Whole slide imaging-based prediction of TP53 mutations identifies an aggressive disease phenotype in prostate cancer
- Author
- Marija Pizurica (UGent) , Maarten Larmuseau (UGent) , Kim Van der Eecken, Louise de Schaetzen van Brienen (UGent) , Francisco Carrillo-Perez, Simon Isphording (UGent) , Nicolaas Lumen (UGent) , Jo Van Dorpe (UGent) , Piet Ost (UGent) , Sofie Verbeke (UGent) , Olivier Gevaert and Kathleen Marchal (UGent)
- Organization
- Project
-
- High resolution networks for the analysis of genetic rewiring in cancer
- Digital pathology as a proxy for molecular profiling of prostate tumors
- Forwarding precision oncology by integrating cohort-derived molecular and clinical information.
- ATHENA: Augmenting Therapeutic Effectiveness through Novel Analytics
- Deep learning models for predicting molecular tumor properties directly from Whole Slide images
- Leveraging comprehensive cancer systems genetic data to uncover the modus operandi of driver mutations
- A data-driven integrative framework for the identification of cancer driver pathways and their mode of action.
- Abstract
- Deep learning models predicting TP53 mutations from whole slide images of prostate cancer capture histologic phenotypes associated with stromal composition, lymph node metastasis, and biochemical recurrence, indicating their potential as in silico prognostic biomarkers. Abstract In prostate cancer, there is an urgent need for objective prognostic biomarkers that identify the metastatic potential of a tumor at an early stage. While recent analyses indicated TP53 mutations as candidate biomarkers, molecular profiling in a clinical setting is complicated by tumor heterogeneity. Deep learning models that predict the spatial presence of TP53 mutations in whole slide images (WSI) offer the potential to mitigate this issue. To assess the potential of WSIs as proxies for spatially resolved profiling and as biomarkers for aggressive disease, we developed TiDo, a deep learning model that achieves state-of-the-art performance in predicting TP53 mutations from WSIs of primary prostate tumors. In an independent multifocal cohort, the model showed successful generalization at both the patient and lesion level. Analysis of model predictions revealed that false positive (FP) predictions could at least partially be explained by TP53 deletions, suggesting that some FP carry an alteration that leads to the same histological phenotype as TP53 mutations. Comparative expression and histologic cell type analyses identified a TP53-like cellular phenotype triggered by expression of pathways affecting stromal composition. Together, these findings indicate that WSI-based models might not be able to perfectly predict the spatial presence of individual TP53 mutations but they have the potential to elucidate the prognosis of a tumor by depicting a downstream phenotype associated with aggressive disease biomarkers. Significance: Deep learning models predicting TP53 mutations from whole slide images of prostate cancer capture histologic phenotypes associated with stromal composition, lymph node metastasis, and biochemical recurrence, indicating their potential as in silico prognostic biomarkers.
Downloads
-
2970-2.pdf
- full text (Published version)
- |
- open access
- |
- |
- 12.49 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01HY0E616P1RXEX3G52ZDYY2CQ
- MLA
- Pizurica, Marija, et al. “Whole Slide Imaging-Based Prediction of TP53 Mutations Identifies an Aggressive Disease Phenotype in Prostate Cancer.” CANCER RESEARCH, vol. 83, no. 17, 2023, pp. 2970–84, doi:10.1158/0008-5472.CAN-22-3113.
- APA
- Pizurica, M., Larmuseau, M., Van der Eecken, K., de Schaetzen van Brienen, L., Carrillo-Perez, F., Isphording, S., … Marchal, K. (2023). Whole slide imaging-based prediction of TP53 mutations identifies an aggressive disease phenotype in prostate cancer. CANCER RESEARCH, 83(17), 2970–2984. https://doi.org/10.1158/0008-5472.CAN-22-3113
- Chicago author-date
- Pizurica, Marija, Maarten Larmuseau, Kim Van der Eecken, Louise de Schaetzen van Brienen, Francisco Carrillo-Perez, Simon Isphording, Nicolaas Lumen, et al. 2023. “Whole Slide Imaging-Based Prediction of TP53 Mutations Identifies an Aggressive Disease Phenotype in Prostate Cancer.” CANCER RESEARCH 83 (17): 2970–84. https://doi.org/10.1158/0008-5472.CAN-22-3113.
- Chicago author-date (all authors)
- Pizurica, Marija, Maarten Larmuseau, Kim Van der Eecken, Louise de Schaetzen van Brienen, Francisco Carrillo-Perez, Simon Isphording, Nicolaas Lumen, Jo Van Dorpe, Piet Ost, Sofie Verbeke, Olivier Gevaert, and Kathleen Marchal. 2023. “Whole Slide Imaging-Based Prediction of TP53 Mutations Identifies an Aggressive Disease Phenotype in Prostate Cancer.” CANCER RESEARCH 83 (17): 2970–2984. doi:10.1158/0008-5472.CAN-22-3113.
- Vancouver
- 1.Pizurica M, Larmuseau M, Van der Eecken K, de Schaetzen van Brienen L, Carrillo-Perez F, Isphording S, et al. Whole slide imaging-based prediction of TP53 mutations identifies an aggressive disease phenotype in prostate cancer. CANCER RESEARCH. 2023;83(17):2970–84.
- IEEE
- [1]M. Pizurica et al., “Whole slide imaging-based prediction of TP53 mutations identifies an aggressive disease phenotype in prostate cancer,” CANCER RESEARCH, vol. 83, no. 17, pp. 2970–2984, 2023.
@article{01HY0E616P1RXEX3G52ZDYY2CQ,
abstract = {{Deep learning models predicting TP53 mutations from whole slide images of prostate cancer capture histologic phenotypes associated with stromal composition, lymph node metastasis, and biochemical recurrence, indicating their potential as in silico prognostic biomarkers.
Abstract
In prostate cancer, there is an urgent need for objective prognostic biomarkers that identify the metastatic potential of a tumor at an early stage. While recent analyses indicated TP53 mutations as candidate biomarkers, molecular profiling in a clinical setting is complicated by tumor heterogeneity. Deep learning models that predict the spatial presence of TP53 mutations in whole slide images (WSI) offer the potential to mitigate this issue. To assess the potential of WSIs as proxies for spatially resolved profiling and as biomarkers for aggressive disease, we developed TiDo, a deep learning model that achieves state-of-the-art performance in predicting TP53 mutations from WSIs of primary prostate tumors. In an independent multifocal cohort, the model showed successful generalization at both the patient and lesion level. Analysis of model predictions revealed that false positive (FP) predictions could at least partially be explained by TP53 deletions, suggesting that some FP carry an alteration that leads to the same histological phenotype as TP53 mutations. Comparative expression and histologic cell type analyses identified a TP53-like cellular phenotype triggered by expression of pathways affecting stromal composition. Together, these findings indicate that WSI-based models might not be able to perfectly predict the spatial presence of individual TP53 mutations but they have the potential to elucidate the prognosis of a tumor by depicting a downstream phenotype associated with aggressive disease biomarkers.
Significance: Deep learning models predicting TP53 mutations from whole slide images of prostate cancer capture histologic phenotypes associated with stromal composition, lymph node metastasis, and biochemical recurrence, indicating their potential as in silico prognostic biomarkers.}},
author = {{Pizurica, Marija and Larmuseau, Maarten and Van der Eecken, Kim and de Schaetzen van Brienen, Louise and Carrillo-Perez, Francisco and Isphording, Simon and Lumen, Nicolaas and Van Dorpe, Jo and Ost, Piet and Verbeke, Sofie and Gevaert, Olivier and Marchal, Kathleen}},
issn = {{0008-5472}},
journal = {{CANCER RESEARCH}},
language = {{eng}},
number = {{17}},
pages = {{2970--2984}},
title = {{Whole slide imaging-based prediction of TP53 mutations identifies an aggressive disease phenotype in prostate cancer}},
url = {{http://doi.org/10.1158/0008-5472.CAN-22-3113}},
volume = {{83}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: