Skip to main content
[Preprint]. 2023 Nov 21:rs.3.rs-3044914. [Version 2] doi: 10.21203/rs.3.rs-3044914/v2

Figure 2 |. SLIViT’s outperformance overview.

Figure 2 |

Shown are the performance scores in one classification task (with two different metrics) of eye disease biomarker diagnosis in volumetric-OCT scans and two regression tasks of (1) heart function analysis in ultrasound videos and (2) liver fat levels imputation in volumetric MRI scans. Domain-specific methods (hatched) used are SLIVER-net, EchoNet, and 3D ResNet, for OCT, ultrasound, and MRI, respectively. The general cross-modality benchmarking used are 3D ResNet (green) and UniMiSS (brown) which are (fully) supervised and self-supervised-based, respectively (see relevant experiment’s section for additional benchmarking). Box plot whiskers represent a 90% CI.