Crowdsourcing Games for Medical Applications

Supervision: Shadi Albarqouni

Abstract

Crowdsourcing has been widely used for annotation, i.e. collecting ground-truth, in the medical community. Many studies have shown that non-expert can perform as well as experts in crowdsourcing tasks if they were trained well, however, users/crowd are not motivated to complete the task to the very end. Recently, we showed that games can play a crucial role in motivating the crowd in the annotation task. In this work, we need to extend this to many different use cases.

Tasks:

• Extend the Playsourcing paper
• Publish it online for crowdsourcing
• Compare the results with few baselines

Requirements:

• Good understanding of statistics and machine learning methods.
• Very good programming skills in Unity3D, Java, and C++/Python

Location:

• FMI Building, Garching

Literature

2016
	S. Albarqouni, S. Matl, M. Baust, N. Navab, S. Demirci Playsourcing: A Novel Concept for Knowledge Creation in Biomedical Research Proceedings of MICCAI Workshop on Large-scale Annotation of Biomedical data and Expert Label Synthesis, Athens, Greece, October 2016 The first two authors contribute equally to this paper. (bib)
	S. Albarqouni, C. Baur, F. Achilles, V. Belagiannis, S. Demirci, N. Navab AggNet: Deep Learning from Crowds for Mitosis Detection in Breast Cancer Histology Images IEEE Transactions on Medical Imaging (TMI), Special Issue on Deep Learning, vol. 35, no. 5, pp. 1313 - 1321, 2016. The first two authors contribute equally to this paper. (bib)