ENHANCE (ENriching Health data by ANnotations of Crowd and Experts): A case study for skin lesion classification

1 code implementation • 27 Jul 2021 • Ralf Raumanns, Gerard Schouten, Max Joosten, Josien P. W. Pluim, Veronika Cheplygina

In this paper we first analyse the correlations between the annotations and the diagnostic label of the lesion, as well as study the agreement between different annotation sources.

Lesion Classification Multi-Task Learning +1

Risk of Training Diagnostic Algorithms on Data with Demographic Bias

no code implementations • 20 May 2020 • Samaneh Abbasi-Sureshjani, Ralf Raumanns, Britt E. J. Michels, Gerard Schouten, Veronika Cheplygina

Surprisingly, we found that papers focusing on diagnosis rarely describe the demographics of the datasets used, and the diagnosis is purely based on images.

Multi-task Ensembles with Crowdsourced Features Improve Skin Lesion Diagnosis

1 code implementation • 28 Apr 2020 • Ralf Raumanns, Elif K Contar, Gerard Schouten, Veronika Cheplygina

Machine learning has a recognised need for large amounts of annotated data.

Multi-Task Learning