Prediction of Clinicopathological Features, Multi-omics Events and Prognosis Based on Digital Pathology and Deep Learning in HR/HER2 Breast Cancer

Overview

Journal J Thorac Dis

Publisher AME Publishing Company

Specialty Pulmonary Medicine

Date 2023 Jun 16

PMID 37324098

Authors

Jia Hu

Hong Lv

Shen Zhao

Cai-Jin Lin

Guan-Hua Su

Zhi-Ming Shao

Affiliations

Soon will be listed here.

Abstract

Background: Breast cancer has the highest incidence and mortality rates among women worldwide. Hormone receptor (HR)/human epidermal growth factor receptor 2 (HER2) breast cancer is the most common molecular subtype, accounting for 50-79% of breast cancers. Deep learning has been widely used in cancer image analysis, especially for predicting targets related to precise treatment and patient prognosis. However, studies focusing on therapeutic target and prognosis predicting in HR/HER2 breast cancer are lacking.

Methods: This study retrospectively collected hematoxylin and eosin (H&E)-stained slides of HR/HER2 breast cancer patients between January 2013 and December 2014 at Fudan University Shanghai Cancer Center (FUSCC) and scanned to generate whole-slide images (WSIs). Then, we built a deep-learning-based workflow to train and validate model to predict clinicopathological features, multi-omics molecular features and prognosis; the area under the curve (AUC) of the receiver operating characteristic (ROC) and the concordance index (C-index) of the test set were used to assess model effectiveness.

Results: A total of 421 HR/HER2 breast cancer patients were included in our study. Regarding clinicopathological features, grade III could be predicted with an AUC of 0.90 [95% confidence interval (CI): 0.84-0.97]. Regarding somatic mutations, TP53 and GATA3 mutation could be predicted with AUCs of 0.68 (95% CI: 0.56-0.81) and 0.68 (95% CI: 0.47-0.89), respectively. Regarding gene set enrichment analysis (GSEA) pathways, the G2-M checkpoint pathway was predicted with an AUC of 0.79 (95% CI: 0.69-0.90). Regarding markers of immunotherapy response, intratumoral tumor-infiltrating lymphocytes (iTILs), stromal tumor-infiltrating lymphocytes (sTILs), CD8A, and PDCD1 were predicted with AUCs of 0.78 (95% CI: 0.55-1.00), 0.76 (95% CI: 0.65-0.87), 0.71 (95% CI: 0.60-0.82), and 0.74 (95% CI: 0.63-0.85), respectively. In addition, we found that the integration of clinical prognostic variables and deep features of images can improve the stratification of patient prognosis.

Conclusions: Using a deep-learning-based workflow, we developed models to predict the clinicopathological features, multi-omics features and prognosis of patients with HR/HER2 breast cancer using pathological WSIs. This work may contribute to efficient patient stratification to promote the personalized management of HR/HER2 breast cancer.

Citing Articles

Artificial intelligence-based morphologic classification and molecular characterization of neuroblastic tumors from digital histopathology.

Ramesh S, Dyer E, Pomaville M, Doytcheva K, Dolezal J, Kochanny S NPJ Precis Oncol. 2024; 8(1):255.

PMID: 39511421 PMC: 11544094. DOI: 10.1038/s41698-024-00745-0.

Innovations in Artificial Intelligence-Driven Breast Cancer Survival Prediction: A Narrative Review.

Mooghal M, Nasir S, Arif A, Khan W, Rashid Y, Vohra L Cancer Inform. 2024; 23:11769351241272389.

PMID: 39483314 PMC: 11526191. DOI: 10.1177/11769351241272389.

Deep learning application in prediction of cancer molecular alterations based on pathological images: a bibliographic analysis via CiteSpace.

Xiaojian Y, Zhanbo Q, Jian C, Zefeng W, Jian L, Jin L J Cancer Res Clin Oncol. 2024; 150(10):467.

PMID: 39422817 PMC: 11489169. DOI: 10.1007/s00432-024-05992-z.

Artificial intelligence-based morphologic classification and molecular characterization of neuroblastic tumors from digital histopathology.

Applebaum M, Ramesh S, Dyer E, Pomaville M, Doytcheva K, Dolezal J Res Sq. 2024; .

PMID: 38883758 PMC: 11177984. DOI: 10.21203/rs.3.rs-4396782/v1.

References

Courtiol P, Maussion C, Moarii M, Pronier E, Pilcer S, Sefta M . Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat Med. 2019; 25(10):1519-1525. DOI: 10.1038/s41591-019-0583-3. View

Bejnordi B, Veta M, van Diest P, van Ginneken B, Karssemeijer N, Litjens G . Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA. 2017; 318(22):2199-2210. PMC: 5820737. DOI: 10.1001/jama.2017.14585. View

Liberzon A, Birger C, Thorvaldsdottir H, Ghandi M, Mesirov J, Tamayo P . The Molecular Signatures Database (MSigDB) hallmark gene set collection. Cell Syst. 2016; 1(6):417-425. PMC: 4707969. DOI: 10.1016/j.cels.2015.12.004. View

Wang Y, Acs B, Robertson S, Liu B, Solorzano L, Wahlby C . Improved breast cancer histological grading using deep learning. Ann Oncol. 2021; 33(1):89-98. DOI: 10.1016/j.annonc.2021.09.007. View

Cuyun Carter G, Mohanty M, Stenger K, Morato Guimaraes C, Singuru S, Basa P . Prognostic Factors in Hormone Receptor-Positive/Human Epidermal Growth Factor Receptor 2-Negative (HR+/HER2-) Advanced Breast Cancer: A Systematic Literature Review. Cancer Manag Res. 2021; 13:6537-6566. PMC: 8384149. DOI: 10.2147/CMAR.S300869. View

Oner G, Altintas S, Canturk Z, Tjalma W, Van Berckelaer C, Broeckx G . The immunologic aspects in hormone receptor positive breast cancer. Cancer Treat Res Commun. 2020; 25:100207. DOI: 10.1016/j.ctarc.2020.100207. View

Hashmi A, Hashmi K, Irfan M, Khan S, Edhi M, Ali J . Ki67 index in intrinsic breast cancer subtypes and its association with prognostic parameters. BMC Res Notes. 2019; 12(1):605. PMC: 6755684. DOI: 10.1186/s13104-019-4653-x. View

Miao Y, Wang J, Li Q, Quan W, Wang Y, Li C . Prognostic value and immunological role of PDCD1 gene in pan-cancer. Int Immunopharmacol. 2020; 89(Pt B):107080. DOI: 10.1016/j.intimp.2020.107080. View

Salgado R, Denkert C, Demaria S, Sirtaine N, Klauschen F, Pruneri G . The evaluation of tumor-infiltrating lymphocytes (TILs) in breast cancer: recommendations by an International TILs Working Group 2014. Ann Oncol. 2014; 26(2):259-71. PMC: 6267863. DOI: 10.1093/annonc/mdu450. View

10.

Emens L . Breast Cancer Immunotherapy: Facts and Hopes. Clin Cancer Res. 2017; 24(3):511-520. PMC: 5796849. DOI: 10.1158/1078-0432.CCR-16-3001. View

11.

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

12.

Schmid P, Adams S, Rugo H, Schneeweiss A, Barrios C, Iwata H . Atezolizumab and Nab-Paclitaxel in Advanced Triple-Negative Breast Cancer. N Engl J Med. 2018; 379(22):2108-2121. DOI: 10.1056/NEJMoa1809615. View

13.

Emens L, Molinero L, Loi S, Rugo H, Schneeweiss A, Dieras V . Atezolizumab and nab-Paclitaxel in Advanced Triple-Negative Breast Cancer: Biomarker Evaluation of the IMpassion130 Study. J Natl Cancer Inst. 2021; 113(8):1005-1016. PMC: 8328980. DOI: 10.1093/jnci/djab004. View

14.

Kather J, Heij L, Grabsch H, Loeffler C, Echle A, Muti H . Pan-cancer image-based detection of clinically actionable genetic alterations. Nat Cancer. 2021; 1(8):789-799. PMC: 7610412. DOI: 10.1038/s43018-020-0087-6. View

15.

Viale G, Regan M, Mastropasqua M, Maffini F, Maiorano E, Colleoni M . Predictive value of tumor Ki-67 expression in two randomized trials of adjuvant chemoendocrine therapy for node-negative breast cancer. J Natl Cancer Inst. 2008; 100(3):207-12. DOI: 10.1093/jnci/djm289. View

16.

Kather J, Pearson A, Halama N, Jager D, Krause J, Loosen S . Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med. 2019; 25(7):1054-1056. PMC: 7423299. DOI: 10.1038/s41591-019-0462-y. View

17.

Zhao S, Yan C, Lv H, Yang J, You C, Li Z . Deep learning framework for comprehensive molecular and prognostic stratifications of triple-negative breast cancer. Fundam Res. 2024; 4(3):678-689. PMC: 11197495. DOI: 10.1016/j.fmre.2022.06.008. View

18.

Byrne A, Savas P, Sant S, Li R, Virassamy B, Luen S . Tissue-resident memory T cells in breast cancer control and immunotherapy responses. Nat Rev Clin Oncol. 2020; 17(6):341-348. DOI: 10.1038/s41571-020-0333-y. View

19.

Matsuo K, Purushotham S, Jiang B, Mandelbaum R, Takiuchi T, Liu Y . Survival outcome prediction in cervical cancer: Cox models vs deep-learning model. Am J Obstet Gynecol. 2018; 220(4):381.e1-381.e14. PMC: 7526040. DOI: 10.1016/j.ajog.2018.12.030. View

20.

Naik N, Madani A, Esteva A, Keskar N, Press M, Ruderman D . Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains. Nat Commun. 2020; 11(1):5727. PMC: 7670411. DOI: 10.1038/s41467-020-19334-3. View