Masked Autoencoder Joint Learning for Robust Spitzoid Tumor Classification

TL;DR

This paper introduces ReMAC, a novel method for classifying spitzoid tumors using DNA methylation data that effectively handles missing data, improving robustness over existing methods.

Contribution

ReMAC extends ReMasker to perform robust tumor classification on high-dimensional methylation data with missing entries, addressing a key challenge in clinical diagnostics.

Findings

ReMAC outperforms competing methods in tumor classification accuracy.

ReMAC maintains high performance with incomplete methylation data.

The method is validated on real clinical datasets.

Abstract

Accurate diagnosis of spitzoid tumors (ST) is critical to ensure a favorable prognosis and to avoid both under- and over-treatment. Epigenetic data, particularly DNA methylation, provide a valuable source of information for this task. However, prior studies assume complete data, an unrealistic setting as methylation profiles frequently contain missing entries due to limited coverage and experimental artifacts. Our work challenges these favorable scenarios and introduces ReMAC, an extension of ReMasker designed to tackle classification tasks on high-dimensional data under complete and incomplete regimes. Evaluation on real clinical data demonstrates that ReMAC achieves strong and robust performance compared to competing classification methods in the stratification of ST. Code is available: https://github.com/roshni-mahtani/ReMAC.