Sk-Unet Model with Fourier Domain for Mitosis Detection
This work addresses domain shift issues in mitosis detection for breast cancer grading, but it is incremental as it builds on existing deep learning methods with a specific adaptation.
The paper tackles the problem of domain shift in mitosis detection for breast cancer grading by constructing a Fourier-based segmentation model that swaps low-frequency spectra between source and target images, achieving an F1 score of 0.7456 on a preliminary test set.
Mitotic count is the most important morphological feature of breast cancer grading. Many deep learning-based methods have been proposed but suffer from domain shift. In this work, we construct a Fourier-based segmentation model for mitosis detection to address the problem. Swapping the low-frequency spectrum of source and target images is shown effective to alleviate the discrepancy between different scanners. Our Fourier-based segmentation method can achieve F1 with 0.7456 on the preliminary test set.