Assessment of algorithms for mitosis detection in breast cancer histopathology images

[Display omitted] •We organized a challenge on mitosis detection in breast cancer histopathology images.•The challenge dataset consisted of 23 cases with more than 1000 annotated mitoses.•Eleven proposed algorithms were evaluated and compared.•The top scoring method had a performance comparable to e...

Full description

Saved in:
Bibliographic Details
Published in:Medical image analysis 2015-02, Vol.20 (1), p.237-248
Main Authors: Veta, Mitko, van Diest, Paul J., Willems, Stefan M., Wang, Haibo, Madabhushi, Anant, Cruz-Roa, Angel, Gonzalez, Fabio, Larsen, Anders B.L., Vestergaard, Jacob S., Dahl, Anders B., Cireşan, Dan C., Schmidhuber, Jürgen, Giusti, Alessandro, Gambardella, Luca M., Tek, F. Boray, Walter, Thomas, Wang, Ching-Wei, Kondo, Satoshi, Matuszewski, Bogdan J., Precioso, Frederic, Snell, Violet, Kittler, Josef, de Campos, Teofilo E., Khan, Adnan M., Rajpoot, Nasir M., Arkoumani, Evdokia, Lacle, Miangela M., Viergever, Max A., Pluim, Josien P.W.
Format: Article
Language:English
Subjects:
Algorithms
Breast cancer
Breast Neoplasms - pathology
Cancer grading
Digital pathology
Female
Humans
Life Sciences
Mitosis
Mitosis detection
Observer Variation
Quantitative Methods
Whole slide imaging
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] •We organized a challenge on mitosis detection in breast cancer histopathology images.•The challenge dataset consisted of 23 cases with more than 1000 annotated mitoses.•Eleven proposed algorithms were evaluated and compared.•The top scoring method had a performance comparable to expert observers. 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.
ISSN:1361-8415
1361-8423
DOI:10.1016/j.media.2014.11.010