Rotation Equivariant CNNs for Digital Pathology

8 Jun 2018  ·  Bastiaan S. Veeling, Jasper Linmans, Jim Winkens, Taco Cohen, Max Welling ·

We propose a new model for digital pathology segmentation, based on the observation that histopathology images are inherently symmetric under rotation and reflection. Utilizing recent findings on rotation equivariant CNNs, the proposed model leverages these symmetries in a principled manner... We present a visual analysis showing improved stability on predictions, and demonstrate that exploiting rotation equivariance significantly improves tumor detection performance on a challenging lymph node metastases dataset. We further present a novel derived dataset to enable principled comparison of machine learning models, in combination with an initial benchmark. Through this dataset, the task of histopathology diagnosis becomes accessible as a challenging benchmark for fundamental machine learning research. read more

PDF Abstract

Datasets


Introduced in the Paper:

PCam

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Breast Tumour Classification PCam p4m-DenseNet (D4) AUC 0.963 # 7

Methods


No methods listed for this paper. Add relevant methods here