Deep Learning Predicts Chromosomal Instability from Histopathology Images

Overview

Journal iScience

Publisher Cell Press

Date 2021 May 17

PMID 33997679

Citations 25

Authors

Zhuoran Xu

Akanksha Verma

Uska Naveed

Samuel F Bakhoum

Pegah Khosravi

Olivier Elemento

Affiliations

Soon will be listed here.

Abstract

Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in the test set. Patch-level predictions of CIN status suggested intra-tumor heterogeneity within slides. Moreover, presence of patches with high predicted CIN score within an entire slide was more predictive of clinical outcome than the average CIN score of the slide, thus underscoring the clinical importance of intra-tumor heterogeneity.

Citing Articles

Targeting chromosomally unstable tumors with a selective KIF18A inhibitor.

Phillips A, Zhang R, Jaffe M, Schulz R, Carty M, Verma A Nat Commun. 2025; 16(1):307.

PMID: 39747049 PMC: 11697083. DOI: 10.1038/s41467-024-55300-z.

Integrating histopathology and transcriptomics for spatial tumor microenvironment profiling in a melanoma case study.

Lapuente-Santana O, Kant J, Eduati F NPJ Precis Oncol. 2024; 8(1):254.

PMID: 39511301 PMC: 11543820. DOI: 10.1038/s41698-024-00749-w.

Deep learning-based histological predictions of chromosomal instability in colorectal cancer.

Hyeon D, Kim Y, Hwang Y, Bae J, Kang G, Kim K Am J Cancer Res. 2024; 14(9):4495-4505.

PMID: 39417190 PMC: 11477831. DOI: 10.62347/JYND6488.

Integrating Machine Learning with Multi-Omics Technologies in Geroscience: Towards Personalized Medicine.

Theodorakis N, Feretzakis G, Tzelves L, Paxinou E, Hitas C, Vamvakou G J Pers Med. 2024; 14(9).

PMID: 39338186 PMC: 11433587. DOI: 10.3390/jpm14090931.

Detecting cell types and densities in the tumor microenvironment improves prognostic risk assessment for breast cancer.

Liu P, Zhang X, Wang W, Zhu Y, Xie Y, Tai Y Biomol Biomed. 2024; 25(1):106-114.

PMID: 39151110 PMC: 11647253. DOI: 10.17305/bb.2024.10974.

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

Birkbak N, Eklund A, Li Q, McClelland S, Endesfelder D, Tan P . Paradoxical relationship between chromosomal instability and survival outcome in cancer. Cancer Res. 2011; 71(10):3447-52. PMC: 3096721. DOI: 10.1158/0008-5472.CAN-10-3667. View

Zasadil L, Britigan E, Ryan S, Kaur C, Guckenberger D, Beebe D . High rates of chromosome missegregation suppress tumor progression but do not inhibit tumor initiation. Mol Biol Cell. 2016; 27(13):1981-9. PMC: 4927272. DOI: 10.1091/mbc.E15-10-0747. View

Khosravi P, Kazemi E, Imielinski M, Elemento O, Hajirasouliha I . Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images. EBioMedicine. 2018; 27:317-328. PMC: 5828543. DOI: 10.1016/j.ebiom.2017.12.026. View

Sipos O, Tovey H, Quist J, Haider S, Nowinski S, Gazinska P . Assessment of structural chromosomal instability phenotypes as biomarkers of carboplatin response in triple negative breast cancer: the TNT trial. Ann Oncol. 2020; 32(1):58-65. PMC: 7784666. DOI: 10.1016/j.annonc.2020.10.475. View

Srinidhi C, Ciga O, Martel A . Deep neural network models for computational histopathology: A survey. Med Image Anal. 2020; 67:101813. PMC: 7725956. DOI: 10.1016/j.media.2020.101813. View

Thompson L, McManus K . A novel multiplexed, image-based approach to detect phenotypes that underlie chromosome instability in human cells. PLoS One. 2015; 10(4):e0123200. PMC: 4404342. DOI: 10.1371/journal.pone.0123200. View

Carter S, Eklund A, Kohane I, Harris L, Szallasi Z . A signature of chromosomal instability inferred from gene expression profiles predicts clinical outcome in multiple human cancers. Nat Genet. 2006; 38(9):1043-8. DOI: 10.1038/ng1861. View

Kwei K, Kung Y, Salari K, Holcomb I, Pollack J . Genomic instability in breast cancer: pathogenesis and clinical implications. Mol Oncol. 2010; 4(3):255-66. PMC: 2904860. DOI: 10.1016/j.molonc.2010.04.001. View

10.

CAILLEAU R, Olive M, Cruciger Q . Long-term human breast carcinoma cell lines of metastatic origin: preliminary characterization. In Vitro. 1978; 14(11):911-5. DOI: 10.1007/BF02616120. View

11.

Tijhuis A, Johnson S, McClelland S . The emerging links between chromosomal instability (CIN), metastasis, inflammation and tumour immunity. Mol Cytogenet. 2019; 12:17. PMC: 6518824. DOI: 10.1186/s13039-019-0429-1. View

12.

Noorbakhsh J, Farahmand S, Foroughi Pour A, Namburi S, Caruana D, Rimm D . Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images. Nat Commun. 2020; 11(1):6367. PMC: 7733499. DOI: 10.1038/s41467-020-20030-5. View

13.

Liao H, Long Y, Han R, Wang W, Xu L, Liao M . Deep learning-based classification and mutation prediction from histopathological images of hepatocellular carcinoma. Clin Transl Med. 2020; 10(2):e102. PMC: 7403820. DOI: 10.1002/ctm2.102. View

14.

Zeimet A, Fiegl H, Goebel G, Kopp F, Allasia C, Reimer D . DNA ploidy, nuclear size, proliferation index and DNA-hypomethylation in ovarian cancer. Gynecol Oncol. 2011; 121(1):24-31. PMC: 3062717. DOI: 10.1016/j.ygyno.2010.12.332. View

15.

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

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.

Penner-Goeke S, Lichtensztejn Z, Neufeld M, Ali J, Altman A, Nachtigal M . The temporal dynamics of chromosome instability in ovarian cancer cell lines and primary patient samples. PLoS Genet. 2017; 13(4):e1006707. PMC: 5395197. DOI: 10.1371/journal.pgen.1006707. View

18.

Baergen A, Jeusset L, Lichtensztejn Z, McManus K . Diminished Condensin Gene Expression Drives Chromosome Instability That May Contribute to Colorectal Cancer Pathogenesis. Cancers (Basel). 2019; 11(8). PMC: 6721357. DOI: 10.3390/cancers11081066. View

19.

Smid M, Hoes M, Sieuwerts A, Sleijfer S, Zhang Y, Wang Y . Patterns and incidence of chromosomal instability and their prognostic relevance in breast cancer subtypes. Breast Cancer Res Treat. 2010; 128(1):23-30. DOI: 10.1007/s10549-010-1026-5. View

20.

Walther A, Houlston R, Tomlinson I . Association between chromosomal instability and prognosis in colorectal cancer: a meta-analysis. Gut. 2008; 57(7):941-50. DOI: 10.1136/gut.2007.135004. View