Skip to main content

Her2 Scoring Contest

Home | Background | Contest Registration | Download| Submission | Results | Contest Rules| Forum | Contact

Her2

Welcome to the contest page of HER2 scoring in breast cancer histology images. This challenge will be held in conjunction with Nottingham Pathology 2016 (The Pathological Society of Great Britain & Ireland).

Overview

The aim of this challenge is to accelerate the development of state-of-the-art algorithms for automated scoring of HER2 in whole-slide images of breast cancer histology slides. The task of automated HER2 scoring has a significant clinical utility by reducing the subjectivity in the process of cancer diagnostics, and is expected to reduce the pathologist workload. For this contest, we will provide a dataset of nearly 100 whole-slide images (of the order of 100,000 x 80,000 pixels) linked with the ground-truth data in HER2 score and a %age score given by pathologists.

How to participate?

The registration is now open, interested teams can get registered. Please read the contest rules and an introduction to HER2 scoring before registering. Upon completion of the registration process, access to training dataset will be granted. In case of any queries or comments regarding this contest, please feel free to contact us.

The contest dataset is available for post contest submissions (link).

Publication

Selected participating teams will be invited to contribute in a special issue of a well-reputed journal to publish their scientific approach for solving this problem.

Contest Paper

Qaiser, T., Mukherjee, A., Munugoti, S.D., Tallam, V., Pitkäaho, T., Lehtimäki, T., Naughton, T., Berseth, M., Pedraza, A., Mukundan, R. and Smith, M.,.., Rajpoot, N., 2017. Her2 Challenge Contest: A Detailed Assessment of Automated Her2 Scoring Algorithms in Whole Slide Images of Breast Cancer Tissues. arXiv preprint arXiv:1705.08369.

Important Dates

  • 14 April 2016: Registration opens
  • 20 24 April 2016: Release of the training data
  • 17 May 2016: Release of the test data
  • 21 June 2016: Submission of results for the test data
  • 28 June 2016: Contest meeting (preliminary programme) to take place during Nottingham Pathology 2016

Statistics

  • Number of registered teams has grown to 104 as of May 23, 2016 (since Apr 14, 2016)


Organizers

tialab-logo

aidpath_logo.jpg

UOT-logo


uclm-logo

uhcw-logo