Automatic Analysis of Nuclear Features Reveals a Non-tumoral Predictor of Tumor Grade in Bladder Cancer

Overview

Journal Diagn Pathol

Publisher Biomed Central

Specialty Pathology

Date 2024 Jun 8

PMID 38851736

Authors

Ibrahim Fahoum

Shlomo Tsuriel

Daniel Rattner

Ariel Greenberg

Asia Zubkov

Rabab Naamneh

Orli Greenberg

Valentina Zemser-Werner

Gilad Gitstein

Rami Hagege

Dov Hershkovitz

Affiliations

Soon will be listed here.

Abstract

Background & Objectives: Tumor grade determines prognosis in urothelial carcinoma. The classification of low and high grade is based on nuclear morphological features that include nuclear size, hyperchromasia and pleomorphism. These features are subjectively assessed by the pathologists and are not numerically measured, which leads to high rates of interobserver variability. The purpose of this study is to assess the value of a computer-based image analysis tool for identifying predictors of tumor grade in bladder cancer.

Methods: Four hundred images of urothelial tumors were graded by five pathologists and two expert genitourinary pathologists using a scale of 1 (lowest grade) to 5 (highest grade). A computer algorithm was used to automatically segment the nuclei and to provide morphometric parameters for each nucleus, which were used to establish the grading algorithm. Grading algorithm was compared to pathologists' agreement.

Results: Comparison of the grading scores of the five pathologists with the expert genitourinary pathologists score showed agreement rates between 88.5% and 97.5%.The agreement rate between the two expert genitourinary pathologists was 99.5%. The quantified algorithm based conventional parameters that determine the grade (nuclear size, pleomorphism and hyperchromasia) showed > 85% agreement with the expert genitourinary pathologists. Surprisingly, the parameter that was most associated with tumor grade was the 10th percentile of the nuclear area, and high grade was associated with lower 10th percentile nuclei, caused by the presence of more inflammatory cells in the high-grade tumors.

Conclusion: Quantitative nuclear features could be applied to determine urothelial carcinoma grade and explore new biologically explainable parameters with better correlation to grade than those currently used.

References

Babjuk M, Bohle A, Burger M, Capoun O, Cohen D, Comperat E . EAU Guidelines on Non-Muscle-invasive Urothelial Carcinoma of the Bladder: Update 2016. Eur Urol. 2016; 71(3):447-461. DOI: 10.1016/j.eururo.2016.05.041. View

Greenberg A, Samueli B, Farkash S, Zohar Y, Ish-Shalom S, Hagege R . Algorithm-assisted diagnosis of Hirschsprung's disease - evaluation of robustness and comparative image analysis on data from various labs and slide scanners. Diagn Pathol. 2024; 19(1):26. PMC: 10845737. DOI: 10.1186/s13000-024-01452-x. View

Downes M, Hartmann A, Shen S, Tsuzuki T, van Rhijn B, Bubendorf L . International Society of Urological Pathology (ISUP) Consensus Conference on Current Issues in Bladder Cancer. Working Group 1: Comparison of Bladder Cancer Grading System Performance. Am J Surg Pathol. 2023; 48(1):e1-e10. DOI: 10.1097/PAS.0000000000002059. View

Greenberg A, Aizic A, Zubkov A, Borsekofsky S, Hagege R, Hershkovitz D . Automatic ganglion cell detection for improving the efficiency and accuracy of hirschprung disease diagnosis. Sci Rep. 2021; 11(1):3306. PMC: 7870950. DOI: 10.1038/s41598-021-82869-y. View

Bera K, Schalper K, Rimm D, Velcheti V, Madabhushi A . Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology. Nat Rev Clin Oncol. 2019; 16(11):703-715. PMC: 6880861. DOI: 10.1038/s41571-019-0252-y. View

Bulten W, Balkenhol M, Belinga J, Brilhante A, Cakir A, Egevad L . Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists. Mod Pathol. 2020; 34(3):660-671. PMC: 7897578. DOI: 10.1038/s41379-020-0640-y. View

Bulten W, Pinckaers H, van Boven H, Vink R, de Bel T, van Ginneken B . Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study. Lancet Oncol. 2020; 21(2):233-241. DOI: 10.1016/S1470-2045(19)30739-9. View

Sylvester R, Rodriguez O, Hernandez V, Turturica D, Bauerova L, Bruins H . European Association of Urology (EAU) Prognostic Factor Risk Groups for Non-muscle-invasive Bladder Cancer (NMIBC) Incorporating the WHO 2004/2016 and WHO 1973 Classification Systems for Grade: An Update from the EAU NMIBC Guidelines Panel. Eur Urol. 2021; 79(4):480-488. DOI: 10.1016/j.eururo.2020.12.033. View

Wang B, Pan W, Yang M, Yang W, He W, Chen X . Programmed death ligand-1 is associated with tumor infiltrating lymphocytes and poorer survival in urothelial cell carcinoma of the bladder. Cancer Sci. 2018; 110(2):489-498. PMC: 6361576. DOI: 10.1111/cas.13887. View

10.

Lopez-Beltran A, Raspollini M, Hansel D, Comperat E, Williamson S, Liedberg F . International Society of Urological Pathology (ISUP) Consensus Conference on Current Issues in Bladder Cancer: Working Group 3: Subcategorization of T1 Bladder Cancer. Am J Surg Pathol. 2023; 48(1):e24-e31. DOI: 10.1097/PAS.0000000000002121. View

11.

Colla Ruvolo C, Wurnschimmel C, Wenzel M, Nocera L, Califano G, Tian Z . Comparison between 1973 and 2004/2016 WHO grading systems in patients with Ta urothelial carcinoma of urinary bladder. J Clin Pathol. 2021; 75(5):333-337. DOI: 10.1136/jclinpath-2021-207400. View

12.

Strom P, Kartasalo K, Olsson H, Solorzano L, Delahunt B, Berney D . Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020; 21(2):222-232. DOI: 10.1016/S1470-2045(19)30738-7. View

13.

Eich M, Chaux A, Guner G, Taheri D, Mendoza Rodriguez M, Pena M . Tumor immune microenvironment in non-muscle-invasive urothelial carcinoma of the bladder. Hum Pathol. 2019; 89:24-32. DOI: 10.1016/j.humpath.2019.04.003. View

14.

Greenberg A, Samueli B, Fahoum I, Farkash S, Greenberg O, Zemser-Werner V . Short Training Significantly Improves Ganglion Cell Detection Using an Algorithm-Assisted Approach. Arch Pathol Lab Med. 2022; 147(2):215-221. DOI: 10.5858/arpa.2021-0481-OA. View

15.

Epstein J, Amin M, Reuter V, Mostofi F . The World Health Organization/International Society of Urological Pathology consensus classification of urothelial (transitional cell) neoplasms of the urinary bladder. Bladder Consensus Conference Committee. Am J Surg Pathol. 1998; 22(12):1435-48. DOI: 10.1097/00000478-199812000-00001. View

16.

Niazi M, Parwani A, Gurcan M . Digital pathology and artificial intelligence. Lancet Oncol. 2019; 20(5):e253-e261. PMC: 8711251. DOI: 10.1016/S1470-2045(19)30154-8. View

17.

Siegel R, Miller K, Fuchs H, Jemal A . Cancer statistics, 2022. CA Cancer J Clin. 2022; 72(1):7-33. DOI: 10.3322/caac.21708. View

18.

Reis L, Taheri D, Chaux A, Guner G, Mendoza Rodriguez M, Bivalacqua T . Significance of a minor high-grade component in a low-grade noninvasive papillary urothelial carcinoma of bladder. Hum Pathol. 2015; 47(1):20-5. DOI: 10.1016/j.humpath.2015.09.007. View

19.

Kulkarni S, Seneviratne N, Baig M, Khan A . Artificial Intelligence in Medicine: Where Are We Now?. Acad Radiol. 2019; 27(1):62-70. DOI: 10.1016/j.acra.2019.10.001. View

20.

Perincheri S, Levi A, Celli R, Gershkovich P, Rimm D, Morrow J . An independent assessment of an artificial intelligence system for prostate cancer detection shows strong diagnostic accuracy. Mod Pathol. 2021; 34(8):1588-1595. PMC: 8295034. DOI: 10.1038/s41379-021-00794-x. View