# Sk-Unet Model with Fourier Domain for Mitosis Detection

arXiv: https://arxiv.org/abs/2109.00957 · HTML: https://mlsanity.com/paper/2109.00957/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 14 references that are in the map.
- First posted on arXiv 1 Sep 2021.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation](https://mlsanity.com/paper/1707.03718/) (2017)

## Built on by (most cited first, 6 of 6)

- [Mitosis domain generalization in histopathology images -- The MIDOG challenge](https://mlsanity.com/paper/2204.03742/) (2022)
- [Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures](https://mlsanity.com/paper/2208.12587/) (2022)
- [Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge](https://mlsanity.com/paper/2208.12437/) (2022)
- [SCORPION: Addressing Scanner-Induced Variability in Histopathology](https://mlsanity.com/paper/2507.20907/) (2025)
- [Multi-task learning for tissue segmentation and tumor detection in colorectal cancer histology slides](https://mlsanity.com/paper/2304.03101/) (2023)
- [Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification](https://mlsanity.com/paper/2509.02591/) (2025)

## Abstract (arXiv)

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.