• Funk, Christopher
• Montgomery, Sean
• Hersh, Andrew M.
• Morris, Michael
• Anderson, Jess T.
• Aylward, Stephen
• Li, Forrest
• Peethumangsin, Erica

Abstract

<jats:sec><jats:title>BACKGROUND</jats:title><jats:p>Ultrasound (US) for the detection of pneumothorax shows excellent sensitivity in the hands of skilled providers. Artificial intelligence may facilitate the movement of US for pneumothorax into the prehospital setting. The large amount of training data required for conventional neural network methodologies has limited their use in US so far.</jats:p></jats:sec><jats:sec><jats:title>METHODS</jats:title><jats:p>A limited training database was supplied by Defense Advanced Research Projects Agency of 30 patients, 15 cases with pneumothorax and 15 cases without. There were two US videos per patient, of which we were allowed to choose one to train on, so that a limited set of 30 videos were used. Images were annotated for ribs and pleural interface. The software performed anatomic reconstruction to identify the region of interest bounding the pleura. Three neural networks were created to analyze images on a pixel-by-pixel fashion with direct voting determining the outcome. Independent verification and validation was performed on a data set gathered by the Department of Defense.</jats:p></jats:sec><jats:sec><jats:title>RESULTS</jats:title><jats:p>Anatomic reconstruction with the identification of ribs and pleura was able to be accomplished on all images. On independent verification and validation against the Department of Defense testing data, our program concurred with the SME 80% of the time and achieved a 86% sensitivity (18/21) for pneumothorax and a 75% specificity for the absence of pneumothorax (18/24). Some of the mistakes by our artificial intelligence can be explained by chest wall motion, hepatization of the underlying lung, or being equivocal cases.</jats:p></jats:sec><jats:sec><jats:title>CONCLUSION</jats:title><jats:p>Using learning with limited labeling techniques, pneumothorax was identified on US with an accuracy of 80%. Several potential improvements are controlling for chest wall motion and the use of longer videos.</jats:p></jats:sec><jats:sec><jats:title>LEVEL OF EVIDENCE</jats:title><jats:p>Diagnostic Tests; Level III.</jats:p></jats:sec>

Topics

• size-exclusion chromatography