September 5, 2025PeerJOpen Access

Market-approved convolutional neural network tasked with classifying skin lesions under suspicion of melanoma: performance across primary care clinics within Australia

View Full Paper

Ask AI

Bookmark

Authors

Discussion

This multicentre study assesses the diagnostic performance of a CNN for melanoma classification, suggesting room for improvement.

The CNN achieved an average sensitivity of 63.2%, indicating moderate ability to detect melanoma.
Specificity was recorded at 53.9%, reflecting its limited accuracy in classifying non-melanoma lesions.
The study involved a multicentre, cross-sectional analysis of 373 skin lesions, providing a robust clinical context.
Findings highlight that enhancement of the CNN's performance is crucial before clinical implementation in Australia.

Miller et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark