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.

Additional Metadata
Keywords Emphysema, Multiple Instance Learning, Weak supervision
Persistent URL dx.doi.org/10.1109/ISBI.2018.8363627, hdl.handle.net/1765/108752
Conference 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
Rights no subscription
Orting, S.N. (Silas Nyboe), Petersen, J, Thomsen, L.H, Wille, M.M.W, & de Bruijne, M. (2018). Detecting emphysema with multiple instance learning. In Proceedings - International Symposium on Biomedical Imaging (pp. 510–513). doi:10.1109/ISBI.2018.8363627