Automatic acromegaly detection using deep learning on hand images: a multicenter observational study - PubMed
3 hours ago
- #deep learning
- #medical imaging
- #acromegaly
- Development of a privacy-conscious deep learning model for detecting acromegaly using hand images.
- Study involved 716 patients (317 with acromegaly and 399 controls) and 11,480 images from 15 Japanese pituitary centers.
- Hand images focused on the dorsal and fist sign, excluding palm/fingerprint regions, were used.
- Model achieved high performance metrics: sensitivity of 0.89, specificity of 0.91, and AUC of 0.96.
- Outperformed endocrinologists with F1-scores ranging from 0.43 to 0.63.
- Highlights utility of dorsal hand and fist sign as diagnostic clues for acromegaly.
- Potential deployment in public settings like health checkups due to privacy-conscious features.
- Further validation needed with larger datasets including healthy individuals and diverse diseases.