A Clinically Inspired Approach for Melanoma classification

TL;DR

This paper introduces a novel clinical-inspired method for melanoma detection that uses intra-patient comparison to identify outliers, improving diagnostic sensitivity and specificity in computer-aided systems.

Contribution

It presents a new approach incorporating differential recognition of outliers into CAD systems, enhancing melanoma diagnosis with clinical justification.

Findings

Outlier detection improves sensitivity by at least 4.1%.

Specificity increases by 4.0% to 8.9%.

Method is effective across different classifiers.

Abstract

Melanoma is a leading cause of deaths due to skin cancer deaths and hence, early and effective diagnosis of melanoma is of interest. Current approaches for automated diagnosis of melanoma either use pattern recognition or analytical recognition like ABCDE (asymmetry, border, color, diameter and evolving) criterion. In practice however, a differential approach wherein outliers (ugly duckling) are detected and used to evaluate nevi/lesions. Incorporation of differential recognition in Computer Aided Diagnosis (CAD) systems has not been explored but can be beneficial as it can provide a clinical justification for the derived decision. We present a method for identifying and quantifying ugly ducklings by performing Intra-Patient Comparative Analysis (IPCA) of neighboring nevi. This is then incorporated in a CAD system design for melanoma detection. This design ensures flexibility to handle cases where IPCA is not possible. Our experiments on a public dataset show that the outlier information helps boost the sensitivity of detection by at least 4.1 % and specificity by 4.0 % to 8.9 %, depending on the use of a strong (EfficientNet) or moderately strong (VGG or ResNet) classifier.