Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

At a glance: The ONWARDS insulin icodec trials

A round-up of the ONWARDS phase 3 clinical trials evaluating the novel weekly insulin icodec in people with diabetes.
ADVANCED SEARCH
Log in
Top
Diagnostic Pathology
Published in: Diagnostic Pathology 1/2020

01-12-2020 | Artificial Intelligence | Research

Accuracy and efficiency of an artificial intelligence tool when counting breast mitoses

Authors: Liron Pantanowitz, Douglas Hartman, Yan Qi, Eun Yoon Cho, Beomseok Suh, Kyunghyun Paeng, Rajiv Dhir, Pamela Michelow, Scott Hazelhurst, Sang Yong Song, Soo Youn Cho

Published in: Diagnostic Pathology | Issue 1/2020

Login to get access

Abstract

Background

The mitotic count in breast carcinoma is an important prognostic marker. Unfortunately substantial inter- and intra-laboratory variation exists when pathologists manually count mitotic figures. Artificial intelligence (AI) coupled with whole slide imaging offers a potential solution to this problem. The aim of this study was to accordingly critique an AI tool developed to quantify mitotic figures in whole slide images of invasive breast ductal carcinoma.

Methods

A representative H&E slide from 320 breast invasive ductal carcinoma cases was scanned at 40x magnification. Ten expert pathologists from two academic medical centers labeled mitotic figures in whole slide images to train and validate an AI algorithm to detect and count mitoses. Thereafter, 24 readers of varying expertise were asked to count mitotic figures with and without AI support in 140 high-power fields derived from a separate dataset. Their accuracy and efficiency of performing these tasks were calculated and statistical comparisons performed.

Results

For each experience level the accuracy, precision and sensitivity of counting mitoses by users improved with AI support. There were 21 readers (87.5%) that identified more mitoses using AI support and 13 reviewers (54.2%) that decreased the quantity of falsely flagged mitoses with AI. More time was spent on this task for most participants when not provided with AI support. AI assistance resulted in an overall time savings of 27.8%.

Conclusions

This study demonstrates that pathology end-users were more accurate and efficient at quantifying mitotic figures in digital images of invasive breast carcinoma with the aid of AI. Higher inter-pathologist agreement with AI assistance suggests that such algorithms can also help standardize practice. Not surprisingly, there is much enthusiasm in pathology regarding the prospect of using AI in routine practice to perform mundane tasks such as counting mitoses.
Appendix
Available only for authorised users
Literature
1.
Elston CW, Ellis IO. Pathological prognostic factors in breast cancer. I. the value of histological grade in breast cancer: experience from a large study with long-term follow-up. Histopathology. 1991;19(5):403–10.PubMed
2.
Chang JM, McCullough AE, Dueck AC. Back to basics: traditional Nottingham grade mitotic counts alone are significant in predicting survival in invasive breast carcinoma. Ann Surg Oncol. 2015;22(Suppl. 3):S509–15.PubMed
3.
Beelen K, Opdam M, Severson T, Koornstra R, Vincent A, Wesseling J, Sanders J, Vermorken J, van Diest P, Linn S. Mitotic count can predict tamoxifen benefit in postmenopausal breast cancer patients while Ki67 score cannot. BMC Cancer. 2018;18(1):761.PubMedPubMedCentral
4.
van Dooijeweert C, van Diest PJ, Willems SM, Kuijpers CCHJ, van der Wall E, Overbeek LIH, Deckers IAG. Significant inter- and intra-laboratory variation in grading of invasive breast cancer: a nationwide study of 33,043 patients in the Netherlands. Int J Cancer. 2020;146(3):769–80.PubMed
5.
Veta M. Breast Cancer Histopathology Image Analysis. The Netherlands: PhD Thesis, Utrecht University; 2014. Chapter 5:61–88.
6.
Facchetti F. A proposal for the adoption of a uniform metrical system for mitosis counting. Int J Surg Pathol. 2005;13(2):157–9.PubMed
7.
Yigit N, Gunal A, Kucukodaci Z, Karslioglu Y, Onguru O, Ozcan A. Are we counting mitoses correctly? Ann Diagn Pathol. 2013;17(6):536–9.PubMed
8.
Al-Janabi S, Huisman A, Willems SM, Van Diest PJ. Digital slide images for primary diagnostics in breast pathology: a feasibility study. Hum Pathol. 2012;43(12):2318–25.PubMed
9.
Al-Janabi S, van Slooten HJ, Visser M, van der Ploeg T, van Diest PJ, Jiwa M. Evaluation of mitotic activity index in breast cancer using whole slide digital images. PLoS One. 2013;8(12):e82576.PubMedPubMedCentral
10.
Wei BR, Halsey CH, Hoover SB, Puri M, Yang HH, Gallas BD, et al. Agreement in histological assessment of mitotic activity between microscopy and digital whole slide images informs conversion for clinical diagnosis. Acad Pathol. 2019;6:2374289519859841.PubMedPubMedCentral
11.
Hanna M, Xing J, Monaco SE, Hartman D, Pantanowitz L. Evaluation of diagnostic concordance between manual mitotic figure counting on glass slides versus whole slide images. J Pathol Inform. 2017;8:26.
12.
Malon C, Brachtel E, Cosatto E, Graf HP, Kurata A, Kuroda M, Meyer JS, Saito A, Wu S, Yagi Y. Mitotic figure recognition: agreement among pathologists and computerized detector. Anal Cell Pathol (Amst). 2012;35(2):97–100.
13.
Cireşan DC, Giusti A, Gambardella LM, Schmidhuber J. Mitosis detection in breast cancer histology images with deep neural networks. Med Image Comput Comput Assist Interv. 2013;16(Pt 2):411–8.PubMed
14.
Roux L, Racoceanu D, Loménie N, Kulikova M, Irshad H, Klossa J, Capron F, Genestie C, Le Naour G, Gurcan MN. Mitosis detection in breast cancer histological images an ICPR 2012 contest. J Pathol Inform. 2013;4:8.PubMedPubMedCentral
15.
Veta M, van Diest PJ, Willems SM, Wang H, Madabhushi A, Cruz-Roa A, et al. Assessment of algorithms for mitosis detection in breast cancer histopathology images. Med Image Anal. 2015;20(1):237–48.PubMed
16.
Racoceanu D, Capron F. Towards semantic-driven high-content image analysis: an operational instantiation for mitosis detection in digital histopathology. Comput Med Imaging Graph. 2015;42:2–15.PubMed
17.
Veta M, Heng YJ, Stathonikos N, Bejnordi BE, Beca F, Wollmann T, et al. Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge. Med Image Anal. 2019;54:111–21.PubMed
18.
Balkenhol MCA, Bult P, Tellez D, Vreuls W, Clahsen PC, Ciompi F, van der Laak JAWM. Deep learning and manual assessment show that the absolute mitotic count does not contain prognostic information in triple negative breast cancer. Cell Oncol (Dordr). 2019;42(4):555–69.
19.
Tizoosh HR, Pantanowitz L. Artificial intelligence and digital pathology: challenges and opportunities. J Pathol Inform. 2018;9:38.
20.
Metter DM, Colgan TJ, Leung ST, Timmons CF, Park JY. Trends in the US and Canadian pathologist workforces from 2007 to 2017. JAMA Netw Open. 2019;2(5):e194337.PubMedPubMedCentral
21.
Maddox TM, Rumsfeld JS, Payne PRO. Questions for artificial intelligence in health care. JAMA. 2019;321(1):31–2.PubMed
22.
Stevanovic L, Choschzick M, Moskovszky L, Varga Z. Variability of predicitve markers (hormone receptors, Her2, Ki67) and intrinsic subtypes of breast cancer in four consecutive years 2015-2018. J Cancer Res Clin Oncol. 2019;145:2983–94.PubMedPubMedCentral
23.
Paeng K, Hwang S, Park S, Kim M. A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology. In: Cardoso M, et al., editors. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. DLMIA 2017, ML-CDS 2017. Lecture notes in computer science, vol. 10553. Cham: Springer.
24.
Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems; 2015. p. 91–9.
25.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770–8.
26.
Tabata K, Uraoka N, Benhamida J, Hanna MG, Sirintrapan SJ, Gallas BD, et al. Validation of mitotic cell quantification via microscopy and multiple whole-slide scanners. Diagn Pathol. 2019;14(1):65.PubMedPubMedCentral
27.
Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17(1):195.PubMedPubMedCentral
28.
Barinov L, Jairaj A, Becker M, Seymour S, Lee E, Schram A, Lane E, Goldszal A, Quigley D, Paster L. Impact of data presentation on physician performance utilizing artificial intelligence-based computer-aided diagnosis and decision support systems. J Digit Imaging. 2019;32(3):408–16.PubMed
29.
Chen J-M, Li Y, Xu J, Gong L, Wang L-W, Liu W-L, Liu J. Computer-aided prognosis on breast cancer with hematoxylin and eosin histopathology images: a review. Tumor Biol. 2017;39(3):1010428317694550.
30.
Kaman EJ, Smeulders AW, Verbeek PW, Young IT, Baak JP. Image processing for mitoses in sections of breast cancer: a feasibility study. Cytometry. 1984;5(3):244–9.PubMed
31.
ten Kate TK, Beliën JA, Smeulders AW, Baak JP. Method for counting mitoses by image processing in Feulgen stained breast cancer sections. Cytometry. 1993;14(3):241–50.PubMed
32.
Wang H, Cruz-Roa A, Basavanhally A, Gilmore H, Shih N, Feldman M, Tomaszewski J, Gonzalez F, Madabhushi A. Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features. J Med Imaging (Bellingham). 2014;1(3):034003.
33.
Veta M, van Diest PJ, Jiwa M, Al-Janabi S, Pluim JP. Mitosis counting in Breast Cancer: object-level Interobserver agreement and comparison to an automatic method. PLoS One. 2016;11(8):e0161286.PubMedPubMedCentral
34.
Beevi KS, Nair MS, Bindu GR. A multi-classifier system for automatic mitosis detection in Breast histopathology images using deep belief networks. IEEE J Transl Eng Health Med. 2017;5:4300211.PubMed
35.
Nateghi R, Danyali H, Helfroush MS. Maximized inter-class weighted mean for fast and accurate mitosis cells detection in Breast Cancer histopathology images. J Med Syst. 2017;41(9):146.PubMed
36.
Li C, Wang X, Liu W, Latecki LJ. DeepMitosis: mitosis detection via deep detection, verification and segmentation networks. Med Image Anal. 2018;45:121–33.PubMed
37.
Puri M, Hoover SB, Hewitt SM, Wei BR, Adissu HA, Halsey CHC, et al. 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.PubMedPubMedCentral
38.
Hartman DJ, Van Der Laak JAWM, Gurcan MN, Pantanowitz L. Value of public challenges for the development of pathology deep learning algorithms. J Pathol Inform. 2020;11:7.PubMedPubMedCentral
39.
Wahab N, Khan A, Lee YS. Transfer learning based deep CNN for segmentation and detection of mitoses in breast cancer histopathological images. Microscopy (Oxf). 2019;68(3):216–33.
40.
Dessauvagie BF, Thomas C, Robinson C, Frost FA, Harvey J, Sterrett GF. Validation of mitosis counting by automated phosphohistone H3 (PHH3) digital image analysis in a breast carcinoma tissue microarray. Pathology. 2015;47(4):329–34.PubMed
41.
Focke CM, Finsterbusch K, Decker T, van Diest PJ. Performance of 4 Immunohistochemical Phosphohistone H3 antibodies for marking mitotic figures in Breast Cancer. Appl Immunohistochem Mol Morphol. 2018;26(1):20–6.PubMed
42.
Davidson TM, Rendi MH, Frederick PD, Onega T, Allison KH, Mercan E, et al. Breast Cancer prognostic factors in the digital era: comparison of Nottingham grade using Whle slide images and glass slides. J Pathol Inform. 2019;10:11.PubMedPubMedCentral
43.
Norgan AP, Suman VJ, Brown CL, Flotte TJ, Mounajjed T. Comparison of a medical-grade monitor vs commercial off-the-shelf display for mitotic figure enumeration and small object (helicobacter pylori) detection. Am J Clin Pathol. 2018;149(2):181–5.PubMed
44.
Bonert M, Tate AJ. Mitotic counts in breast cancer should be standardized with a uniform sample area. Biomed Eng Online. 2017;16:28.PubMedPubMedCentral
45.
Hanna M, Pantanowitz L. Redefining the high power field when counting mitoses using digital pathology. Mod Pathol. 2017;30(s2):396A.
Metadata
Title
Accuracy and efficiency of an artificial intelligence tool when counting breast mitoses
Authors
Liron Pantanowitz
Douglas Hartman
Yan Qi
Eun Yoon Cho
Beomseok Suh
Kyunghyun Paeng
Rajiv Dhir
Pamela Michelow
Scott Hazelhurst
Sang Yong Song
Soo Youn Cho
Publication date
01-12-2020
Publisher
BioMed Central
Published in
Diagnostic Pathology / Issue 1/2020
Electronic ISSN: 1746-1596
DOI
https://doi.org/10.1186/s13000-020-00995-z

Other articles of this Issue 1/2020

Diagnostic Pathology 1/2020 Go to the issue

Research

Circ_0003998 enhances doxorubicin resistance in hepatocellular carcinoma by regulating miR-218-5p/EIF5A2 pathway

Case Report

ALK-1-positive inflammatory myofibroblastic tumor of the thyroid complicated by Hashimoto’s thyroiditis: report of a rare case and a literature review

Research

Clinical study on primary screening of oral cancer and precancerous lesions by oral cytology

Research

Significance of druggable targets (PD-L1, KRAS, BRAF, PIK3CA, MSI, and HPV) on curatively resected esophageal squamous cell carcinoma

Review

Non coding RNAs as the critical factors in chemo resistance of bladder tumor cells

Case Report

Unilateral synchronous papillary renal neoplasm with reverse polarity and clear cell renal cell carcinoma: a case report with KRAS and PIK3CA mutations