Journal Article
. 2014 May; 38(5):390-402.
doi: 10.1016/j.compmedimag.2014.04.003.

Multispectral band selection and spatial characterization: Application to mitosis detection in breast cancer histopathology

H Irshad 1 A Gouaillard 2 L Roux 3 D Racoceanu 4 
Affiliations
  • PMID: 24831181
  •     9 citations

Abstract

Breast cancer is the second most frequent cancer. The reference process for breast cancer prognosis is Nottingham grading system. According to this system, mitosis detection is one of the three important criteria required for grading process and quantifying the locality and prognosis of a tumor. Multispectral imaging, as relatively new to the field of histopathology, has the advantage, over traditional RGB imaging, to capture spectrally resolved information at specific frequencies, across the electromagnetic spectrum. This study aims at evaluating the accuracy of mitosis detection on histopathological multispectral images. The proposed framework includes: selection of spectral bands and focal planes, detection of candidate mitotic regions and computation of morphological and multispectral statistical features. A state-of-the-art of the methods for mitosis classification is also provided. This framework has been evaluated on MITOS multispectral dataset and achieved higher detection rate (67.35%) and F-Measure (63.74%) than the best MITOS contest results (Roux et al., 2013). Our results indicate that the selected multispectral bands have more discriminant information than a single spectral band or all spectral bands for mitotic figures, validating the interest of using multispectral images to improve the quality of the diagnostic in histopathology.

Keywords: Breast cancer; Classification; Features extraction; Histopathology; Multispectral images; Object detection; Spectral bands selection; Texture characterization.

Computational pathology to discriminate benign from malignant intraductal proliferations of the breast.
Fei Dong, Humayun Irshad, +11 authors, Andrew H Beck.
PLoS One, 2014 Dec 10; 9(12). PMID: 25490766    Free PMC article.
Hyperspectral interventional imaging for enhanced tissue visualization and discrimination combining band selection methods.
Dorra Nouri, Yves Lucas, Sylvie Treuillet.
Int J Comput Assist Radiol Surg, 2016 Jul 06; 11(12). PMID: 27378443
Review.
A Comparative Performance Analysis of Multispectral and RGB Imaging on HER2 Status Evaluation for the Prediction of Breast Cancer Prognosis.
Wenlou Liu, Linwei Wang, +6 authors, Yan Li.
Transl Oncol, 2016 Nov 12; 9(6). PMID: 27835789    Free PMC article.
Screening of the prognostic targets for breast cancer based co-expression modules analysis.
Huijuan Liu, Hui Ye.
Mol Med Rep, 2017 Jul 22; 16(4). PMID: 28731166    Free PMC article.
Maximized Inter-Class Weighted Mean for Fast and Accurate Mitosis Cells Detection in Breast Cancer Histopathology Images.
Ramin Nateghi, Habibollah Danyali, Mohammad Sadegh Helfroush.
J Med Syst, 2017 Aug 16; 41(9). PMID: 28808813
A Multi-Classifier System for Automatic Mitosis Detection in Breast Histopathology Images Using Deep Belief Networks.
K Sabeena Beevi, Madhu S Nair, G R Bindu.
IEEE J Transl Eng Health Med, 2017 Oct 12; 5. PMID: 29018640    Free PMC article.
Using spectral imaging for the analysis of abnormalities for colorectal cancer: When is it helpful?
Ruqayya Awan, Somaya Al-Maadeed, Rafif Al-Saady.
PLoS One, 2018 Jun 07; 13(6). PMID: 29874262    Free PMC article.
Hyperspectral imaging and deep learning for the detection of breast cancer cells in digitized histological images.
Samuel Ortega, Martin Halicek, +6 authors, Baowei Fei.
Proc SPIE Int Soc Opt Eng, 2020 Jun 13; 11320. PMID: 32528219    Free PMC article.
Hyperspectral and multispectral imaging in digital and computational pathology: a systematic review [Invited].
Samuel Ortega, Martin Halicek, +2 authors, Baowei Fei.
Biomed Opt Express, 2020 Jul 09; 11(6). PMID: 32637250    Free PMC article.
Review.