Quantitative Nuclear Grading: An Objective, Artificial Intelligence-Facilitated Foundation for Grading Noninvasive Papillary Urothelial Carcinoma

Ava Slotman; Minqi Xu; Katherine Lindale; Céline Hardy; Dan Winkowski; Regan Baird; Lina Chen; Priti Lal; Theodorus van der Kwast; Chelsea L Jackson; Robert J Gooding; David M Berman

doi:10.1016/j.labinv.2023.100155

Quantitative Nuclear Grading: An Objective, Artificial Intelligence-Facilitated Foundation for Grading Noninvasive Papillary Urothelial Carcinoma

Lab Invest. 2023 Jul;103(7):100155. doi: 10.1016/j.labinv.2023.100155. Epub 2023 Apr 13.

Authors

Affiliations

¹ Division of Cancer Biology and Genetics, Queen's University, Kingston, Ontario, Canada; Department of Pathology and Molecular Medicine, Queen's University, Kingston, Ontario, Canada.
² Department of Pathology and Molecular Medicine, Queen's University, Kingston, Ontario, Canada.
³ Division of Cancer Biology and Genetics, Queen's University, Kingston, Ontario, Canada; Department of Pathology and Molecular Medicine, Queen's University, Kingston, Ontario, Canada; Now with College of Medicine, Upstate Medical University, Syracuse, New York.
⁴ Visiopharm Corporation, Westminster, Colorado.
⁵ Department of Pathology and Molecular Medicine, Queen's University, Kingston, Ontario, Canada; Now with Laboratory Medicine and Molecular Diagnostics, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Ontario, Canada.
⁶ Department of Pathology and Laboratory Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania.
⁷ University Health Network, Princess Margaret Cancer Center, University of Toronto, Toronto, Ontario, Canada.
⁸ Division of Cancer Biology and Genetics, Queen's University, Kingston, Ontario, Canada; Department of Pathology and Molecular Medicine, Queen's University, Kingston, Ontario, Canada; Now with CancerCare Manitoba Research Institute, Winnipeg, Manitoba, Canada; Now with Department of Pathology, Rady Faculty of Health Science, University of Manitoba, Winnipeg, Manitoba, Canada.
⁹ Division of Cancer Biology and Genetics, Queen's University, Kingston, Ontario, Canada; Department of Physics, Engineering Physics, and Astronomy, Queen's University, Kingston, Ontario, Canada.
¹⁰ Division of Cancer Biology and Genetics, Queen's University, Kingston, Ontario, Canada; Department of Pathology and Molecular Medicine, Queen's University, Kingston, Ontario, Canada. Electronic address: bermand@queensu.ca.

PMID: 37059267
DOI: 10.1016/j.labinv.2023.100155

Abstract

In nonmuscle invasive bladder cancer, grade drives important treatment and management decisions. However, grading is complex and qualitative, and it has considerable interobserver and intraobserver variability. Previous literature showed that nuclear features quantitatively differ between bladder cancer grades, but these studies were limited in size and scope. In this study, we aimed to measure morphometric features relevant to grading criteria and build simplified classification models that objectively distinguish between the grades of noninvasive papillary urothelial carcinoma (NPUC). We analyzed 516 low-grade and 125 high-grade 1.0-mm diameter image samples from a cohort of 371 NPUC cases. All images underwent World Health Organization/International Society of Urological Pathology 2004 consensus pathologist grading at our institution that was subsequently validated by expert genitourinary pathologists from 2 additional institutions. Automated software segmented the tissue regions and measured the nuclear features of size, shape, and mitotic rate for millions of nuclei. Then, we analyzed differences between grades and constructed classification models, which had accuracies up to 88% and areas under the curve as high as 0.94. Variation in the nuclear area was the best univariate discriminator and was prioritized, along with the mitotic index, in the top-performing classifiers. Adding shape-related variables improved accuracy further. These findings indicate that nuclear morphometry and automated mitotic figure counts can be used to objectively differentiate between grades of NPUC. Future efforts will adapt the workflow to whole slides and tune grading thresholds to best reflect time to recurrence and progression. Defining these essential quantitative elements of grading has the potential to revolutionize pathologic assessment and provide a starting point from which to improve the prognostic utility of grade.

Keywords: artificial intelligence; digital pathology; grading; urothelial carcinoma.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Artificial Intelligence
Carcinoma, Papillary* / pathology
Carcinoma, Transitional Cell* / pathology
Humans
Neoplasm Grading
Prognosis
Urinary Bladder Neoplasms* / diagnosis
Urinary Bladder Neoplasms* / pathology