Detecting mitotic figures in breast cancer histopathology images

M. Veta, P. J. Van Diest, J. P W Pluim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The scoring of mitotic figures is an integrated part of the Bloom and Richardson system for grading of invasive breast cancer. It is routinely done by pathologists by visual examination of hematoxylin and eosin (H&E) stained histology slides on a standard light microscope. As such, it is a tedious process prone to inter- and intra-observer variability. In the last decade, whole-slide imaging (WSI) has emerged as the "digital age" alternative to the classical microscope. The increasing acceptance of WSI in pathology labs has brought an interest in the application of automatic image analysis methods, with the goal of reducing or completely eliminating manual input to the analysis. In this paper, we present a method for automatic detection of mitotic figures in breast cancer histopathology images. The proposed method consists of two main components: candidate extraction and candidate classification. Candidate objects are extracted by image segmentation with the Chan-Vese level set method. The candidate classification component aims at classifying all extracted candidates as being a mitotic figure or a false object. A statistical classifier is trained with a number of features that describe the size, shape, color and texture of the candidate objects. The proposed detection procedure was developed using a set of 18 whole-slide images, with over 900 manually annotated mitotic figures, split into independent training and testing sets. The overall true positive rate on the testing set was 59.5% while achieving 4.2 false positives per one high power field (HPF).

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8676
DOIs
StatePublished - 2013
Externally publishedYes
EventSPIE Medical Imaging Symposium 2013: Digital Pathology - Lake Buena Vista, FL, United States
Duration: Feb 10 2013Feb 11 2013

Other

OtherSPIE Medical Imaging Symposium 2013: Digital Pathology
CountryUnited States
CityLake Buena Vista, FL
Period2/10/132/11/13

Fingerprint

chutes
breast
Microscopes
cancer
Breast Neoplasms
Imaging techniques
Histology
Testing
Pathology
Hematoxylin
Eosine Yellowish-(YS)
Image segmentation
Image analysis
Classifiers
Textures
microscopes
Color
histology
scoring
pathology

Keywords

  • Breast cancer
  • Digital pathology
  • Image segmentation
  • Mitotic figures
  • Object detection
  • Whole-slide imaging

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Veta, M., Van Diest, P. J., & Pluim, J. P. W. (2013). Detecting mitotic figures in breast cancer histopathology images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 8676). [867607] https://doi.org/10.1117/12.2006626

Detecting mitotic figures in breast cancer histopathology images. / Veta, M.; Van Diest, P. J.; Pluim, J. P W.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8676 2013. 867607.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Veta, M, Van Diest, PJ & Pluim, JPW 2013, Detecting mitotic figures in breast cancer histopathology images. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 8676, 867607, SPIE Medical Imaging Symposium 2013: Digital Pathology, Lake Buena Vista, FL, United States, 2/10/13. https://doi.org/10.1117/12.2006626
Veta M, Van Diest PJ, Pluim JPW. Detecting mitotic figures in breast cancer histopathology images. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8676. 2013. 867607 https://doi.org/10.1117/12.2006626
Veta, M. ; Van Diest, P. J. ; Pluim, J. P W. / Detecting mitotic figures in breast cancer histopathology images. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 8676 2013.
@inproceedings{f1c5e5df867b43d39d98e4dd1c40d387,
title = "Detecting mitotic figures in breast cancer histopathology images",
abstract = "The scoring of mitotic figures is an integrated part of the Bloom and Richardson system for grading of invasive breast cancer. It is routinely done by pathologists by visual examination of hematoxylin and eosin (H&E) stained histology slides on a standard light microscope. As such, it is a tedious process prone to inter- and intra-observer variability. In the last decade, whole-slide imaging (WSI) has emerged as the {"}digital age{"} alternative to the classical microscope. The increasing acceptance of WSI in pathology labs has brought an interest in the application of automatic image analysis methods, with the goal of reducing or completely eliminating manual input to the analysis. In this paper, we present a method for automatic detection of mitotic figures in breast cancer histopathology images. The proposed method consists of two main components: candidate extraction and candidate classification. Candidate objects are extracted by image segmentation with the Chan-Vese level set method. The candidate classification component aims at classifying all extracted candidates as being a mitotic figure or a false object. A statistical classifier is trained with a number of features that describe the size, shape, color and texture of the candidate objects. The proposed detection procedure was developed using a set of 18 whole-slide images, with over 900 manually annotated mitotic figures, split into independent training and testing sets. The overall true positive rate on the testing set was 59.5{\%} while achieving 4.2 false positives per one high power field (HPF).",
keywords = "Breast cancer, Digital pathology, Image segmentation, Mitotic figures, Object detection, Whole-slide imaging",
author = "M. Veta and {Van Diest}, {P. J.} and Pluim, {J. P W}",
year = "2013",
doi = "10.1117/12.2006626",
language = "English (US)",
isbn = "9780819494504",
volume = "8676",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Detecting mitotic figures in breast cancer histopathology images

AU - Veta, M.

AU - Van Diest, P. J.

AU - Pluim, J. P W

PY - 2013

Y1 - 2013

N2 - The scoring of mitotic figures is an integrated part of the Bloom and Richardson system for grading of invasive breast cancer. It is routinely done by pathologists by visual examination of hematoxylin and eosin (H&E) stained histology slides on a standard light microscope. As such, it is a tedious process prone to inter- and intra-observer variability. In the last decade, whole-slide imaging (WSI) has emerged as the "digital age" alternative to the classical microscope. The increasing acceptance of WSI in pathology labs has brought an interest in the application of automatic image analysis methods, with the goal of reducing or completely eliminating manual input to the analysis. In this paper, we present a method for automatic detection of mitotic figures in breast cancer histopathology images. The proposed method consists of two main components: candidate extraction and candidate classification. Candidate objects are extracted by image segmentation with the Chan-Vese level set method. The candidate classification component aims at classifying all extracted candidates as being a mitotic figure or a false object. A statistical classifier is trained with a number of features that describe the size, shape, color and texture of the candidate objects. The proposed detection procedure was developed using a set of 18 whole-slide images, with over 900 manually annotated mitotic figures, split into independent training and testing sets. The overall true positive rate on the testing set was 59.5% while achieving 4.2 false positives per one high power field (HPF).

AB - The scoring of mitotic figures is an integrated part of the Bloom and Richardson system for grading of invasive breast cancer. It is routinely done by pathologists by visual examination of hematoxylin and eosin (H&E) stained histology slides on a standard light microscope. As such, it is a tedious process prone to inter- and intra-observer variability. In the last decade, whole-slide imaging (WSI) has emerged as the "digital age" alternative to the classical microscope. The increasing acceptance of WSI in pathology labs has brought an interest in the application of automatic image analysis methods, with the goal of reducing or completely eliminating manual input to the analysis. In this paper, we present a method for automatic detection of mitotic figures in breast cancer histopathology images. The proposed method consists of two main components: candidate extraction and candidate classification. Candidate objects are extracted by image segmentation with the Chan-Vese level set method. The candidate classification component aims at classifying all extracted candidates as being a mitotic figure or a false object. A statistical classifier is trained with a number of features that describe the size, shape, color and texture of the candidate objects. The proposed detection procedure was developed using a set of 18 whole-slide images, with over 900 manually annotated mitotic figures, split into independent training and testing sets. The overall true positive rate on the testing set was 59.5% while achieving 4.2 false positives per one high power field (HPF).

KW - Breast cancer

KW - Digital pathology

KW - Image segmentation

KW - Mitotic figures

KW - Object detection

KW - Whole-slide imaging

UR - http://www.scopus.com/inward/record.url?scp=84878620117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878620117&partnerID=8YFLogxK

U2 - 10.1117/12.2006626

DO - 10.1117/12.2006626

M3 - Conference contribution

SN - 9780819494504

VL - 8676

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -