To assess the generalizability of a deep learning pneumothorax detection model on datasets from multiple external institutions and examine patient and acquisition factors that might influence performance. In this retrospective study, a deep learning model was trained for pneumothorax detection by merging two large open-source chest radiograph datasets: ChestX-ray14 and CheXpert. It was then tested on six external datasets from multiple independent institutions (labeled A–F) in a retrospective case-control design (data acquired between 2016 and 2019 from institutions A–E; institution F consisted of data from the MIMIC–CXR dataset). Performance on each dataset was evaluated by using area under the receiver operating characteristic curve (AUC) analysis, sensitivity, specificity, and positive and negative predictive values, with two radiologists in consensus being used as the reference standard. Patient and acquisition factors that influenced performance were analyzed.

MIT 6.S191 is more than just another lecture series on deep learning. In designing the course, we wanted to do something more. We wanted to equip our audience with the practical skills necessary to go out and implement their own deep learning models, to apply what they got out of this course to the questions that excite and inspire them. And so, we turned to TensorFlow. We designed two TensorFlow based software labs, focusing on music generation with recurrent neural networks and pneumothorax detection in medical images, to complement the course lectures.