In:
Cancer Research, American Association for Cancer Research (AACR), Vol. 83, No. 8_Supplement ( 2023-04-14), p. LB171-LB171
Abstract:
In prostate cancer, there is an urgent need for objective prognostic biomarkers that identify a tumor’s metastatic potential at an early stage. While recent analyses indicated TP53 mutations as candidate biomarker, 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 (WSIs) offer the potential to mitigate this issue. To assess the potential of WSIs as proxy for spatially resolved profiling or as biomarker 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. On an independent multi-focal cohort, we could show successful generalization of the model, both at patient and lesion level. Hence, the model offers insight into which lesions on a WSI most likely contain a TP53 mutation. Analysis of model predictions revealed that false positive (FP) predictions could at least partially be explained by TP53 deletions. This suggests that some FP carry another alteration of which the effect converges in the same histological phenotype. Comparative expression analysis and histological cell type analysis identified such common phenotype (related to stromal composition) in both TP and FP predictions. This indicates that WSI-based models might not be able to perfectly predict the spatial presence of individual TP53 mutations. However, we show they have the potential of capturing a tumor’s aggressive potential by observing a downstream phenotype of the tumor cells and TME associated with a biomarker of aggressive disease (TP53). Citation Format: Marija Pizurica, 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, Kathleen Marchal. WSI based prediction of TP53 mutations identifies aggressive disease phenotype in prostate cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB171.
Type of Medium:
Online Resource
ISSN:
1538-7445
DOI:
10.1158/1538-7445.AM2023-LB171
Language:
English
Publisher:
American Association for Cancer Research (AACR)
Publication Date:
2023
detail.hit.zdb_id:
2036785-5
detail.hit.zdb_id:
1432-1
detail.hit.zdb_id:
410466-3
Permalink
