Deep learning classification of chest x-ray images
This work addresses diagnostic accuracy in medical imaging for healthcare, but it is incremental as it builds on existing deep learning approaches with specific improvements.
The authors tackled the problem of misdiagnosing thoracic diseases from chest X-ray images by proposing a deep learning method, which improved AUC for detecting pulmonary nodules and cardiomegaly compared to three existing methods.
We propose a deep learning based method for classification of commonly occurring pathologies in chest X-ray images. The vast number of publicly available chest X-ray images provides the data necessary for successfully employing deep learning methodologies to reduce the misdiagnosis of thoracic diseases. We applied our method to the classification of two example pathologies, pulmonary nodules and cardiomegaly, and we compared the performance of our method to three existing methods. The results show an improvement in AUC for detection of nodules and cardiomegaly compared to the existing methods.