Detecting emphysema with multiple instance learning

Emphysema is part of chronic obstructive pulmonary disease, a leading cause of mortality worldwide. Visual assessment of emphysema presence is useful for identifying subjects at risk and for research into disease development. We train a machine learning method to predict emphysema from visually asse...

Full description

Saved in:
Bibliographic Details
Published inProceedings (International Symposium on Biomedical Imaging) pp. 510 - 513
Main Authors Orting, Silas Nyboe, Petersen, Jens, Thomsen, Laura H., Wille, Mathilde M W, de Bruijne, Marleen
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2018
Subjects
Biomedical imaging
Computed tomography
Diseases
Emphysema
Lung
Multiple Instance Learning
Training
Visualization
Weak supervision
Online AccessGet full text

Cover

More Information
Summary:Emphysema is part of chronic obstructive pulmonary disease, a leading cause of mortality worldwide. Visual assessment of emphysema presence is useful for identifying subjects at risk and for research into disease development. We train a machine learning method to predict emphysema from visually assessed expert labels. We use a multiple instance learning approach to predict both scan-level and region-level emphysema presence. We evaluate performance on 600 low-dose CT scans from the Danish Lung Cancer Screening Study and achieve an AUC of 0.82 for scan-level prediction and AUCs between 0.76 and 0.88 for region-level prediction.
ISSN:1945-8452
DOI:10.1109/ISBI.2018.8363627