Deep Learning-based Risk Stratification of Preoperative Breast Biopsies Using Digital Whole Slide Images

Overview

Journal Breast Cancer Res

Specialty Oncology

Date 2024 Jun 3

PMID 38831336

Authors

Constance Boissin

Yinxi Wang

Abhinav Sharma

Philippe Weitz

Emelie Karlsson

Stephanie Robertson

Johan Hartman

Mattias Rantalainen

Affiliations

Soon will be listed here.

Abstract

Background: Nottingham histological grade (NHG) is a well established prognostic factor in breast cancer histopathology but has a high inter-assessor variability with many tumours being classified as intermediate grade, NHG2. Here, we evaluate if DeepGrade, a previously developed model for risk stratification of resected tumour specimens, could be applied to risk-stratify tumour biopsy specimens.

Methods: A total of 11,955,755 tiles from 1169 whole slide images of preoperative biopsies from 896 patients diagnosed with breast cancer in Stockholm, Sweden, were included. DeepGrade, a deep convolutional neural network model, was applied for the prediction of low- and high-risk tumours. It was evaluated against clinically assigned grades NHG1 and NHG3 on the biopsy specimen but also against the grades assigned to the corresponding resection specimen using area under the operating curve (AUC). The prognostic value of the DeepGrade model in the biopsy setting was evaluated using time-to-event analysis.

Results: Based on preoperative biopsy images, the DeepGrade model predicted resected tumour cases of clinical grades NHG1 and NHG3 with an AUC of 0.908 (95% CI: 0.88; 0.93). Furthermore, out of the 432 resected clinically-assigned NHG2 tumours, 281 (65%) were classified as DeepGrade-low and 151 (35%) as DeepGrade-high. Using a multivariable Cox proportional hazards model the hazard ratio between DeepGrade low- and high-risk groups was estimated as 2.01 (95% CI: 1.06; 3.79).

Conclusions: DeepGrade provided prediction of tumour grades NHG1 and NHG3 on the resection specimen using only the biopsy specimen. The results demonstrate that the DeepGrade model can provide decision support to identify high-risk tumours based on preoperative biopsies, thus improving early treatment decisions.

Citing Articles

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.

References

Hameed Z, Zahia S, Garcia-Zapirain B, Aguirre J, Maria Vanegas A . Breast Cancer Histopathology Image Classification Using an Ensemble of Deep Learning Models. Sensors (Basel). 2020; 20(16). PMC: 7472736. DOI: 10.3390/s20164373. View

Couture H . Deep Learning-Based Prediction of Molecular Tumor Biomarkers from H&E: A Practical Review. J Pers Med. 2022; 12(12). PMC: 9784641. DOI: 10.3390/jpm12122022. View

Chen Y, Li H, Janowczyk A, Toro P, Corredor G, Whitney J . Computational pathology improves risk stratification of a multi-gene assay for early stage ER+ breast cancer. NPJ Breast Cancer. 2023; 9(1):40. PMC: 10192429. DOI: 10.1038/s41523-023-00545-y. View

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

Buono G, Gerratana L, Bulfoni M, Provinciali N, Basile D, Giuliano M . Circulating tumor DNA analysis in breast cancer: Is it ready for prime-time?. Cancer Treat Rev. 2019; 73:73-83. DOI: 10.1016/j.ctrv.2019.01.004. View

Cardoso F, Kyriakides S, Ohno S, Penault-Llorca F, Poortmans P, Rubio I . Early breast cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol. 2019; 30(10):1674. DOI: 10.1093/annonc/mdz189. View

Pantanowitz L, Quiroga-Garza G, Bien L, Heled R, Laifenfeld D, Linhart C . An artificial intelligence algorithm for prostate cancer diagnosis in whole slide images of core needle biopsies: a blinded clinical validation and deployment study. Lancet Digit Health. 2020; 2(8):e407-e416. DOI: 10.1016/S2589-7500(20)30159-X. View

Lorgis V, Algros M, Villanueva C, Chaigneau L, Thierry-Vuillemin A, Nguyen T . Discordance in early breast cancer for tumour grade, estrogen receptor, progesteron receptors and human epidermal receptor-2 status between core needle biopsy and surgical excisional primary tumour. Breast. 2011; 20(3):284-7. DOI: 10.1016/j.breast.2010.12.007. View

Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez J . pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics. 2011; 12:77. PMC: 3068975. DOI: 10.1186/1471-2105-12-77. View

10.

Couture H, Williams L, Geradts J, Nyante S, Butler E, Marron J . Image analysis with deep learning to predict breast cancer grade, ER status, histologic subtype, and intrinsic subtype. NPJ Breast Cancer. 2018; 4:30. PMC: 6120869. DOI: 10.1038/s41523-018-0079-1. View

11.

Jaroensri R, Wulczyn E, Hegde N, Brown T, Flament-Auvigne I, Tan F . Deep learning models for histologic grading of breast cancer and association with disease prognosis. NPJ Breast Cancer. 2022; 8(1):113. PMC: 9530224. DOI: 10.1038/s41523-022-00478-y. View

12.

Mantrala S, Ginter P, Mitkari A, Joshi S, Prabhala H, Ramachandra V . Concordance in Breast Cancer Grading by Artificial Intelligence on Whole Slide Images Compares With a Multi-Institutional Cohort of Breast Pathologists. Arch Pathol Lab Med. 2022; 146(11):1369-1377. DOI: 10.5858/arpa.2021-0299-OA. View

13.

Sharma A, Weitz P, Wang Y, Liu B, Vallon-Christersson J, Hartman J . Development and prognostic validation of a three-level NHG-like deep learning-based model for histological grading of breast cancer. Breast Cancer Res. 2024; 26(1):17. PMC: 10823657. DOI: 10.1186/s13058-024-01770-4. View

14.

Paik S, Shak S, Tang G, Kim C, Baker J, Cronin M . A multigene assay to predict recurrence of tamoxifen-treated, node-negative breast cancer. N Engl J Med. 2004; 351(27):2817-26. DOI: 10.1056/NEJMoa041588. View

15.

Strom P, Kartasalo K, Olsson H, Solorzano L, Delahunt B, Berney D . Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020; 21(2):222-232. DOI: 10.1016/S1470-2045(19)30738-7. View

16.

van Dooijeweert C, van Diest P, Ellis I . Grading of invasive breast carcinoma: the way forward. Virchows Arch. 2021; 480(1):33-43. PMC: 8983621. DOI: 10.1007/s00428-021-03141-2. View

17.

Rakha E, Ellis I . An overview of assessment of prognostic and predictive factors in breast cancer needle core biopsy specimens. J Clin Pathol. 2007; 60(12):1300-6. PMC: 2095575. DOI: 10.1136/jcp.2006.045377. View

18.

Chattopadhyay S, Dey A, Singh P, Oliva D, Cuevas E, Sarkar R . MTRRE-Net: A deep learning model for detection of breast cancer from histopathological images. Comput Biol Med. 2022; 150:106155. DOI: 10.1016/j.compbiomed.2022.106155. View

19.

Cahill R, Walsh D, Landers R, Watson R . Preoperative profiling of symptomatic breast cancer by diagnostic core biopsy. Ann Surg Oncol. 2005; 13(1):45-51. DOI: 10.1245/ASO.2006.03.047. View

20.

Desmedt C, Haibe-Kains B, Wirapati P, Buyse M, Larsimont D, Bontempi G . Biological processes associated with breast cancer clinical outcome depend on the molecular subtypes. Clin Cancer Res. 2008; 14(16):5158-65. DOI: 10.1158/1078-0432.CCR-07-4756. View