Lesion Elevation Prediction from Skin Images Improves Diagnosis

TL;DR

This study demonstrates that predicting skin lesion elevation from images and using these predictions as additional features enhances the accuracy of skin lesion diagnosis models across multiple datasets.

Contribution

It introduces a deep learning approach to predict lesion elevation labels from 2D images and shows that these labels improve diagnostic performance across different datasets.

Findings

Elevation prediction accuracy on derm7pt dataset

Improved diagnosis AUROC by up to 6.29% using elevation features

Cross-domain generalization of elevation-based diagnosis enhancement

Abstract

While deep learning-based computer-aided diagnosis for skin lesion image analysis is approaching dermatologists' performance levels, there are several works showing that incorporating additional features such as shape priors, texture, color constancy, and illumination further improves the lesion diagnosis performance. In this work, we look at another clinically useful feature, skin lesion elevation, and investigate the feasibility of predicting and leveraging skin lesion elevation labels. Specifically, we use a deep learning model to predict image-level lesion elevation labels from 2D skin lesion images. We test the elevation prediction accuracy on the derm7pt dataset, and use the elevation prediction model to estimate elevation labels for images from five other datasets: ISIC 2016, 2017, and 2018 Challenge datasets, MSK, and DermoFit. We evaluate cross-domain generalization by using these estimated elevation labels as auxiliary inputs to diagnosis models, and show that these improve the classification performance, with AUROC improvements of up to 6.29% and 2.69% for dermoscopic and clinical images, respectively. The code is publicly available at https://github.com/sfu-mial/LesionElevation.