Journal
IEEE TRANSACTIONS ON MEDICAL IMAGING
Volume 38, Issue 4, Pages 1037-1047Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2018.2877080
Keywords
Unsupervised deep learning; anomaly detection; biomarker identification; optical coherence tomography
Categories
Funding
- Christian Doppler Research Association
- Austrian Federal Ministry for Digital and Economic Affairs
- National Foundation for Research, Technology, and Development through the Austrian Science Fund [FWF I2714-B31]
- IBM
- NVIDIA Corporation
Ask authors/readers for more resources
The identification and quantification of markers in medical images is critical for diagnosis, prognosis, and disease management. Supervised machine learning enables the detection and exploitation of findings that are known a priori after annotation of training examples by experts. However, supervision does not scale well, due to the amount of necessary training examples, and the limitation of the marker vocabulary to known entities. In this proof-of-concept study, we propose unsupervised identification of anomalies as candidates for markers in retinal optical coherencetomography (OCT) imaging data without a constraint to a priori definitions. We identify and categorize marker candidates occurring frequently in the data and demonstrate that these markers show a predictive value in the task of detecting disease. A careful qualitative analysis of the identified data driven markers reveals how their quantifiable occurrence aligns with our current understanding of disease course, in early-and late age-related macular degeneration (AMD) patients. A multi-scale deep denoising autoencoder is trained on healthy images, and a one-class support vector machine identifies anomalies in new data. Clustering in the anomalies identifies stable categories. Using these markers to classify healthy-, early AMD- and late AMD cases yields an accuracy of 81.40%. In a second binary classification experiment on a publicly available data set (healthy versus intermediate AMD), the model achieves an area under the ROC curve of 0.944.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available