TextRay: Mining Clinical Reports to Gain a Broad Understanding of Chest X-rays
This addresses the shortage of physicians for rapid CXR interpretation, though it is incremental as it builds on existing methods with new data.
The paper tackled the problem of interpreting chest X-rays by mining clinical reports to create a large training set, and trained a deep learning model that, for 12 findings, achieved performance where radiologists agreed more with the algorithm than with each other on average.
The chest X-ray (CXR) is by far the most commonly performed radiological examination for screening and diagnosis of many cardiac and pulmonary diseases. There is an immense world-wide shortage of physicians capable of providing rapid and accurate interpretation of this study. A radiologist-driven analysis of over two million CXR reports generated an ontology including the 40 most prevalent pathologies on CXR. By manually tagging a relatively small set of sentences, we were able to construct a training set of 959k studies. A deep learning model was trained to predict the findings given the patient frontal and lateral scans. For 12 of the findings we compare the model performance against a team of radiologists and show that in most cases the radiologists agree on average more with the algorithm than with each other.