HEROHE Challenge: assessing HER2 status in breast cancer without immunohistochemistry or in situ hybridization

Abstract

Breast cancer is the most common malignancy in women, being responsible for more than half a million deaths every year. As such, early and accurate diagnosis is of paramount importance. Human expertise is required to diagnose and correctly classify breast cancer and define appropriate therapy, which depends on the evaluation of the expression of different biomarkers such as the transmembrane protein receptor HER2. This evaluation requires several steps, including special techniques such as immunohistochemistry or in situ hybridization to assess HER2 status. With the goal of reducing the number of steps and human bias in diagnosis, the HEROHE Challenge was organized, as a parallel event of the 16th European Congress on Digital Pathology, aiming to automate the assessment of the HER2 status based only on hematoxylin and eosin stained tissue sample of invasive breast cancer. Methods to assess HER2 status were presented by 21 teams worldwide and the results achieved by some of the proposed methods open potential perspectives to advance the state-of-the-art.

References in corpus (9)

• XGBoost: A Scalable Tree Boosting System
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Squeeze-and-Excitation Networks
• BACH: Grand Challenge on Breast Cancer Histology Images
• Attention-based Deep Multiple Instance Learning
• Her2 Challenge Contest: A Detailed Assessment of Automated Her2 Scoring Algorithms in Whole Slide Images of Breast Cancer Tissues
• GAN-based Virtual Re-Staining: A Promising Solution for Whole Slide Image Analysis
• Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images
• Weakly Supervised Clustering by Exploiting Unique Class Count