Towards Digital Quantification of Ploidy from Pan-Cancer Digital Pathology Slides using Deep Learning DOI Creative Commons
Francisco Carrillo‐Pérez, Eric Cramer, Marija Pizurica

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 20, 2024

Abnormal DNA ploidy, found in numerous cancers, is increasingly being recognized as a contributor driving chromosomal instability, genome evolution, and the heterogeneity that fuels cancer cell progression. Furthermore, it has been linked with poor prognosis of patients. While next-generation sequencing can be used to approximate tumor high error rate for near-euploid states, cost time consuming, motivating alternative rapid quantification methods. We introduce PloiViT, transformer-based model ploidy outperforms traditional machine learning models, enabling cost-effective directly from pathology slides. trained PloiViT on dataset fifteen types The Cancer Genome Atlas validated its performance multiple independent cohorts. Additionally, we explored impact self-supervised feature extraction performance. using features, achieved lowest prediction cohorts, exhibiting better generalization capabilities. Our findings demonstrate predicts higher values aggressive groups patients specific mutations, validating potential complementary assessment data. To further promote use, release our models user-friendly inference application Python package easy adoption use.

Language: Английский

A deep-learning framework to predict cancer treatment response from histopathology images through imputed transcriptomics DOI
Danh-Tai Hoang, Gal Dinstag, Eldad D. Shulman

et al.

Nature Cancer, Journal Year: 2024, Volume and Issue: 5(9), P. 1305 - 1317

Published: July 3, 2024

Language: Английский

Citations

29
Towards Digital Quantification of Ploidy from Pan-Cancer Digital Pathology Slides using Deep Learning DOI Creative Commons
Francisco Carrillo‐Pérez, Eric Cramer, Marija Pizurica

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 20, 2024

Abnormal DNA ploidy, found in numerous cancers, is increasingly being recognized as a contributor driving chromosomal instability, genome evolution, and the heterogeneity that fuels cancer cell progression. Furthermore, it has been linked with poor prognosis of patients. While next-generation sequencing can be used to approximate tumor high error rate for near-euploid states, cost time consuming, motivating alternative rapid quantification methods. We introduce PloiViT, transformer-based model ploidy outperforms traditional machine learning models, enabling cost-effective directly from pathology slides. trained PloiViT on dataset fifteen types The Cancer Genome Atlas validated its performance multiple independent cohorts. Additionally, we explored impact self-supervised feature extraction performance. using features, achieved lowest prediction cohorts, exhibiting better generalization capabilities. Our findings demonstrate predicts higher values aggressive groups patients specific mutations, validating potential complementary assessment data. To further promote use, release our models user-friendly inference application Python package easy adoption use.

Language: Английский

Citations

0