Keywords:
Metastases, Atelectasis, Screening, Computer Applications-Detection, diagnosis, Neural networks, Conventional radiography, CAD, Thorax, Lung, Cardiac
Authors:
N. Ramanauskas, J. Dementaviciene, J. Bialopetravičius, D. Barušauskas, J. Armaitis, J. Stankeviciene, G. Danys, R. Puronaite, R. Kizlaitis; Vilnius/LT
DOI:
10.1594/ecr2018/C-1896
Conclusion
We have demonstrated robust CXR classification results on a particularly heterogeneous set of radiographs from different medical centers worldwide.
We have also created an API to clearly visualize the neural network output and the localization of the detected labels.
Using data from different medical centers contributes greatly to the data heterogeneity and pose significant challenges to creating a neural network which could provide high AUC scores for pathology detection. This however is necessary while working towards a robust algorithm that could be implemented into a real word clinical setting and significantly contribute to radiological diagnostics.
In future work,
we plan to expand the pathology list; improve the localization of the abnormalities in the image; improve the model in general,
in order to increase the accuracy and robustness of the model with respect to images of varying quality etc.; add the possibility to diagnose from several different images (i.e.,
PA+LAT) of the same patient.