Share Email Print
cover

Proceedings Paper • new

Impact of imprinted labels on deep learning classification of AP and PA thoracic radiographs
Author(s): Jennie Crosby; Thomas Rhines; Clara Duan; Feng Li; Heber MacMahon; Maryellen Giger
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Deep learning can be used to classify images to verify or correct DICOM header information. One situation where this is useful is in the classification of thoracic radiographs that were acquired anteroposteriorly (AP) or posteroanteriorly (PA). A convolutional neural network (CNN) was previously trained and showed a strong performance in the task of classifying between AP and PA radiographs, giving a 0.97 ± 0.005 AUC for an independent test set. However, 81% of the AP training set and 24% of the AP independent test set consisted of images with imprinted labels. To evaluate the effect of labels on training and testing of a CNN, the labels on the images used for training were removed by cropping. Then the CNN was retrained using the cropped images with the same training parameters as before. The retrained CNN was tested on the same independent test set and resulted in a 0.95 ± 0.007 AUC in the task of classifying between AP and PA radiographs. The p-value is 0.002 between the AUCs from the two networks, showing a statistically significant decrease in performance by the network trained on the cropped images. The decrease in performance may be due to the network being previously trained to recognize imprinted labels or due to relevant anatomy being cropped along with the label, however, the performance is still high and can be incorporated in clinical workflow.

Paper Details

Date Published: 15 March 2019
PDF: 5 pages
Proc. SPIE 10954, Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications, 109540E (15 March 2019); doi: 10.1117/12.2513026
Show Author Affiliations
Jennie Crosby, The Univ. of Chicago (United States)
Thomas Rhines, The Univ. of Chicago (United States)
Clara Duan, The Univ. of Chicago (United States)
Feng Li, The Univ. of Chicago (United States)
Heber MacMahon, The Univ. of Chicago (United States)
Maryellen Giger, The Univ. of Chicago (United States)


Published in SPIE Proceedings Vol. 10954:
Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications
Po-Hao Chen; Peter R. Bak, Editor(s)

© SPIE. Terms of Use
Back to Top