Deep Learning Allows Assessment of Risk of Metastatic Relapse from Invasive Breast Cancer Histological Slides
Preprint
Abstract
Background Correctly classifying early estrogen receptor-positive and HER2-negative (ER+/HER2) breast cancer (EBC) cases allows to propose an adapted adjuvant systemic treatment strategy. We developed a new AI-based tool to assess the risk of distant relapse at 5 years for ER+/HER2− EBC patients from pathological slides. Patients and Methods The discovery dataset (GrandTMA) included 1429 ER+/HER2− EBC patients, with long-term follow-up and an available hematoxylin-eosin and saffron (HES) whole slide image (WSI). A Deep Learning (DL) network was trained to predict metastasis free survival (MFS) at five years, based on the HES WSI only (termed RlapsRisk). A combined score was then built using RlapsRisk and well established prognostic factors. A threshold corresponding to a probability of MFS event of 5% at 5 years was applied to dichotomize patients into low or high-risk groups. The external validation, as well as assessment of the additional prognosis value of the DL model beyond standard clinico-pathologic factors were carried out on an independent, prospective cohort (CANTO, NCT01993498) including 889 HES WSI of ER+/HER2− EBC patients. Results RlapsRisk was an independent prognostic factor of MFS in multivariable analysis adjusted for established clinico-pathological factors (pConclusions Our deep learning model developed on digitized HES slides provided additional prognostic information as compared to current clinico-pathological factors and has the potential of valuably informing the decision making process in the adjuvant setting when combined with current clinico-pathological factors.Keywords
All Related Versions
- Published version: Nature Communications, 16 (1), 1.
This publication has 41 references indexed in Scilit:
- Digital image analysis of Ki67 in hot spots is superior to both manual Ki67 and mitotic counts in breast cancerHistopathology, 2017
- Clinical utility of gene-expression signatures in early stage breast cancerNature Reviews Clinical Oncology, 2017
- Prospective Validation of a 21-Gene Expression Assay in Breast CancerNew England Journal of Medicine, 2015
- Evaluation of an Optimal Cut-Off Point for the Ki-67 Index as a Prognostic Factor in Primary Breast Cancer: A Retrospective StudyPLOS ONE, 2015
- Review The Cancer Genome Atlas (TCGA): an immeasurable source of knowledgeContemporary Oncology, 2015
- An International Ki67 Reproducibility StudyJNCI: Journal of the National Cancer Institute, 2013
- Assessment of Ki67 in Breast Cancer: Recommendations from the International Ki67 in Breast Cancer Working GroupJNCI: Journal of the National Cancer Institute, 2011
- PREDICT: a new UK prognostic model that predicts survival following surgery for invasive breast cancerBreast Cancer Research, 2010
- Use of Archived Specimens in Evaluation of Prognostic and Predictive BiomarkersJNCI: Journal of the National Cancer Institute, 2009
- 17. A Value for n-Person Games1953