Abstract
Problem: An application of Explainable Artificial Intelligence Methods for COVID CT-Scan classifiers is presented. Motivation: It is possible that classifiers are using spurious artifacts in dataset images to achieve high performances, and such explainable techniques can help identify this issue. Aim: For this purpose, several approaches were used in tandem, in order to create a complete overview of the classificatios. Methodology: The techniques used included GradCAM, LIME, RISE, Squaregrid, and direct Gradient approaches (Vanilla, Smooth, Integrated). Main results: Among the deep neural networks architectures evaluated for this image classification task, VGG16 was shown to be most affected by biases towards spurious artifacts, while DenseNet was notably more robust against them. Further impacts: Results further show that small differences in validation accuracies can cause drastic changes in explanation heatmaps for DenseNet architectures, indicating that small changes in validation accuracy may have large impacts on the biases learned by the networks. Notably, it is important to notice that the strong performance metrics achieved by all these networks (Accuracy, F1 score, AUC all in the 80 to 90% range) could give users the erroneous impression that there is no bias. However, the analysis of the explanation heatmaps highlights the bias.
Highlights
The COVID-19 outbreak has become a central topic of research and public discussion throughout 2020 and 2021, after millions of cases and deaths around the world [1]
It consists of images extracted from various COVID-19 related papers, containing a total of 746 images divided into training, validation and test sets of 425, 118 and 203 images, respectively
The models were trained on a dataset that is balanced, considering the number of samples for each classes, but potentially biased by artifacts and spurious aberrations that happen within each class
Summary
The COVID-19 outbreak has become a central topic of research and public discussion throughout 2020 and 2021, after millions of cases and deaths around the world [1]. A key problem regarding this disease is the fast spread and the lack of reliable testing (such as using reverse transcription, or RT-PCR, tests) in enough numbers, in many locations [1]. The magnitude of this pandemic results in overworked medical staff in places with less testing capabilities. This situation greatly motivated the use of Computer Assisted Diagnostic (CAD) tools, to help medical professionals in the triage and sorting of cases. Throughout the pandemic, a growing number of works have been published, describing CXR and CT-scan models for the tasks of multiclass classification of CXR and CT-scan images [2,3,4]. A number of such publications report promising classification metrics [5,6,7]. The models are based on various types of Convolutional Neural Networks (CNNs), which are currently the best type of image classifiers for medical imaging data
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
