Assessment of AURKA Expression and Prognosis Prediction in Lung Adenocarcinoma Using Machine Learning-based Pathomics Signature

Overview

Journal Heliyon

Specialty Social Sciences

Date 2024 Jul 18

PMID 39022022

Authors

Cuiqing Bai

Yan Sun

Xiuqin Zhang

Zhitong Zuo

Affiliations

Soon will be listed here.

Abstract

Objective: This study aimed to develop quantitative feature-based models from histopathological images to assess aurora kinase A (AURKA) expression and predict the prognosis of patients with lung adenocarcinoma (LUAD).

Methods: A dataset of patients with LUAD was derived from the cancer genome atlas (TCGA) with information on clinical characteristics, RNA sequencing and histopathological images. The TCGA-LUAD cohort was randomly divided into training (n = 229) and testing (n = 98) sets. We extracted quantitative image features from histopathological slides of patients with LUAD using computational approaches, constructed a predictive model for AURKA expression in the training set, and estimated their predictive performance in the test set. A Cox proportional hazards model was used to assess whether the pathomic scores (PS) generated by the model independently predicted LUAD survival.

Results: High AURKA expression was an independent risk factor for overall survival (OS) in patients with LUAD (hazard ratio = 1.816, 95 % confidence intervals = 1.257-2.623, P = 0.001). The model based on histopathological image features had significant predictive value for AURKA expression: the area under the curve of the receiver operating characteristic curve in the training set and validation set was 0.809 and 0.739, respectively. Decision curve analysis showed that the model had clinical utility. Patients with high PS and low PS had different survival rates (P = 0.019). Multivariate analysis suggested that PS was an independent prognostic factor for LUAD (hazard ratio = 1.615, 95 % confidence intervals = 1.071-2.438, P = 0.022).

Conclusion: Pathomics models based on machine learning can accurately predict AURKA expression and the PS generated by the model can predict LUAD prognosis.

References

Coudray N, Ocampo P, Sakellaropoulos T, Narula N, Snuderl M, Fenyo D . Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med. 2018; 24(10):1559-1567. PMC: 9847512. DOI: 10.1038/s41591-018-0177-5. View

Kong J, Cooper L, Wang F, Gao J, Teodoro G, Scarpace L . Machine-based morphologic analysis of glioblastoma using whole-slide pathology images uncovers clinically relevant molecular correlates. PLoS One. 2013; 8(11):e81049. PMC: 3827469. DOI: 10.1371/journal.pone.0081049. View

Yu K, Zhang C, Berry G, Altman R, Re C, Rubin D . Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features. Nat Commun. 2016; 7:12474. PMC: 4990706. DOI: 10.1038/ncomms12474. View

Sun C, Qu Z, Liu W, Qiu Z, Lu Y, Sun Z . The Synergistic Anti-colon Cancer Effect of Aurora A Inhibitors and AKT Inhibitors Through PI3K/AKT Pathway. Anticancer Agents Med Chem. 2022; 23(1):87-93. DOI: 10.2174/1871520622666220422133537. View

Zhang M, Liu X, Li H, Li R, Liu X, Qu Y . Elevated mRNA Levels of AURKA, CDC20 and TPX2 are associated with poor prognosis of smoking related lung adenocarcinoma using bioinformatics analysis. Int J Med Sci. 2018; 15(14):1676-1685. PMC: 6299412. DOI: 10.7150/ijms.28728. View

Moon W, Lee Y, Huang Y, Lee S, Bae M, Yi A . Computer-aided prediction of axillary lymph node status in breast cancer using tumor surrounding tissue features in ultrasound images. Comput Methods Programs Biomed. 2017; 146:143-150. DOI: 10.1016/j.cmpb.2017.06.001. View

Liu Y, Sun Z . Turning cold tumors into hot tumors by improving T-cell infiltration. Theranostics. 2021; 11(11):5365-5386. PMC: 8039952. DOI: 10.7150/thno.58390. View

Fridman W, Pages F, Sautes-Fridman C, Galon J . The immune contexture in human tumours: impact on clinical outcome. Nat Rev Cancer. 2012; 12(4):298-306. DOI: 10.1038/nrc3245. View

Hoque A, Carter J, Xia W, Hung M, Sahin A, Sen S . Loss of aurora A/STK15/BTAK overexpression correlates with transition of in situ to invasive ductal carcinoma of the breast. Cancer Epidemiol Biomarkers Prev. 2003; 12(12):1518-22. View

10.

Chen D, Fu M, Chi L, Lin L, Cheng J, Xue W . Prognostic and predictive value of a pathomics signature in gastric cancer. Nat Commun. 2022; 13(1):6903. PMC: 9653436. DOI: 10.1038/s41467-022-34703-w. View

11.

Li H, Chen L, Zeng H, Liao Q, Ji J, Ma X . Integrative Analysis of Histopathological Images and Genomic Data in Colon Adenocarcinoma. Front Oncol. 2021; 11:636451. PMC: 8504715. DOI: 10.3389/fonc.2021.636451. View

12.

Kanamori S, Kajihara I, Kanazawa-Yamada S, Otsuka-Maeda S, Ihn H . Expression of aurora kinase A expression in dermatofibrosarcoma protuberans. J Dermatol. 2018; 45(4):507-508. DOI: 10.1111/1346-8138.14235. View

13.

Lykkesfeldt A, Iversen B, Jensen M, Ejlertsen B, Giobbie-Hurder A, Reiter B . Aurora kinase A as a possible marker for endocrine resistance in early estrogen receptor positive breast cancer. Acta Oncol. 2017; 57(1):67-73. DOI: 10.1080/0284186X.2017.1404126. View

14.

Hipp J, Flotte T, Monaco J, Cheng J, Madabhushi A, Yagi Y . Computer aided diagnostic tools aim to empower rather than replace pathologists: Lessons learned from computational chess. J Pathol Inform. 2011; 2:25. PMC: 3132993. DOI: 10.4103/2153-3539.82050. View

15.

Madabhushi A, Lee G . Image analysis and machine learning in digital pathology: Challenges and opportunities. Med Image Anal. 2016; 33:170-175. PMC: 5556681. DOI: 10.1016/j.media.2016.06.037. View

16.

Remark R, Alifano M, Cremer I, Lupo A, Dieu-Nosjean M, Riquet M . Characteristics and clinical impacts of the immune environments in colorectal and renal cell carcinoma lung metastases: influence of tumor origin. Clin Cancer Res. 2013; 19(15):4079-91. DOI: 10.1158/1078-0432.CCR-12-3847. View

17.

Giraldo N, Becht E, Pages F, Skliris G, Verkarre V, Vano Y . Orchestration and Prognostic Significance of Immune Checkpoints in the Microenvironment of Primary and Metastatic Renal Cell Cancer. Clin Cancer Res. 2015; 21(13):3031-40. DOI: 10.1158/1078-0432.CCR-14-2926. View

18.

Vivian J, Rao A, Nothaft F, Ketchum C, Armstrong J, Novak A . Toil enables reproducible, open source, big biomedical data analyses. Nat Biotechnol. 2017; 35(4):314-316. PMC: 5546205. DOI: 10.1038/nbt.3772. View

19.

Qu W, Tian M, Lu H, Zhou Y, Liu W, Tang Z . Development of a deep pathomics score for predicting hepatocellular carcinoma recurrence after liver transplantation. Hepatol Int. 2023; 17(4):927-941. PMC: 10386986. DOI: 10.1007/s12072-023-10511-2. View

20.

Petitprez F, Fossati N, Vano Y, Freschi M, Becht E, Luciano R . PD-L1 Expression and CD8 T-cell Infiltrate are Associated with Clinical Progression in Patients with Node-positive Prostate Cancer. Eur Urol Focus. 2017; 5(2):192-196. DOI: 10.1016/j.euf.2017.05.013. View