Rotation Invariance and Extensive Data Augmentation: a strategy for the Mitosis Domain Generalization (MIDOG) Challenge

TL;DR

This paper presents a robust deep learning approach for mitosis detection in histopathology images, emphasizing rotation invariance and extensive data augmentation to improve generalization across unseen scanners in the MIDOG challenge.

Contribution

The authors introduce a combination of rotation-invariant convolutional networks and extensive data augmentation to enhance model robustness for domain generalization in mitosis detection.

Findings

Achieved an average F1-score of 0.747 on test splits.

Ensemble model scored 0.6828 on the challenge's preliminary test set.

Demonstrated effectiveness of rotation invariance and data augmentation for scanner variability.

Abstract

Automated detection of mitotic figures in histopathology images is a challenging task: here, we present the different steps that describe the strategy we applied to participate in the MIDOG 2021 competition. The purpose of the competition was to evaluate the generalization of solutions to images acquired with unseen target scanners (hidden for the participants) under the constraint of using training data from a limited set of four independent source scanners. Given this goal and constraints, we joined the challenge by proposing a straight-forward solution based on a combination of state-of-the-art deep learning methods with the aim of yielding robustness to possible scanner-related distributional shifts at inference time. Our solution combines methods that were previously shown to be efficient for mitosis detection: hard negative mining, extensive data augmentation, rotation-invariant convolutional networks. We trained five models with different splits of the provided dataset. The subsequent classifiers produced F1-scores with a mean and standard deviation of 0.747+/-0.032 on the test splits. The resulting ensemble constitutes our candidate algorithm: its automated evaluation on the preliminary test set of the challenge returned a F1-score of 0.6828.