Automatic analysis of nuclear features reveals a non-tumoral predictor of tumor grade in bladder cancer.
Journal
Diagnostic pathology
ISSN: 1746-1596
Titre abrégé: Diagn Pathol
Pays: England
ID NLM: 101251558
Informations de publication
Date de publication:
08 Jun 2024
08 Jun 2024
Historique:
received:
07
01
2024
accepted:
27
05
2024
medline:
9
6
2024
pubmed:
9
6
2024
entrez:
8
6
2024
Statut:
epublish
Résumé
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. 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. 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. 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.
Sections du résumé
BACKGROUND & OBJECTIVES
OBJECTIVE
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
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
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
CONCLUSIONS
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.
Identifiants
pubmed: 38851736
doi: 10.1186/s13000-024-01501-5
pii: 10.1186/s13000-024-01501-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
75Informations de copyright
© 2024. The Author(s).
Références
Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin. 2022;72(1):7–33. https://doi.org/10.3322/caac.21708 .
doi: 10.3322/caac.21708
pubmed: 35020204
Sylvester RJ, Rodríguez O, Hernández V, et al. 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[Formula present. Eur Urol. 2021;79(4):480–8. https://doi.org/10.1016/j.eururo.2020.12.033 .
doi: 10.1016/j.eururo.2020.12.033
pubmed: 33419683
Bol MG, Baak JP, Buhr-Wildhagen S, Kruse AJ, Kjellevold KH, Janssen EA, Mestad OØP. Reproducibility and prognostic variability of grade and lamina propria invasion in stages Ta, T1 urothelial carcinoma of the bladder. J Urol. 2003;169(4):1291–4.
doi: 10.1097/01.ju.0000055471.78783.ae
pubmed: 12629345
Downes MR, Hartmann A, Shen S, et al. International Society of Urological Pathology (ISUP) Consensus Conference on Current issues in bladder Cancer. Working Group 1. Am J Surg Pathol. 2024;48(1):e1–10. https://doi.org/10.1097/PAS.0000000000002059 .
doi: 10.1097/PAS.0000000000002059
pubmed: 37246824
van der Kwast TH, Bubendorf L, Cheng L. International Society of Urological Pathology (ISUP) Consensus Conference on Current Issues in Bladder Cancer. American Journal of Surgical Pathology. 2024;48(1):1–3. https://doi.org/10.1097/PAS.0000000000002066 .
Paner P GP, Kamat A, Netto GJ, et al. International Society of Urological Pathology (ISUP) Consensus Conference on Current issues in bladder Cancer. Working Group 2. Am J Surg Pathol. 2024;48(1):e11–23. https://doi.org/10.1097/PAS.0000000000002077 .
doi: 10.1097/PAS.0000000000002077
pubmed: 37382156
Herr HW, Donat SM, Reuter VE. Management of low Grade Papillary bladder tumors. J Urol. 2007;178(4):1201–5. https://doi.org/10.1016/j.juro.2007.05.148 .
doi: 10.1016/j.juro.2007.05.148
pubmed: 17698090
Babjuk M, Böhle A, Burger M, et al. EAU guidelines on non–muscle-invasive Urothelial Carcinoma of the bladder: Update 2016. Eur Urol. 2017;71(3):447–61. https://doi.org/10.1016/j.eururo.2016.05.041 .
doi: 10.1016/j.eururo.2016.05.041
pubmed: 27324428
Epstein JI, Amin MB, Reuter VRMF, The World Health Organization/International. Society of Urological Pathology consensus classification of urothelial (transitional cell) neoplasms of the urinary bladder. Bladder Consensus Conference Committee. American Journal of Surgical Pathology. 1998;22(12):1435-48.
Gofrit ON, Pizov G, Shapiro A, et al. Mixed high and low grade bladder tumors - are they clinically high or low grade? J Urol. 2014;191(6):1693–6. https://doi.org/10.1016/j.juro.2013.11.056 .
doi: 10.1016/j.juro.2013.11.056
pubmed: 24316096
Reis LO, Taheri D, Chaux A, et al. Significance of a minor high-grade component in a low-grade noninvasive papillary urothelial carcinoma of bladder. Hum Pathol. 2016;47(1):20–5. https://doi.org/10.1016/j.humpath.2015.09.007 .
doi: 10.1016/j.humpath.2015.09.007
pubmed: 26520419
Collà Ruvolo C, Würnschimmel C, Wenzel M, et al. Comparison between 1973 and 2004/2016 WHO grading systems in patients with Ta Urothelial carcinoma of urinary bladder. J Clin Pathol. 2022;75(5):333–7. https://doi.org/10.1136/jclinpath-2021-207400 .
doi: 10.1136/jclinpath-2021-207400
pubmed: 33622681
Ardila D, Kiraly AP, Bharadwaj S, et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med. 2019;25(6):954–61. https://doi.org/10.1038/s41591-019-0447-x .
doi: 10.1038/s41591-019-0447-x
pubmed: 31110349
Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A. Diagnosis and Precision Oncology. Nat Rev Clin Oncol. 2019;16(11):703–15. https://doi.org/10.1038/s41571-019-0252-y.Artificial .
doi: 10.1038/s41571-019-0252-y.Artificial
pubmed: 31399699
pmcid: 6880861
Niazi MKK, Parwani AV, Gurcan MN. Digital pathology and artificial intelligence. Lancet Oncol. 2019;20(5):e253–61. https://doi.org/10.1016/S1470-2045(19)30154-8 .
doi: 10.1016/S1470-2045(19)30154-8
pubmed: 31044723
pmcid: 8711251
Kulkarni S, Seneviratne N, Baig MS, Khan AHA. Artificial Intelligence in Medicine: where are we now? Acad Radiol. 2020;27(1):62–70. https://doi.org/10.1016/j.acra.2019.10.001 .
doi: 10.1016/j.acra.2019.10.001
pubmed: 31636002
Bulten W, Pinckaers H, van Boven H, et al. Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study. Lancet Oncol. 2020;21(2):233–41. https://doi.org/10.1016/S1470-2045(19)30739-9 .
doi: 10.1016/S1470-2045(19)30739-9
pubmed: 31926805
Ström P, Kartasalo K, Olsson H, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020;21(2):222–32. https://doi.org/10.1016/S1470-2045(19)30738-7 .
doi: 10.1016/S1470-2045(19)30738-7
pubmed: 31926806
Bulten W, Kartasalo K, Chen PHC, et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat Med. 2022;28(1):154–63. https://doi.org/10.1038/s41591-021-01620-2 .
doi: 10.1038/s41591-021-01620-2
pubmed: 35027755
pmcid: 8799467
Perincheri S, Levi AW, Celli R, et al. An independent assessment of an artificial intelligence system for prostate cancer detection shows strong diagnostic accuracy. Mod Pathol. 2021;34(8):1588–95. https://doi.org/10.1038/s41379-021-00794-x .
doi: 10.1038/s41379-021-00794-x
pubmed: 33782551
pmcid: 8295034
Bulten W, Balkenhol M, Belinga JJA, et al. Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists. Mod Pathol. 2021;34(3):660–71. https://doi.org/10.1038/s41379-020-0640-y .
doi: 10.1038/s41379-020-0640-y
pubmed: 32759979
Greenberg A, Aizic A, Zubkov A, Borsekofsky S, Hagege RR, Hershkovitz D. Automatic ganglion cell detection for improving the efficiency and accuracy of hirschprung disease diagnosis. Sci Rep. 2021;11(1):3306. https://doi.org/10.1038/s41598-021-82869-y .
doi: 10.1038/s41598-021-82869-y
pubmed: 33558593
pmcid: 7870950
Greenberg A, Samueli B, Fahoum I et al. Short training significantly improves ganglion cell detection using an algorithm-assisted Approach. Arch Pathol Lab Med. Published online 2022. https://doi.org/10.5858/arpa.2021-0481-oa .
Greenberg A, Samueli B, Farkash S, et al. 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. https://doi.org/10.1186/s13000-024-01452-x .
doi: 10.1186/s13000-024-01452-x
pubmed: 38321431
pmcid: 10845737
Eich Mlisa, Chaux A, Guner G, et al. Tumor immune microenvironment in non – muscle- invasive urothelial carcinoma of the bladder ☆, ☆☆, ★. Hum Pathol. 2022;89(2019):24–32. https://doi.org/10.1016/j.humpath.2019.04.003 .
doi: 10.1016/j.humpath.2019.04.003
Wang B, Pan W, Yang M, et al. Programmed death ligand- 1 is associated with tumor infiltrating lymphocytes and poorer survival in urothelial cell carcinoma of the bladder. 2019;(July. 2018;489–98. https://doi.org/10.1111/cas.13887 .