Journal of Pathology Informatics

ORIGINAL ARTICLE
Year
: 2019  |  Volume : 10  |  Issue : 1  |  Page : 4-

Automated computational detection, quantitation, and mapping of mitosis in whole-slide images for clinically actionable surgical pathology decision support


Munish Puri1, Shelley B Hoover1, Stephen M Hewitt2, Bih-Rong Wei3, Hibret Amare Adissu1, Charles H C Halsey1, Jessica Beck4, Charles Bradley5, Sarah D Cramer6, Amy C Durham5, D Glen Esplin7, Chad Frank8, L Tiffany Lyle9, Lawrence D McGill7, Melissa D Sánchez5, Paula A Schaffer8, Ryan P Traslavina10, Elizabeth Buza5, Howard H Yang1, Maxwell P Lee1, Jennifer E Dwyer1, R Mark Simpson1 
1 Laboratory of Cancer Biology and Genetics, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
2 Laboratory of Pathology, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
3 Laboratory of Cancer Biology and Genetics, Center for Cancer Research, National Cancer Institute; Frederick National Laboratory for Cancer Research, Leidos Biomedical Research, Inc., MD, USA
4 Laboratory of Human Carcinogenesis, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
5 Department of Pathobiology, University of Pennsylvania, Philadelphia, PA, USA
6 Cancer and Inflammation Program, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
7 Animal Reference Pathology, Salt Lake City, UT, USA
8 Department of Microbiology, Immunology, and Pathology, Veterinary Diagnostic Laboratory, Colorado State University, Fort Collins, CO, USA
9 Women's Malignancies Branch, Center for Cancer Research, National Cancer Institute, Bethesda, MD, USA
10 Section of Infections of the Nervous System, National Institute of Neurological Disorders and Stroke, Bethesda, MD, USA

Correspondence Address:
Dr. R Mark Simpson
Laboratory of Cancer Biology and Genetics, Center for Cancer Research, National Cancer Institute, 9000 Rockville Pike, Bethesda, MD 20892
USA

Background: Determining mitotic index by counting mitotic figures (MFs) microscopically from tumor areas with most abundant MF (hotspots [HS]) produces a prognostically useful tumor grading biomarker. However, interobserver concordance identifying MF and HS can be poorly reproducible. Immunolabeling MF, coupled with computer-automated counting by image analysis, can improve reproducibility. A computational system for obtaining MF values across digitized whole-slide images (WSIs) was sought that would minimize impact of artifacts, generate values clinically relatable to counting ten high-power microscopic fields of view typical in conventional microscopy, and that would reproducibly map HS topography. Materials and Methods: Relatively low-resolution WSI scans (0.50 μm/pixel) were imported in grid-tile format for feature-based MF segmentation, from naturally occurring canine melanomas providing a wide range of proliferative activity. MF feature extraction conformed to anti-phospho-histone H3-immunolabeled mitotic (M) phase cells. Computer vision image processing was established to subtract key artifacts, obtain MF counts, and employ rotationally invariant feature extraction to map MF topography. Results: The automated topometric HS (TMHS) algorithm identified mitotic HS and mapped select tissue tiles with greatest MF counts back onto WSI thumbnail images to plot HS topographically. Influence of dye, pigment, and extraneous structure artifacts was minimized. TMHS diagnostic decision support included image overlay graphics of HS topography, as well as a spreadsheet and plot of tile-based MF count values. TMHS performance was validated examining both mitotic HS counting and mapping functions. Significantly correlated TMHS MF mapping and metrics were demonstrated using repeat analysis with WSI in different orientation (R2 = 0.9916) and by agreement with a pathologist (R2 = 0.8605) as well as through assessment of counting function using an independently tuned object counting algorithm (OCA) (R2 = 0.9482). Limits of agreement analysis support method interchangeability. MF counts obtained led to accurate patient survival prediction in all (n = 30) except one case. By contrast, more variable performance was documented when several pathologists examined similar cases using microscopy (pair-wise correlations, rho range = 0.7597–0.9286). Conclusions: Automated TMHS MF segmentation and feature engineering performance were interchangeable with both observer and OCA in digital mode. Moreover, enhanced HS location accuracy and superior method reproducibility were achieved using the automated TMHS algorithm compared to the current practice employing clinical microscopy.


How to cite this article:
Puri M, Hoover SB, Hewitt SM, Wei BR, Adissu HA, Halsey CH, Beck J, Bradley C, Cramer SD, Durham AC, Esplin D G, Frank C, Lyle L T, McGill LD, Sánchez MD, Schaffer PA, Traslavina RP, Buza E, Yang HH, Lee MP, Dwyer JE, Simpson R M. Automated computational detection, quantitation, and mapping of mitosis in whole-slide images for clinically actionable surgical pathology decision support.J Pathol Inform 2019;10:4-4


How to cite this URL:
Puri M, Hoover SB, Hewitt SM, Wei BR, Adissu HA, Halsey CH, Beck J, Bradley C, Cramer SD, Durham AC, Esplin D G, Frank C, Lyle L T, McGill LD, Sánchez MD, Schaffer PA, Traslavina RP, Buza E, Yang HH, Lee MP, Dwyer JE, Simpson R M. Automated computational detection, quantitation, and mapping of mitosis in whole-slide images for clinically actionable surgical pathology decision support. J Pathol Inform [serial online] 2019 [cited 2019 Apr 23 ];10:4-4
Available from: http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2019;volume=10;issue=1;spage=4;epage=4;aulast=Puri;type=0