Visualizing abnormalities in chest radiographs through salient network activations in Deep Learning.
Rajaraman S, Antani SK, Xue Z, Candemir S, Jaeger S, Thoma GR
Proc. IEEE Life Sciences Conference (LSC), Sydney, Australia, 2017. pp. 71-74, DOI:10.1109/LSC.2017.8268146.
Abstract:
This study aims to visualize salient network activations in a customized Convolutional Neural Network (CNN) based Deep Learning (DL) model, applied to the challenge of chest X-ray (CXR) screening. Computer-aided detection (CAD) software using machine learning (ML) approaches have been developed for analyzing CXRs for abnormalities with an aim to reduce delays in resourceconstrained settings. However, field experts often need to know how these techniques arrive at a decision. In this study, we visualize the task-specific features and salient network activations in a customized DL model towards understanding the learned parameters, model behavior and optimizing its architecture and hyper-parameters for improved learning. The performance of the customized model is evaluated against the pre-trained DL models. It is found that the proposed model precisely localizes the abnormalities, aiding in improved abnormality screening.
Rajaraman S, Antani SK, Xue Z, Candemir S, Jaeger S, Thoma GR. Visualizing abnormalities in chest radiographs through salient network activations in Deep Learning.
Proc. IEEE Life Sciences Conference (LSC), Sydney, Australia, 2017. pp. 71-74, DOI:10.1109/LSC.2017.8268146.