MICCAI endorsed event Acute and chronic nonhealing wounds represent a heavy burden to healthcare systems, affecting millions of patients around the world [1]. Accurate measurement of wound areas is an important part of the diagnosis and care protocol since it is crucial to provide quantitative parameters to monitor the wound healing trajectory and to determine future interventions. Unfortunately, Manual measurement is time-consuming and often inaccurate which can cause a negative impact on patients. Lack of expertise can also lead to improper diagnosis of wound etiology and inaccurate wound measurement and documentation. Wound segmentation from images is a popular solution to these problems that not only automates the measurement of the wound area but also allows efficient data entry into the electronic medical record to enhance patient care. With the collaboration between the University of Wisconsin-Milwaukee and Advancing the Zenith of Healthcare Wound and Vascular Center, we build a dataset containing over 1000 foot ulcer images professionally labeled with binary masks. We provide this dataset to the challenge and aim at encouraging and supporting the development of new solutions for the automated and accurate segmentation of foot ulcers from natural images taken in common clinical settings. [1] C. Wang, D.M. Anisuzzaman, V. Williamson, M.K. Dhar, B. Rostami, J. Niezgoda, S. Gopalakrishnan, and Z. Yu, “Fully automatic wound segmentation with deep convolutional neural networks”, accepted for publication in Scientific Reports