Journal Article
. 2013 Jun; 4(Suppl):S1.
doi: 10.4103/2153-3539.109802.

HyMaP: A hybrid magnitude-phase approach to unsupervised segmentation of tumor areas in breast cancer histology images

Adnan M Khan 1 Hesham El-Daly  Emma Simmons  Nasir M Rajpoot  
  • PMID: 23766931
  •     9 References
  •     7 citations


Background: Segmentation of areas containing tumor cells in standard H&E histopathology images of breast (and several other tissues) is a key task for computer-assisted assessment and grading of histopathology slides. Good segmentation of tumor regions is also vital for automated scoring of immunohistochemical stained slides to restrict the scoring or analysis to areas containing tumor cells only and avoid potentially misleading results from analysis of stromal regions. Furthermore, detection of mitotic cells is critical for calculating key measures such as mitotic index; a key criteria for grading several types of cancers including breast cancer. We show that tumor segmentation can allow detection and quantification of mitotic cells from the standard H&E slides with a high degree of accuracy without need for special stains, in turn making the whole process more cost-effective.

Method: BASED ON THE TISSUE MORPHOLOGY, BREAST HISTOLOGY IMAGE CONTENTS CAN BE DIVIDED INTO FOUR REGIONS: Tumor, Hypocellular Stroma (HypoCS), Hypercellular Stroma (HyperCS), and tissue fat (Background). Background is removed during the preprocessing stage on the basis of color thresholding, while HypoCS and HyperCS regions are segmented by calculating features using magnitude and phase spectra in the frequency domain, respectively, and performing unsupervised segmentation on these features.

Results: All images in the database were hand segmented by two expert pathologists. The algorithms considered here are evaluated on three pixel-wise accuracy measures: precision, recall, and F1-Score. The segmentation results obtained by combining HypoCS and HyperCS yield high F1-Score of 0.86 and 0.89 with re-spect to the ground truth.

Conclusions: In this paper, we show that segmentation of breast histopathology image into hypocellular stroma and hypercellular stroma can be achieved using magnitude and phase spectra in the frequency domain. The segmentation leads to demarcation of tumor margins leading to improved accuracy of mitotic cell detection.

Keywords: Breast cancer grading; histopathology image analysis; magnitude and phase spectra of Gabor filters; mitotic cell detection; texture feature; tumor segmentation.

Computerized image-based detection and grading of lymphocytic infiltration in HER2+ breast cancer histopathology.
Ajay Nagesh Basavanhally, Shridar Ganesan, +5 authors, Anant Madabhushi.
IEEE Trans Biomed Eng, 2009 Nov 04; 57(3). PMID: 19884074
A gamma-gaussian mixture model for detection of mitotic cells in breast cancer histopathology images.
Adnan Mujahid Khan, Hesham Eldaly, Nasir M Rajpoot.
J Pathol Inform, 2013 Jul 17; 4. PMID: 23858386    Free PMC article.
The Nottingham Prognostic Index in primary breast cancer.
M H Galea, R W Blamey, C E Elston, I O Ellis.
Breast Cancer Res Treat, 1992 Jan 01; 22(3). PMID: 1391987
Highly Cited.
Automatic breast cancer grading of histopathological images.
Jean-Romain Dalle, Wee Kheng Leow, +2 authors, Thomas C Putti.
Annu Int Conf IEEE Eng Med Biol Soc, 2009 Jan 24; 2008. PMID: 19163350
Robust automated tumour segmentation on histological and immunohistochemical tissue images.
Ching-Wei Wang, Dean Fennell, +2 authors, Peter Hamilton.
PLoS One, 2011 Mar 10; 6(2). PMID: 21386898    Free PMC article.
Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters.
J G Daugman.
J Opt Soc Am A, 1985 Jul 01; 2(7). PMID: 4020513
Highly Cited.
Consensus embedding: theory, algorithms and application to segmentation and classification of biomedical data.
Satish Viswanath, Anant Madabhushi.
BMC Bioinformatics, 2012 Feb 10; 13. PMID: 22316103    Free PMC article.
Multi-resolution graph-based analysis of histopathological whole slide images: application to mitotic cell extraction and visualization.
Vincent Roullier, Olivier L├ęzoray, Vinh-Thong Ta, Abderrahim Elmoataz.
Comput Med Imaging Graph, 2011 May 24; 35(7-8). PMID: 21600733
Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy.
Hanchuan Peng, Fuhui Long, Chris Ding.
IEEE Trans Pattern Anal Mach Intell, 2005 Aug 27; 27(8). PMID: 16119262
Highly Cited.
A gamma-gaussian mixture model for detection of mitotic cells in breast cancer histopathology images.
Adnan Mujahid Khan, Hesham Eldaly, Nasir M Rajpoot.
J Pathol Inform, 2013 Jul 17; 4. PMID: 23858386    Free PMC article.
Computer-based image analysis in breast pathology.
Ziba Gandomkar, Patrick C Brennan, Claudia Mello-Thoms.
J Pathol Inform, 2017 Jan 10; 7. PMID: 28066683    Free PMC article.
Spatial Statistics for Segmenting Histological Structures in H&E Stained Tissue Images.
Luong Nguyen, Akif Burak Tosun, +3 authors, S Chakra Chennubhotla.
IEEE Trans Med Imaging, 2017 Mar 23; 36(7). PMID: 28328502    Free PMC article.
Unsupervised labeling of glomerular boundaries using Gabor filters and statistical testing in renal histology.
Brandon Ginley, John E Tomaszewski, +2 authors, Pinaki Sarder.
J Med Imaging (Bellingham), 2017 Mar 24; 4(2). PMID: 28331889    Free PMC article.
Study Processes and Applications of Ultrasomics in Precision Medicine.
Rui Yin, Meng Jiang, +5 authors, Christoph F Dietrich.
Front Oncol, 2020 Oct 06; 10. PMID: 33014858    Free PMC article.
A novel computational method for automatic segmentation, quantification and comparative analysis of immunohistochemically labeled tissue sections.
Elena Casiraghi, Veronica Huber, +6 authors, Barbara Vergani.
BMC Bioinformatics, 2018 Oct 28; 19(Suppl 10). PMID: 30367588    Free PMC article.
Applications of Topological Data Analysis in Oncology.
Anuraag Bukkuri, Noemi Andor, Isabel K Darcy.
Front Artif Intell, 2021 May 01; 4. PMID: 33928240    Free PMC article.