Comparison of Gray-scale Inversion to Improve Detection of Pulmonary Nodules on Chest X-rays Between Radiologists and a Deep Convolutional Neural Network.

Detection of pulmonary nodules on chest x-rays is an important task for radiologists. Previous studies have shown improved detection rates using gray-scale inversion. The purpose of our study was to compare the efficacy of gray-scale inversion in improving the detection of pulmonary nodules on chest x-rays for radiologists and machine learning models (ML). We created a mixed dataset consisting of 60, 2-view (posteroanterior view - PA and lateral view) chest x-rays with computed tomography confirmed nodule(s) and 62 normal chest x-rays. Twenty percent of the cases were separated for a testing dataset (24 total images). Data augmentation through mirroring and transfer learning was used for the remaining cases (784 total images) for supervised training of 4 ML models (grayscale PA, grayscale lateral, gray-scale inversion PA, and gray-scale inversion lateral) on Google's cloud-based AutoML platform. Three cardiothoracic radiologists analyzed the complete 2-view dataset (n=120) and, for comparison to the ML, the single-view testing subsets (12 images each). Gray-scale inversion (area under the curve (AUC) 0.80, 95% confidence interval (CI) 0.75-0.85) did not improve diagnostic performance for radiologists compared to grayscale (AUC 0.84, 95% CI 0.79-0.88). Gray-scale inversion also did not improve diagnostic performance for the ML. The ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5% respectively). In the limited testing dataset, the ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5%, respectively). Further investigation of other post-processing algorithms to improve diagnostic performance of ML is warranted.

Shedding the Light on the Off-Hours Problem in Radiology.

Diagnostic error and diagnostic delays in health care are widespread. This article outlines an improvement effort targeting weekday evening inpatient radiology delays through staffing changes replacing trainees with faculty-trainee team coverage, pushing faculty coverage from 4 pm to 8 pm. Order-report turnaround times (TATs), critical findings TATs for pneumothorax and intracranial hemorrhage (ICH), and percentage meeting target were compared pre and post implementation for the 4 to 8 pm time frame using the Mann-Whitney U and χ2 tests, respectively. Stakeholder surveys assessed patient safety, morale, education, and operational efficiency. Median TATs (minutes) improved: X-rays 906 to 112, computed tomography 994 to 84, magnetic resonance imaging 1172 to 233, and ultrasound 88 to 58. Median critical findings TATs (minutes) improved from 853 to 30 and 112 to 22 for pneumothorax and ICH, respectively, and the percentage meeting target improved from 45% to 65%. Survey results reported perceived improvement in patient safety, education, and operational efficiency and no impact on morale.