Contest Description

Breast cancer is by far the most frequent cancer found in women worldwide with an estimated 715,000 new cases diagnosed in more developed regions (26.5% of the total), and 577,000 in less developed regions (18.8%). Diagnosis of breast cancer at an early stage is critical in improving breast cancer prognosis.

CAD has resulted in more standardized grading practices which can be achieved by various diagnostic indicators. The earliest of them is the Bloom Richardson grading system . However, it has been shown that, there is variability among pathologists when using the BR grading system. To diagnose Breast Cancer, WHO has recommended an improved version of BR Grading system, the Nottingham grading system. All these diagnosis schemes require efficient segmentation of Cells. [1,2]

The aim of this contest is to find fast and efficient algorithms to segment cells in Breast Cancer Images. For a examples of segmented cells please see the sample segmentation in the dataset.

The data set for the contest can be downloaded from here.

  1. H. Bloom and W. Richardson. Histological grading and prognosis in breast cancer: a study of 1409 cases of which 359 have been followed for 15 years. British Journal of Cancer, 11(3):359, 1957.
  2. H. Cheng, X. Cai, X. Chen, L. Hu, and X. Lou.Computer-aided detection and classification of microcalcifications in mammograms: a survey. Pattern recognition, 36(12):2967–2991, 2003.