Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

E-Poster Display

286P - Artificial intelligence analysis of advanced breast cancer patients from a phase I trial of trastuzumab deruxtecan (T-DxD): HER2 and histopathology features as predictors of clinical benefit

Date

17 Sep 2020

Session

E-Poster Display

Topics

Immunotherapy

Tumour Site

Breast Cancer

Presenters

Shanu Modi

Citation

Annals of Oncology (2020) 31 (suppl_4): S348-S395. 10.1016/annonc/annonc268

Authors

S. Modi1, B. Glass2, A. Prakash2, A. Taylor-Weiner2, H. Elliott2, I. Wapinski2, M. Sugihara3, K. Saito4, J. Kaplan Kerner2, R. Phillips4, T. Shibutani5, K. Honda6, A. Khosla2, A.H. Beck2, J. Cogswell7

Author affiliations

  • 1 Medical Oncology, Memorial Sloan-Kettering Cancer Center, 10065 - New York/US
  • 2 Pathai, PathAI, 02215 - Boston/US
  • 3 Medical Oncology, Daiichi Sankyo, Co., Ltd., Tokyo/JP
  • 4 Translational Sciences, Daiichi Sankyo, Inc, Basking Ridge/US
  • 5 Biomarker Department, Daiichi Sankyo Co., Ltd., Tokyo/JP
  • 6 Oncology Clinical Development Department, Daiichi Sankyo Co., Ltd., Tokyo/JP
  • 7 Clinical Biomarkers, Translational Sciences, Daiichi Sankyo, Co., Ltd., Basking Ridge/US

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 286P

Background

HER2 levels that will meaningfully identify patients who benefit from the HER2 antibody drug conjugate T-DxD are under investigation. We developed a quantitative machine learning (ML) method to measure HER2 expression and evaluated our approach for predicting patient outcomes.

Methods

T-DXd demonstrated clinical activity in advanced-stage breast cancer (BC) patients in the DS8201-A-J101 trial. Digitized pathology images stained for HER2 from 154 patients were added to the PathAI research platform (PathAI; Boston, MA). The ML model was trained on 91,413 annotations created by 87 pathologists to identify HER2 positivity in BC cells, immune cells (IC, macrophages and lymphocytes), and tissue compartments in the HER2 stained BC samples. ML derived patient-level features were clustered and selected, with false discovery rate control, for predicting patient outcomes and HER2 status. Thresholds for feature-based patient selection were identified using cross validation optimizing for hazard ratio (HR) between patients with feature values above and below the threshold.

Results

149 patients with BC treated by T-DXd were included in this study. Patients selected by high manual HER2 ASCO/CAP achieved an ORR of 53% vs. 41% (p=0.29). AI feature measuring complete membranous HER2 positive BC cells with increased cytoplasmic HER2 staining identified more patients than manual HER2 (86% vs. 82%) and patients selected by this achieved an ORR of 55% vs. 24% (p<0.009). A novel biomarker measuring the ratio of IC density in the BC stroma vs. BC epithelium achieved an ORR of 57% vs. 38% (p<0.027). A composite biomarker using both features achieved an ORR of 59% vs. 37% (p<0.011). Similar results were found with PFS.

Conclusions

ML models identified tissue compartments and HER2 positivity in BC cells. ML-based feature combining IC density with complete membranous/increased cytoplasmic HER2 staining in BC cells achieved a comparable ORR (59% vs. 53%) to manual HER2 scoring. These results show the potential of ML models to select patients for HER2 therapy beyond manual HER2 scoring.

Clinical trial identification

NCT02564900.

Editorial acknowledgement

Legal entity responsible for the study

PathAI.

Funding

Daiichi Sankyo Inc.

Disclosure

S. Modi: Advisory/Consultancy, Speaker Bureau/Expert testimony, Research grant/Funding (institution): Daiichi Sankyo; Advisory/Consultancy, Speaker Bureau/Expert testimony, Research grant/Funding (institution): Genentech; Advisory/Consultancy, Speaker Bureau/Expert testimony, Research grant/Funding (institution): AstraZeneca; Advisory/Consultancy: Macrogenics; Speaker Bureau/Expert testimony, Research grant/Funding (institution): Seattle Genetics; Research grant/Funding (institution): Novartis. B. Glass: Shareholder/Stockholder/Stock options, Full/Part-time employment: PathAI. A. Prakash: Shareholder/Stockholder/Stock options, Full/Part-time employment: PathAI. A. Taylor-Weiner: Shareholder/Stockholder/Stock options, Full/Part-time employment: PathAI . H. Elliott: Shareholder/Stockholder/Stock options, Full/Part-time employment: PathAI. I. Wapinski: Shareholder/Stockholder/Stock options, Full/Part-time employment: PathAI. M. Sugihara: Shareholder/Stockholder/Stock options, Full/Part-time employment: Daiichi Sankyo, Co., Ltd.. K. Saito: Shareholder/Stockholder/Stock options, Full/Part-time employment: Daiichi Sankyo, Inc. J. Kaplan Kerner: Shareholder/Stockholder/Stock options, Full/Part-time employment: PathAI. R. Phillips: Shareholder/Stockholder/Stock options, Full/Part-time employment: Daiichi Sankyo, Inc. T. Shibutani: Shareholder/Stockholder/Stock options, Full/Part-time employment: Daiichi Sankyo, Co., Ltd.. K. Honda: Shareholder/Stockholder/Stock options, Full/Part-time employment: Daiichi Sankyo, Co., Ltd.. A. Khosla: Leadership role, Shareholder/Stockholder/Stock options, Full/Part-time employment, Officer/Board of Directors: PathAI. A.H. Beck: Leadership role, Shareholder/Stockholder/Stock options, Full/Part-time employment, Officer/Board of Directors: PathAI. J. Cogswell: Shareholder/Stockholder/Stock options, Full/Part-time employment: Daiichi Sankyo, Inc.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.