Table of Contents Author Guidelines Submit a Manuscript
Analytical Cellular Pathology
Volume 35 (2012), Issue 2, Pages 97-100

Mitotic Figure Recognition: Agreement among Pathologists and Computerized Detector

Christopher Malon,1 Elena Brachtel,2 Eric Cosatto,1 Hans Peter Graf,1 Atsushi Kurata,3 Masahiko Kuroda,3 John S. Meyer,4 Akira Saito,5 Shulin Wu,2 and Yukako Yagi2

1Department of Machine Learning, NEC Laboratories America, NJ, USA
2Department of Pathology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
3Department of Molecular Pathology, Tokyo Medical University, Tokyo, Japan
4Department of Pathology, St. Luke's Hospital (St. Louis), Chesterfield, MO, USA
5Innovative Service Solutions Division, NEC Corporation, Tokyo, Japan

Copyright © 2012 Hindawi Publishing Corporation and the authors. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Despite the prognostic importance of mitotic count as one of the components of the Bloom – Richardson grade [3], several studies ([2, 9, 10]) have found that pathologists’ agreement on the mitotic grade is fairly modest. Collecting a set of more than 4,200 candidate mitotic figures, we evaluate pathologists' agreement on individual figures, and train a computerized system for mitosis detection, comparing its performance to the classifications of three pathologists. The system’s and the pathologists’ classifications are based on evaluation of digital micrographs of hematoxylin and eosin stained breast tissue. On figures where the majority of pathologists agree on a classification, we compare the performance of the trained system to that of the individual pathologists. We find that the level of agreement of the pathologists ranges from slight to moderate, with strong biases, and that the system performs competitively in rating the ground truth set. This study is a step towards automatic mitosis count to accelerate a pathologist's work and improve reproducibility.