Self-supervised Learning for Spinal MRIs
A significant proportion of patients scanned in a clinical setting have follow-up scans. We show in this work that such longitudinal scans alone can be used as a form of “free” self-supervision for training a deep network. We demonstrate this self-supervised learning for the case of T2-weighted sagi...
Saved in:
Published in | Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support pp. 294 - 302 |
---|---|
Main Authors | , , |
Format | Book Chapter |
Language | English |
Published |
Cham
Springer International Publishing
|
Series | Lecture Notes in Computer Science |
Online Access | Get full text |
Cover
Loading…
Summary: | A significant proportion of patients scanned in a clinical setting have follow-up scans. We show in this work that such longitudinal scans alone can be used as a form of “free” self-supervision for training a deep network. We demonstrate this self-supervised learning for the case of T2-weighted sagittal lumbar Magnetic Resonance Images (MRIs). A Siamese convolutional neural network (CNN) is trained using two losses: (i) a contrastive loss on whether the scan is of the same person (i.e. longitudinal) or not, together with (ii) a classification loss on predicting the level of vertebral bodies. The performance of this pre-trained network is then assessed on a grading classification task. We experiment on a dataset of 1016 subjects, 423 possessing follow-up scans, with the end goal of learning the disc degeneration radiological gradings attached to the intervertebral discs. We show that the performance of the pre-trained CNN on the supervised classification task is (i) superior to that of a network trained from scratch; and (ii) requires far fewer annotated training samples to reach an equivalent performance to that of the network trained from scratch. |
---|---|
ISBN: | 3319675575 9783319675572 |
ISSN: | 0302-9743 1611-3349 |
DOI: | 10.1007/978-3-319-67558-9_34 |