Uncertainty-Aware Convolutional Neural Network for Identifying Bilateral Opacities on Chest X-rays: A Tool to Aid Diagnosis of Acute Respiratory Distress Syndrome

Abstract

Acute Respiratory Distress Syndrome (ARDS) is a severe lung injury with high mortality, primarily characterized by bilateral pulmonary opacities on chest radiographs and hypoxemia. In this work, we trained a convolutional neural network (CNN) model that can reliably identify bilateral opacities on routine chest X-ray images of critically ill patients. We propose this model as a tool to generate predictive alerts for possible ARDS cases, enabling early diagnosis. Our team created a unique dataset of 7800 single-view chest-X-ray images labeled for the presence of bilateral or unilateral pulmonary opacities, or ‘equivocal’ images, by three blinded clinicians. We used a novel training technique that enables the CNN to explicitly predict the ‘equivocal’ class using an uncertainty-aware label smoothing loss. We achieved an Area under the Receiver Operating Characteristic Curve (AUROC) of 0.82 (95% CI: 0.80, 0.85), a precision of 0.75 (95% CI: 0.73, 0.78), and a sensitivity of 0.76 (95% CI: 0.73, 0.78) on the internal test set while achieving an (AUROC) of 0.84 (95% CI: 0.81, 0.86), a precision of 0.73 (95% CI: 0.63, 0.69), and a sensitivity of 0.73 (95% CI: 0.70, 0.75) on an external validation set. Further, our results show that this approach improves the model calibration and diagnostic odds ratio of the hypothesized alert tool, making it ideal for clinical decision support systems.

Method for Detecting Pathology of Internal Organs Using Bioelectrography

“…Such methods include studies that allow, on the basis of the X-ray images and machinelearning methods used, us to identify the pathology of the respiratory organs [1][2][3]. The methods based on the classification of untreated lung sounds and the detection of pneumonia and chronic obstructive pulmonary diseases can be attributed [4][5][6].…”

“…The listed methods have a high resource intensity in terms of the applied software and hardware. Summarizing the results [1][2][3][4][5][6][7][8][9][10][11][12][13][14], it is advisable to note that with almost all the methods, there is no possibility of automating the detection of pathology or deviations in the functioning of a particular organ (Table 1). In the table, a «+» sign indicates the presence of this property from the column header in the method from the first column in this source, «−» its absence.…”

“…N. For example, M 3 P may be "responsible" for liver pathology. Based on this, it is necessary to reduce the feature space of the matrix rows M 3 B , taking into account the fact that these data will reveal liver pathology.…”