EUVIMEDEUVIMED entdecken
Crossref

Comparing Gleason pattern 4 measurement approaches on prostate biopsy using machine learning: a proof‐of‐principle study

Matei M Buzoianu iD, Rebecca Yu, Melissa Assel iD, Alican Bozkurt iD, Hamed Aghdam, Samson W Fine iD, Andrew J Vickers iD

Histopathology · 06.11.2026

DOI: 10.1111/his.70313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Histopathology, online erschienen am 06.11.2026. Verfasst von Matei M Buzoianu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York City, New York, USA. Die Arbeit nennt 15 Literaturangaben. Gefördert von: NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and objective There is increasing evidence that length of Gleason Pattern (GP) 4 on biopsy is a stronger predictor of oncological outcomes than Grade Group (GG) or %GP4. However, there is no consensus regarding the optimal method for quantifying GP4 length. We propose that machine learning (ML) can be used to quantify GP4 on digitized biopsy slides using multiple measurement approaches, allowing direct comparison of their prognostic performance. In this study, we attempt to demonstrate proof‐of‐principle for this approach.

Methods

We assembled a convenience sample of 726 patients with GG2‐4 prostate cancer on systematic biopsy who underwent radical prostatectomy between 2014 and 2023. ML algorithm (PAIGE‐AI) quantified GP4 using different approaches, varying by how gaps between cancer foci were handled. GP4 extent was assessed using linear and pixel‐based metrics. Discrimination of each quantification approach, along with GG, was assessed for adverse radical prostatectomy pathology and biochemical recurrence. Key findings and limitations We identified 15 different quantification approaches and observed differences between their discrimination. The highest discrimination was in the pixel‐counting method (AUC 0.648). GP4 quantification outperformed GG for predicting adverse pathology (AUC 0.627 versus 0.608). The amount of GP3 was non‐predictive once GP4 was known. These findings were consistent for BCR.

Conclusions

We were able to measure slides using 15 distinct measurement approaches and replicated prior findings using ML to quantify GP4. Our findings support the use of ML as a research tool to compare different GP4 quantification approaches. We intend to use our method on larger cohorts to determine which measurement approach best predicts oncological outcome.

Schlagwörter

Stichwörter der Autor:innen

Gleason pattern 4Gleason scoreGrade Groupbiopsymachine learningprostate cancer

Autor:innen und Institutionen

  • Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York City, New York, USA.
  • PAIGE-AI, New York City, New York, USA.
  • Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York City, New York, USA.

ORCID-Profile: Matei M Buzoianu, Melissa Assel, Alican Bozkurt, Samson W Fine, Andrew J Vickers

Förderung

  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Buzoianu, M. M., Yu, R., Assel, M., Bozkurt, A., Aghdam, H., Fine, S. W., & Vickers, A. J. (2026). Comparing Gleason pattern 4 measurement approaches on prostate biopsy using machine learning: a proof‐of‐principle study. Histopathology. https://doi.org/10.1111/his.70313

Vancouver

Buzoianu MM, Yu R, Assel M, Bozkurt A, Aghdam H, Fine SW, et al. Comparing Gleason pattern 4 measurement approaches on prostate biopsy using machine learning: a proof‐of‐principle study. Histopathology. 2026. doi:10.1111/his.70313

BibTeX
@article{Buzoianu2026,
  author = {Buzoianu, Matei M and Yu, Rebecca and Assel, Melissa and Bozkurt, Alican and Aghdam, Hamed and Fine, Samson W and Vickers, Andrew J},
  title = {Comparing Gleason pattern 4 measurement approaches on prostate biopsy using machine learning: a proof‐of‐principle study},
  journal = {Histopathology},
  year = {2026},
  doi = {10.1111/his.70313}
}
Kostenlos starten →