No abstract

Purpose: Manual interpretation of chest radiographs is a challenging task and is prone to errors. An automated system capable of categorizing chest radiographs based on the pathologies identified could aid in the timely and efficient diagnosis of chest pathologies. Method: For this retrospective study, 4476 chest radiographs were collected between January and April 2021 from two tertiary care hospitals. Three expert radiologists established the ground truth, and all radiographs were analyzed using a deep-learning AI model to detect suspicious ROIs in the lungs, pleura, and cardiac regions. Three test readers (different from the radiologists who established the ground truth) independently reviewed all radiographs in two sessions (unaided and AI-aided mode) with a washout period of one month. Results: The model demonstrated an aggregate AUROC of 91.2% and a sensitivity of 88.4% in detecting suspicious ROIs in the lungs, pleura, and cardiac regions. These results outperform unaided human readers, who achieved an aggregate AUROC of 84.2% and sensitivity of 74.5% for the same task. When using AI, the aided readers obtained an aggregate AUROC of 87.9% and a sensitivity of 85.1%. The average time taken by the test readers to read a chest radiograph decreased by 21% (p < 0.01) when using AI. Conclusion: The model outperformed all three human readers and demonstrated high AUROC and sensitivity across two independent datasets. When compared to unaided interpretations, AI-aided interpretations were associated with significant improvements in reader performance and chest radiograph interpretation time.

Objective: To assess a deep learning-based artificial intelligence model for the detection of pulmonary nodules on chest radiographs and to compare its performance with board-certified human readers. Methods: For this retrospective study, 308 chest radiographs were obtained between January 2019 to December 2021 from a tertiary care hospital. All radiographs were analyzed using a deep learning AI model called DxNodule AI Screen. Two expert board-certified radiologists established the ground truth, and 11 test readers independently reviewed all radiographs in two sessions (unaided and AI-aided mode) with a washout period of one month. Results: The standalone model had an AUROC of 0.905 [0.87, 0.94] in detecting pulmonary nodules. The mean AUROC across the 11 readers improved from 0.798 [0.74, 0.86] for unaided interpretation to 0.846 [0.82, 0.880] for AI-aided interpretation. With DxNodule AI Screen, readers were able to identify nodules at the correct locations, which they otherwise missed. The mean specificity, accuracy, PPV, and NPV of the readers improved significantly from 0.87 [0.78, 0.96], 0.78 [0.72, 0.84], 0.77 [0.65, 0.88], and 0.86 [0.81, 0.90] in the unaided session to 0.89 [0.82, 0.96], 0.83 [0.80, 0.85], 0.82 [0.73, 0.9], and 0.89 [0.86, 0.92], respectively in the aided session. Conclusion: DxNodule AI Screen outperformed human readers in nodule detection performance on chest radiographs, and enhanced human readers' performances when used as an aid.

Background: The COVID-19 pandemic has claimed numerous lives in the last three years. With new variants emerging every now and then, the world is still battling with the management of COVID-19. Purpose: To utilize a deep learning model for the automatic detection of severity scores from chest CT scans of COVID-19 patients and compare its diagnostic performance with experienced human readers. Methods: A deep learning model capable of identifying consolidations and ground-glass opacities from the chest CT images of COVID-19 patients was used to provide CT severity scores on a 25-point scale for definitive pathogen diagnosis. The model was tested on a dataset of 469 confirmed COVID-19 cases from a tertiary care hospital. The quantitative diagnostic performance of the model was compared with three experienced human readers. Results: The test dataset consisted of 469 CT scans from 292 male (average age: 52.30) and 177 female (average age: 53.47) patients. The standalone model had an MAE of 3.192, which was lower than the average radiologists' MAE of 3.471. The model achieved a precision of 0.69 [0.65, 0.74] and an F1 score of 0.67 [0.62, 0.71], which was significantly superior to the average reader precision of 0.68 [0.65, 0.71] and F1 score of 0.65 [0.63, 0.67]. The model demonstrated a sensitivity of 0.69 [95% CI: 0.65, 0.73] and specificity of 0.83 [95% CI: 0.81, 0.85], which was comparable to the performance of the three human readers, who had an average sensitivity of 0.71 [95% CI: 0.69, 0.73] and specificity of 0.84 [95% CI: 0.83, 0.85]. Conclusion: The AI model provided explainable results and performed at par with human readers in calculating CT severity scores from the chest CT scans of patients affected with COVID-19. The model had a lower MAE than that of the radiologists, indicating that the CTSS calculated by the AI was very close in absolute value to the CTSS determined by the reference standard.

Deep learning semantic segmentation algorithms can localise abnormalities or opacities from chest radiographs. However, the task of collecting and annotating training data is expensive and requires expertise which remains a bottleneck for algorithm performance. We investigate the effect of image augmentations on reducing the requirement of labelled data in the semantic segmentation of chest X-rays for pneumonia detection. We train fully convolutional network models on subsets of different sizes from the total training data. We apply a different image augmentation while training each model and compare it to the baseline trained on the entire dataset without augmentations. We find that rotate and mixup are the best augmentations amongst rotate, mixup, translate, gamma and horizontal flip, wherein they reduce the labelled data requirement by 70% while performing comparably to the baseline in terms of AUC and mean IoU in our experiments.