Surrogate Biomarker Prediction from Whole-Slide Images for Evaluating Overall Survival in Lung Adenocarcinoma

Overview

Journal Diagnostics (Basel)

Specialty Radiology

Date 2024 Mar 13

PMID 38472935

Authors

Pierre Murchan

Anne-Marie Baird

Pilib O Broin

Orla Sheils

Stephen P Finn

Affiliations

Soon will be listed here.

Abstract

Background: Recent advances in computational pathology have shown potential in predicting biomarkers from haematoxylin and eosin (H&E) whole-slide images (WSI). However, predicting the outcome directly from WSIs remains a substantial challenge. In this study, we aimed to investigate how gene expression, predicted from WSIs, could be used to evaluate overall survival (OS) in patients with lung adenocarcinoma (LUAD).

Methods: Differentially expressed genes (DEGs) were identified from The Cancer Genome Atlas (TCGA)-LUAD cohort. Cox regression analysis was performed on DEGs to identify the gene prognostics of OS. Attention-based multiple instance learning (AMIL) models were trained to predict the expression of identified prognostic genes from WSIs using the TCGA-LUAD dataset. Models were externally validated in the Clinical Proteomic Tumour Analysis Consortium (CPTAC)-LUAD dataset. The prognostic value of predicted gene expression values was then compared to the true gene expression measurements.

Results: The expression of 239 prognostic genes could be predicted in TCGA-LUAD with cross-validated Pearson's R > 0.4. Predicted gene expression demonstrated prognostic performance, attaining a cross-validated concordance index of up to 0.615 in TCGA-LUAD through Cox regression. In total, 36 genes had predicted expression in the external validation cohort that was prognostic of OS.

Conclusions: Gene expression predicted from WSIs is an effective method of evaluating OS in patients with LUAD. These results may open up new avenues of cost- and time-efficient prognosis assessment in LUAD treatment.

References

Wang F, Chen X, Yu X, Lin Q . Degradation of CCNB1 mediated by APC11 through UBA52 ubiquitination promotes cell cycle progression and proliferation of non-small cell lung cancer cells. Am J Transl Res. 2019; 11(11):7166-7185. PMC: 6895529. View

Eymin B, Gazzeri S . Role of cell cycle regulators in lung carcinogenesis. Cell Adh Migr. 2010; 4(1):114-23. PMC: 2852568. DOI: 10.4161/cam.4.1.10977. View

Schmauch B, Romagnoni A, Pronier E, Saillard C, Maille P, Calderaro J . A deep learning model to predict RNA-Seq expression of tumours from whole slide images. Nat Commun. 2020; 11(1):3877. PMC: 7400514. DOI: 10.1038/s41467-020-17678-4. View

Diamond S, Boyd S . CVXPY: A Python-Embedded Modeling Language for Convex Optimization. J Mach Learn Res. 2016; 17. PMC: 4927437. View

Enrico Bena C, Del Giudice M, Grob A, Gueudre T, Miotto M, Gialama D . Initial cell density encodes proliferative potential in cancer cell populations. Sci Rep. 2021; 11(1):6101. PMC: 7969775. DOI: 10.1038/s41598-021-85406-z. View

Virtanen P, Gommers R, Oliphant T, Haberland M, Reddy T, Cournapeau D . SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods. 2020; 17(3):261-272. PMC: 7056644. DOI: 10.1038/s41592-019-0686-2. View

Lipkova J, Chen R, Chen B, Lu M, Barbieri M, Shao D . Artificial intelligence for multimodal data integration in oncology. Cancer Cell. 2022; 40(10):1095-1110. PMC: 10655164. DOI: 10.1016/j.ccell.2022.09.012. View

El Nahhas O, Loeffler C, Carrero Z, van Treeck M, Kolbinger F, Hewitt K . Regression-based Deep-Learning predicts molecular biomarkers from pathology slides. Nat Commun. 2024; 15(1):1253. PMC: 10858881. DOI: 10.1038/s41467-024-45589-1. View

Petersen I, Kotb W, Friedrich K, Schluns K, Bocking A, Dietel M . Core classification of lung cancer: correlating nuclear size and mitoses with ploidy and clinicopathological parameters. Lung Cancer. 2009; 65(3):312-8. DOI: 10.1016/j.lungcan.2008.12.013. View

10.

Gillette M, Satpathy S, Cao S, Dhanasekaran S, Vasaikar S, Krug K . Proteogenomic Characterization Reveals Therapeutic Vulnerabilities in Lung Adenocarcinoma. Cell. 2020; 182(1):200-225.e35. PMC: 7373300. DOI: 10.1016/j.cell.2020.06.013. View

11.

Choi C, Seo K, Jang S, Oh Y, Shim T, Kim W . Chromosomal instability is a risk factor for poor prognosis of adenocarcinoma of the lung: Fluorescence in situ hybridization analysis of paraffin-embedded tissue from Korean patients. Lung Cancer. 2008; 64(1):66-70. DOI: 10.1016/j.lungcan.2008.07.016. View

12.

Wu T, Hu E, Xu S, Chen M, Guo P, Dai Z . clusterProfiler 4.0: A universal enrichment tool for interpreting omics data. Innovation (Camb). 2021; 2(3):100141. PMC: 8454663. DOI: 10.1016/j.xinn.2021.100141. View

13.

Szklarczyk D, Franceschini A, Wyder S, Forslund K, Heller D, Huerta-Cepas J . STRING v10: protein-protein interaction networks, integrated over the tree of life. Nucleic Acids Res. 2014; 43(Database issue):D447-52. PMC: 4383874. DOI: 10.1093/nar/gku1003. View

14.

Laleh N, Muti H, Loeffler C, Echle A, Saldanha O, Mahmood F . Benchmarking weakly-supervised deep learning pipelines for whole slide classification in computational pathology. Med Image Anal. 2022; 79:102474. DOI: 10.1016/j.media.2022.102474. View

15.

Chen R, Lu M, Williamson D, Chen T, Lipkova J, Noor Z . Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell. 2022; 40(8):865-878.e6. PMC: 10397370. DOI: 10.1016/j.ccell.2022.07.004. View

16.

Echle A, Grabsch H, Quirke P, van den Brandt P, West N, Hutchins G . Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning. Gastroenterology. 2020; 159(4):1406-1416.e11. PMC: 7578071. DOI: 10.1053/j.gastro.2020.06.021. View

17.

Laleh N, Ligero M, Perez-Lopez R, Kather J . Facts and Hopes on the Use of Artificial Intelligence for Predictive Immunotherapy Biomarkers in Cancer. Clin Cancer Res. 2022; 29(2):316-323. DOI: 10.1158/1078-0432.CCR-22-0390. View

18.

Sung H, Ferlay J, Siegel R, Laversanne M, Soerjomataram I, Jemal A . Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021; 71(3):209-249. DOI: 10.3322/caac.21660. View

19.

Shen W, Tong D, Chen J, Li H, Hu Z, Xu S . Silencing oncogene cell division cycle associated 5 induces apoptosis and G1 phase arrest of non-small cell lung cancer cells via p53-p21 signaling pathway. J Clin Lab Anal. 2022; 36(5):e24396. PMC: 9102649. DOI: 10.1002/jcla.24396. View

20.

Ritchie M, Phipson B, Wu D, Hu Y, Law C, Shi W . limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 2015; 43(7):e47. PMC: 4402510. DOI: 10.1093/nar/gkv007. View