with CT scans”, and “COVID-19 diagnosis with CT scans and machine learning”. While going through the online existing literature (peer-reviewed) published in reputed journals, we found a plethora of machine learning techniques to diagnose COVID-19 using chest CT scans with varying sources and amount of training data [ [22] , [23] , [24] , [25] , [26] , [27] , [28] , [29] , [30] , [31] , [32] , [33] , [34] , [35] , [36] , [37] ]. All these previously published techniques can be categorized into three main classes as follows: Deep learning-based, transfer learning with fine-tuning a customized fully connected layer, shallow learning with handcrafted textured features.…”

“…Previously published studies employing deep learning-based machine learning techniques to detect COVID-19 mostly used Convolution Neural Network (CNN) [ 20 ] based architectures in their proposed design [ [23] , [24] , [25] , 29 , [31] , [32] , [33] , [34] , [35] , [36] , [37] ]. However, deep learning approaches to generalize well normally require an enormous amount of data which is not readily available right now [ 22 ].…”