Concordance in basal cell carcinoma diagnosis. Building a proper ground truth to train Artificial Intelligence tools

TL;DR

This study establishes a reliable ground-truth for basal cell carcinoma diagnosis by analyzing dermatologist consensus, improving AI training, and highlighting the importance of multi-expert validation for accurate dermoscopic feature detection.

Contribution

It provides a method to derive a consensus ground-truth from multiple dermatologists, enhancing AI training accuracy for BCC diagnosis.

Findings

High dermatologist agreement on BCC diagnosis (Fleiss-Kappa=0.908)

AI performance varies depending on the ground-truth source

Consensus-based ground-truth improves AI diagnostic accuracy

Abstract

Background: The existence of different basal cell carcinoma (BCC) clinical criteria cannot be objectively validated. An adequate ground-truth is needed to train an artificial intelligence (AI) tool that explains the BCC diagnosis by providing its dermoscopic features. Objectives: To determine the consensus among dermatologists on dermoscopic criteria of 204 BCC. To analyze the performance of an AI tool when the ground-truth is inferred. Methods: A single center, diagnostic and prospective study was conducted to analyze the agreement in dermoscopic criteria by four dermatologists and then derive a reference standard. 1434 dermoscopic images have been used, that were taken by a primary health physician, sent via teledermatology, and diagnosed by a dermatologist. They were randomly selected from the teledermatology platform (2019-2021). 204 of them were tested with an AI tool; the remainder trained it. The performance of the AI tool trained using the ground-truth of one dermatologist versus the ground-truth statistically inferred from the consensus of four dermatologists was analyzed using McNemar's test and Hamming distance. Results: Dermatologists achieve perfect agreement in the diagnosis of BCC (Fleiss-Kappa=0.9079), and a high correlation with the biopsy (PPV=0.9670). However, there is low agreement in detecting some dermoscopic criteria. Statistical differences were found in the performance of the AI tool trained using the ground-truth of one dermatologist versus the ground-truth statistically inferred from the consensus of four dermatologists. Conclusions: Care should be taken when training an AI tool to determine the BCC patterns present in a lesion. Ground-truth should be established from multiple dermatologists.