Interaction of a priori Anatomic Knowledge with Self-Supervised Contrastive Learning in Cardiac Magnetic Resonance Imaging

by   Makiya Nakashima, et al.

Training deep learning models on cardiac magnetic resonance imaging (CMR) can be a challenge due to the small amount of expert generated labels and inherent complexity of data source. Self-supervised contrastive learning (SSCL) has recently been shown to boost performance in several medical imaging tasks. However, it is unclear how much the pre-trained representation reflects the primary organ of interest compared to spurious surrounding tissue. In this work, we evaluate the optimal method of incorporating prior knowledge of anatomy into a SSCL training paradigm. Specifically, we evaluate using a segmentation network to explicitly local the heart in CMR images, followed by SSCL pretraining in multiple diagnostic tasks. We find that using a priori knowledge of anatomy can greatly improve the downstream diagnostic performance. Furthermore, SSCL pre-training with in-domain data generally improved downstream performance and more human-like saliency compared to end-to-end training and ImageNet pre-trained networks. However, introducing anatomic knowledge to pre-training generally does not have significant impact.


page 1

page 2

page 3

page 4


Unlocking the Diagnostic Potential of ECG through Knowledge Transfer from Cardiac MRI

The electrocardiogram (ECG) is a widely available diagnostic tool that a...

About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations

Self-supervised learning methods for computer vision have demonstrated t...

Learning to segment with limited annotations: Self-supervised pretraining with regression and contrastive loss in MRI

Obtaining manual annotations for large datasets for supervised training ...

Self-Supervised Learning for Spinal MRIs

A significant proportion of patients scanned in a clinical setting have ...

3D Masked Modelling Advances Lesion Classification in Axial T2w Prostate MRI

Masked Image Modelling (MIM) has been shown to be an efficient self-supe...

Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization

Unmasking the decision-making process of machine learning models is esse...

Please sign up or login with your details

Forgot password? Click here to reset