Across five encoder backbones, better self-supervised vision-transformer features improve both GCN graph homophily and breast-ultrasound classification accuracy, with homophily correlating strongly with accuracy.
Biocybernetics and Biomedical Engineering42, 921–933 (2022)
1 Pith paper cite this work, alongside 18 external citations. Polarity classification is still indexing.
1
Pith paper citing it
18
external citations · OpenAlex
fields
eess.IV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analyzing Image Encoder Choices and Graph Homophily in GCN Frameworks for Breast Ultrasound Classification
Across five encoder backbones, better self-supervised vision-transformer features improve both GCN graph homophily and breast-ultrasound classification accuracy, with homophily correlating strongly with accuracy.