# A Novel Domain Adaptation Framework for Medical Image Segmentation

arXiv: https://arxiv.org/abs/1810.05732 · HTML: https://mlsanity.com/paper/1810.05732/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2018.

## Built on by (most cited first, 9 of 9)

- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [CellTranspose: Few-shot Domain Adaptation for Cellular Instance Segmentation](https://mlsanity.com/paper/2212.14121/) (2022)
- [A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation](https://mlsanity.com/paper/2306.08720/) (2023)
- [Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation](https://mlsanity.com/paper/2103.05529/) (2021)
- [Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions](https://mlsanity.com/paper/2203.10507/) (2022)
- [Adnexal Mass Segmentation with Ultrasound Data Synthesis](https://mlsanity.com/paper/2209.12305/) (2022)
- [Unsupervised Domain Adaptive Fundus Image Segmentation with Few Labeled Source Data](https://mlsanity.com/paper/2210.04379/) (2022)
- [Brain MRI study for glioma segmentation using convolutional neural networks and original post-processing techniques with low computational demand](https://mlsanity.com/paper/2207.07622/) (2022)
- [SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation](https://mlsanity.com/paper/2308.04946/) (2023)

## Abstract (arXiv)

We propose a segmentation framework that uses deep neural networks and introduce two innovations. First, we describe a biophysics-based domain adaptation method. Second, we propose an automatic method to segment white and gray matter, and cerebrospinal fluid, in addition to tumorous tissue. Regarding our first innovation, we use a domain adaptation framework that combines a novel multispecies biophysical tumor growth model with a generative adversarial model to create realistic looking synthetic multimodal MR images with known segmentation. Regarding our second innovation, we propose an automatic approach to enrich available segmentation data by computing the segmentation for healthy tissues. This segmentation, which is done using diffeomorphic image registration between the BraTS training data and a set of prelabeled atlases, provides more information for training and reduces the class imbalance problem. Our overall approach is not specific to any particular neural network and can be used in conjunction with existing solutions. We demonstrate the performance improvement using a 2D U-Net for the BraTS'18 segmentation challenge. Our biophysics based domain adaptation achieves better results, as compared to the existing state-of-the-art GAN model used to create synthetic data for training.