Revisiting Lesion Tracking in 3D Total Body Photography

TL;DR

This paper introduces a novel framework for tracking skin lesions in 3D total body photography, addressing previous challenges with improved accuracy and robustness, supported by a large-scale annotated dataset.

Contribution

The paper presents a new lesion tracking framework using correspondence maps and flow fields, along with the first large-scale dataset for skin lesion tracking.

Findings

Achieves 89.9% success rate at 10 mm criterion

Achieves 98.2% matching accuracy for subjects with >200 lesions

Addresses key challenges in lesion tracking accuracy and noise sensitivity

Abstract

Melanoma is the most deadly form of skin cancer. Tracking the evolution of nevi and detecting new lesions across the body is essential for the early detection of melanoma. Despite prior work on longitudinal tracking of skin lesions in 3D total body photography, there are still several challenges, including 1) low accuracy for finding correct lesion pairs across scans, 2) sensitivity to noisy lesion detection, and 3) lack of large-scale datasets with numerous annotated lesion pairs. We propose a framework that takes in a pair of 3D textured meshes, matches lesions in the context of total body photography, and identifies unmatchable lesions. We start by computing correspondence maps bringing the source and target meshes to a template mesh. Using these maps to define source/target signals over the template domain, we construct a flow field aligning the mapped signals. The initial correspondence maps are then refined by advecting forward/backward along the vector field. Finally, lesion assignment is performed using the refined correspondence maps. We propose the first large-scale dataset for skin lesion tracking with 25K lesion pairs across 198 subjects. The proposed method achieves a success rate of 89.9% (at 10 mm criterion) for all pairs of annotated lesions and a matching accuracy of 98.2% for subjects with more than 200 lesions.