Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection

By Biraja Ghoshal, Allan Tucker. 2020

404 citations recorded by the source corpus.

Deep Learning has achieved state of the art performance in medical imaging. However, these methods for disease detection focus exclusively on improving the accuracy of classification or predictions without quantifying uncertainty in a decision. Knowing how much confidence there is in a computer-based medical diagnosis is essential for gaining clinicians trust in the technology and therefore improve treatment. Today, the 2019 Coronavirus (SARS-CoV-2) infections are a major healthcare challenge around the world. Detecting COVID-19 in X-ray images is crucial for diagnosis, assessment and treatment. However, diagnostic uncertainty in the report is a challenging and yet inevitable task for radiologist. In this paper, we investigate how drop-weights based Bayesian Convolutional Neural Networks (BCNN) can estimate uncertainty in Deep Learning solution to improve the diagnostic performance of the human-machine team using publicly available COVID-19 chest X-ray dataset and show that the uncertainty in prediction is highly correlates with accuracy of prediction. We believe that the availability of uncertainty-aware deep learning solution will enable a wider adoption of Artificial Intelligence (AI) in a clinical setting.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans (2020, methodology): “9172 [8] X-ray 2D Yes - 5,941 68 4,290 1,583 1,188 2D 88.”
Leveraging Data Science to Combat COVID-19: A Comprehensive Review (2020, background): “[141] Chest X-rays Bayesian Convolutional Neural Networks (BCNN) Investigated the significance of dropping weights BCNN.”
Automatic Detection of Coronavirus Disease (COVID-19) in X-ray and CT Images: A Machine Learning Based Approach (2020, neutral): “Ghoshal and Tucker [22] investigated the diagnostic uncertainty and interpretability of deep learning-based methods for COVID-19 detection in X-ray images.”
AI for radiographic COVID-19 detection selects shortcuts over signal (2020, methodology): “While such spurious correlations may arise in any dataset, we observed that many recent ML models for radiographic detection of COVID-19 were trained using data with the potential for near worst-case confounding: these datasets are composed of an exclusively COVID-19 negative source and a COVID-19 p”
Artificial Intelligence (AI) and Big Data for Coronavirus (COVID-19) Pandemic: A Survey on the State-of-the-Arts (2020, methodology): “In contrast with other studies, the work in [51] exploited a pre-trained ResNet50V2 model [61] with the Bayesian DL classifier to estimate the diagnostic uncertainty.”
Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19 (2020, background): “[73] propose a Bayesian Convolutional Neural network to estimate the diagnosis uncertainty in COVID-19 prediction.”
Automated Deep Transfer Learning-Based Approach for Detection of COVID-19 Infection in Chest X-rays (2020, neutral): “Ghoshal and Tucker [21] utilized Bayesian CNN (BCNN) to diagnosis the COVID-19 using a chest X-ray.”
AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system (2020, neutral): “Among X-ray based AI-assisted systems, Ghoshal et al. [41] develop a Bayesian Convolutional Neural network to measure the diagnosis uncertainty of COVID-19 prediction.”
Deep learning and medical image processing for coronavirus (COVID-19) pandemic: A survey (2020, neutral): “Similar information fusion has been observed in Ghoshal and Tucker (2020) where X-ray images of the lung from Dr. Joseph Cohen ’ s GitHub repository have been augmented with Chest X-ray images available from the publicly available Kaggle S. Bhattacharya et al. repository.”
COVIDGR Dataset and COVID-SDNet Methodology for Predicting COVID-19 Based on Chest X-Ray Images (2020, background): “In [22], the authors proposed explaining the decision of the classification model to radiologists using different saliency map types together with uncertainty estimations (i.”
Machine-Learning-Based Disease Diagnosis: A Comprehensive Review (2021, background): “With a dataset of 5941 images, Ghoshal & Tucker (2020) achieved 92.9% accuracy [99].”
Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks (2020, methodology): “Ghoshal and Tucker used the dropweights based Bayesian CNN model using chest X-ray images for the diagnosis of COVID-19 [23].”
Mapping the Landscape of Artificial Intelligence Applications against COVID-19 (2020, background): “However, further work is ongoing in order to make predictions interpretable (Karim et al., 2020; Ghoshal & Tucker, 2020) † and to ensure that the models can be deployed in mobile and low-resource settings (Li et al., 2020b) † .”
Predicting the trend of indicators related to Covid-19 using the combined MLP-MC model (2021, neutral): “Then, given the speciﬁed states, the transition probability matrix of states R ( m ) , m = 1 , was obtained per each indicator as follows: The tran siti on prob abil ity matr ix of stat es for the numb er of disc harg ed cases”