Assessing domain adaptation techniques for mitosis detection in multi-scanner breast cancer histopathology images

TL;DR

This study evaluates unsupervised domain adaptation methods, CycleGAN and Neural Style Transfer, to improve mitosis detection in breast cancer histopathology images across different scanners, highlighting their variable effectiveness.

Contribution

It provides a comparative analysis of two domain adaptation techniques applied to mitosis detection models, demonstrating their potential and limitations in multi-scanner settings.

Findings

CycleGAN improved detection on some scanners

Neural Style Transfer showed mixed results

Both methods need further refinement for consistency

Abstract

Breast cancer is the most commonly diagnosed cancer worldwide, with over two million new cases each year. During diagnostic tumour grading, pathologists manually count the number of dividing cells (mitotic figures) in biopsy or tumour resection specimens. Since the process is subjective and time-consuming, data-driven artificial intelligence (AI) methods have been developed to automatically detect mitotic figures. However, these methods often generalise poorly, with performance reduced by variations in tissue types, staining protocols, or the scanners used to digitise whole-slide images. Domain adaptation approaches have been adopted in various applications to mitigate this issue of domain shift. We evaluate two unsupervised domain adaptation methods, CycleGAN and Neural Style Transfer, using the MIDOG 2021 Challenge dataset. This challenge focuses on detecting mitotic figures in whole-slide images digitised using different scanners. Two baseline mitosis detection models based on U-Net and RetinaNet were investigated in combination with the aforementioned domain adaptation methods. Both baseline models achieved human expert level performance, but had reduced performance when evaluated on images which had been digitised using a different scanner. The domain adaptation techniques were each found to be beneficial for detection with data from some scanners but not for others, with the only average increase across all scanners being achieved by CycleGAN on the RetinaNet detector. These techniques require further refinement to ensure consistency in mitosis detection.