# MI^2GAN: Generative Adversarial Network for Medical Image Domain Adaptation using Mutual Information Constraint

arXiv: https://arxiv.org/abs/2007.11180 · HTML: https://mlsanity.com/paper/2007.11180/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2020.

## Built on by (most cited first, 17 of 17)

- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images](https://mlsanity.com/paper/2310.03559/) (2023)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2211.12081/) (2022)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey](https://mlsanity.com/paper/2401.11734/) (2024)
- [Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging](https://mlsanity.com/paper/2407.18792/) (2024)
- [Domain Adaptation of Carotid Ultrasound Images using Generative Adversarial Network](https://mlsanity.com/paper/2601.01460/) (2026)
- [Sim2Real within 5 Minutes: Efficient Domain Transfer with Stylized Gaussian Splatting for Endoscopic Images](https://mlsanity.com/paper/2403.10860/) (2024)
- [Gaze-Assisted Human-Centric Domain Adaptation for Cardiac Ultrasound Image Segmentation](https://mlsanity.com/paper/2502.03781/) (2025)
- [Source-Free Domain Adaptation via Multi-view Contrastive Learning](https://mlsanity.com/paper/2507.03321/) (2025)
- [Robust Source-Free Domain Adaptation for Medical Image Segmentation based on Curriculum Learning](https://mlsanity.com/paper/2510.08393/) (2025)
- [Fine-Tuning Cycle-GAN for Domain Adaptation of MRI Images](https://mlsanity.com/paper/2601.12512/) (2026)
- [Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study](https://mlsanity.com/paper/2602.18502/) (2026)
- [EndoSERV: A Vision-based Endoluminal Robot Navigation System](https://mlsanity.com/paper/2603.08324/) (2026)

## Abstract (arXiv)

Domain shift between medical images from multicentres is still an open question for the community, which degrades the generalization performance of deep learning models. Generative adversarial network (GAN), which synthesize plausible images, is one of the potential solutions to address the problem. However, the existing GAN-based approaches are prone to fail at preserving image-objects in image-to-image (I2I) translation, which reduces their practicality on domain adaptation tasks. In this paper, we propose a novel GAN (namely MI2GAN) to maintain image-contents during cross-domain I2I translation. Particularly, we disentangle the content features from domain information for both the source and translated images, and then maximize the mutual information between the disentangled content features to preserve the image-objects. The proposed MI2GAN is evaluated on two tasks---polyp segmentation using colonoscopic images and the segmentation of optic disc and cup in fundus images. The experimental results demonstrate that the proposed MI2GAN can not only generate elegant translated images, but also significantly improve the generalization performance of widely used deep learning networks (e.g., U-Net).