Vision transformers and DINOv2 outperform CNNs at diagnosing Cushing's syndrome from frontal facial photos, with ViT reaching the best F1 score of 85.74% on a 343-patient dataset.
Deep-learning approach to automatic identifi- cation of facial anomalies in endocrine disorders,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Comparative Analysis of Pre-trained Deep Learning Models and DINOv2 for Cushing's Syndrome Diagnosis in Facial Analysis
Vision transformers and DINOv2 outperform CNNs at diagnosing Cushing's syndrome from frontal facial photos, with ViT reaching the best F1 score of 85.74% on a 343-patient dataset.