Format

Send to

Choose Destination
Med Image Anal. 2015 Feb;20(1):237-48. doi: 10.1016/j.media.2014.11.010. Epub 2014 Nov 29.

Assessment of algorithms for mitosis detection in breast cancer histopathology images.

Author information

1
Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands. Electronic address: mitko@isi.uu.nl.
2
Pathology Department, University Medical Center Utrecht, Utrecht, The Netherlands.
3
BME Department, Case Western Reserve University, Cleveland, USA.
4
MindLab, National University of Colombia, Bogota, Colombia.
5
Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark.
6
IDSIA, USI-SUPSI, Lugano, Switzerland.
7
Department of Computer Engineering, Işık University, İstanbul, Turkey.
8
MINES ParisTech, PSL-Research University, CBIO-Centre for Computational Biology, France; Institut Curie, Paris, France; INSERM U900, Paris, France.
9
Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan.
10
Corporate R&D Center, Panasonic Healthcare Co., Ltd., Osaka, Japan; Current address: Konica Minolta, Inc., Japan.
11
School of Computing, Engineering and Physical Sciences, University of Central Lancashire, Preston, UK.
12
I3S, UMR 7271 UNS-CNRS, Nice Sophia-Antipolis University, Sophia Antipolis, France.
13
CVSSP, University of Surrey, Guildford, UK.
14
CVSSP, University of Surrey, Guildford, UK; Department of Computer Science and Sheffield Institute for Translational Medicine, University of Sheffield, UK.
15
Department of Computer Science, University of Warwick, UK.
16
Department of Computer Science, University of Warwick, UK; Department of Computer Science & Engineering, College of Engineering Qatar University, Doha, Qatar.
17
The Michael Letcher Department of Cellular Pathology, Princess Alexandra Hospital NHS Trust, Harlow, Essex, UK.
18
Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands.

Abstract

The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.

KEYWORDS:

Breast cancer; Cancer grading; Digital pathology; Mitosis detection; Whole slide imaging

PMID:
25547073
DOI:
10.1016/j.media.2014.11.010
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center