Molecular Subtype Prediction for Breast Cancer Using H&E Specialized Backbone

no code implementations • MICCAI Workshop COMPAY 2021 • Samaneh Abbasi Sureshjani, Anil Yuce, Simon Till Schönenberger, Maris Skujevskis, Uwe Schalles, Fabien Gaire, Konstanty Korski

In this work, we investigated the predictiveness of morphological characteristics of Hematoxylin and Eosin (H&E) stained tissues for molecular subtype analysis, as an initial step for direct treatment response prediction based on H&E whole slide images (WSI).

Transfer Learning whole slide images

Witness Autoencoder: Shaping the Latent Space with Witness Complexes

no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Simon Till Schönenberger, Anastasiia Varava, Vladislav Polianskii, Jen Jen Chung, Danica Kragic, Roland Siegwart

We present a Witness Autoencoder (W-AE) – an autoencoder that captures geodesic distances of the data in the latent space.