Back

Interpretable multi-stream ensemble learning for radiographic pattern recognition

Ferreira, J. R.; Cardenas, D. A. C.

2021-08-10 radiology and imaging
10.1101/2021.08.09.21261788 medRxiv
Show abstract

Chest radiography (CXR) remains an essential component to evaluate lung diseases. However, it is crucial nowadays to include computer-based tools to aid physicians in the early detection of chest abnormalities. Therefore, this work proposed deep ensemble models to improve the CXR evaluation, interpretability, and reproducibility. Five convolutional neural networks and six different processed image inputs yielded an AUC of 0.982. Furthermore, ensemble learning could produce more reliable outcomes as it did not consider the information of only one method. Moreover, the ensemble strategy balanced the most critical factors from each model to perform a more consistent classification. Finally, class activation and gradient propagation maps allowed locally visualizing CXR regions that most activate neurons from the trained models and explaining practically which areas of the CXR correlated to the model output.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.