Radial Prediction Domain Adaption Classifier for the MIDOG 2022 Challenge

TL;DR

This paper presents a novel domain adaptation classifier combined with an adapted YOLOv5s model and stain augmentation techniques to improve mitotic cell detection robustness in histopathology images, achieving a test F1-score of 0.6658.

Contribution

We introduce the Radial-Prediction-DAC, a new domain adaptation classifier, integrated with YOLOv5s and stain augmentation, to enhance robustness against domain shifts in histopathology image analysis.

Findings

Achieved a test F1-score of 0.6658 on the MIDOG 2022 dataset.

Demonstrated improved robustness under domain shifts with the proposed method.

Enhanced training data variability using stain augmentation in HED color space.

Abstract

This paper describes our contribution to the MIDOG 2022 challenge for detecting mitotic cells. One of the major problems to be addressed in the MIDOG 2022 challenge is the robustness under the natural variance that appears for real-life data in the histopathology field. To address the problem, we use an adapted YOLOv5s model for object detection in conjunction with a new Domain Adaption Classifier (DAC) variant, the Radial-Prediction-DAC, to achieve robustness under domain shifts. In addition, we increase the variability of the available training data using stain augmentation in HED color space. Using the suggested method, we obtain a test set F1-score of 0.6658.