Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910189167312896 |
|---|---|
| author | Ji, Xiaoyi Zelic, Renata Aspegren, Oskar Mulliqi, Nita Fiorentino, Michelangelo Giunchi, Francesca Molinaro, Luca Boman, Sol Erika Richiardi, Lorenzo Pettersson, Andreas Vincent, Per Henrik Eklund, Martin Akre, Olof Kartasalo, Kimmo |
| author_facet | Ji, Xiaoyi Zelic, Renata Aspegren, Oskar Mulliqi, Nita Fiorentino, Michelangelo Giunchi, Francesca Molinaro, Luca Boman, Sol Erika Richiardi, Lorenzo Pettersson, Andreas Vincent, Per Henrik Eklund, Martin Akre, Olof Kartasalo, Kimmo |
| contents | Artificial intelligence (AI) is becoming a clinical tool for prostate pathology, but generalization across variations in sample preparation and preservation over prolonged time periods remains poorly understood. We evaluated GleasonAI, an end-to-end attention-based multiple instance learning model, on an independent validation cohort comprising 10,366 biopsy cores from 1,028 patients across 14 Swedish regions, using archival diagnostic specimens from the ProMort cohorts collected between 1998-2015. The model achieved an overall quadratic-weighted kappa of 0.86 for core-level ISUP grading, comparable to several experienced pathologists and consistent across geographic regions. Notably, performance remained stable across the 17-year collection period, demonstrating robustness to time-related variation in archival material, a property not consistently observed with foundation model-based approaches, with exploratory analysis demonstrating a significant prognostic gradient across AI-assigned grade groups for prostate cancer-specific mortality. These findings support the generalizability of the AI grading model and demonstrate the potential of pathology archives as a large-scale resource for AI development, validation, and retrospective prognostic research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02614 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples Ji, Xiaoyi Zelic, Renata Aspegren, Oskar Mulliqi, Nita Fiorentino, Michelangelo Giunchi, Francesca Molinaro, Luca Boman, Sol Erika Richiardi, Lorenzo Pettersson, Andreas Vincent, Per Henrik Eklund, Martin Akre, Olof Kartasalo, Kimmo Computer Vision and Pattern Recognition Artificial Intelligence Artificial intelligence (AI) is becoming a clinical tool for prostate pathology, but generalization across variations in sample preparation and preservation over prolonged time periods remains poorly understood. We evaluated GleasonAI, an end-to-end attention-based multiple instance learning model, on an independent validation cohort comprising 10,366 biopsy cores from 1,028 patients across 14 Swedish regions, using archival diagnostic specimens from the ProMort cohorts collected between 1998-2015. The model achieved an overall quadratic-weighted kappa of 0.86 for core-level ISUP grading, comparable to several experienced pathologists and consistent across geographic regions. Notably, performance remained stable across the 17-year collection period, demonstrating robustness to time-related variation in archival material, a property not consistently observed with foundation model-based approaches, with exploratory analysis demonstrating a significant prognostic gradient across AI-assigned grade groups for prostate cancer-specific mortality. These findings support the generalizability of the AI grading model and demonstrate the potential of pathology archives as a large-scale resource for AI development, validation, and retrospective prognostic research. |
| title | Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.02614 |