Extended Data Fig. 5: ImageNet and OCT B-scans pre-training contribution for non-OCT-related downstream learning tasks. | Nature Biomedical Engineering

Extended Data Fig. 5: ImageNet and OCT B-scans pre-training contribution for non-OCT-related downstream learning tasks.

From: Accurate prediction of disease-risk factors from volumetric medical scans by a deep vision model pre-trained with 2D scans

Extended Data Fig. 5

Shown are the performance scores for the volumetric ultrasound and MRI regression tasks (R2) and the volumetric CT classification task (ROC AUC) initialized with five different sets of weights. Combined, the proposed SLIViT’s initialization, is ImageNet weights initialization followed by supervised pre-training on the Kermany Dataset. ssCombined is an ImageNet weights initialization followed by self-supervised pre-training on an unlabeled version of the Kermany Dataset. The expected R2 and ROC AUC of a random model are 0 and 0.5, respectively. Box plot whiskers represent a 90% CI.

Back to article page