# User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation

arXiv: https://arxiv.org/abs/2009.02455 · HTML: https://mlsanity.com/paper/2009.02455/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning](https://mlsanity.com/paper/2104.12166/) (2021)
- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [Deep Implicit Statistical Shape Models for 3D Medical Image Delineation](https://mlsanity.com/paper/2104.02847/) (2021)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans](https://mlsanity.com/paper/2302.00162/) (2023)
- [Multi-Slice Low-Rank Tensor Decomposition Based Multi-Atlas Segmentation: Application to Automatic Pathological Liver CT Segmentation](https://mlsanity.com/paper/2102.12056/) (2021)
- [Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation](https://mlsanity.com/paper/2410.04689/) (2024)

## Abstract (arXiv)

Mask-based annotation of medical images, especially for 3D data, is a bottleneck in developing reliable machine learning models. Using minimal-labor user interactions (UIs) to guide the annotation is promising, but challenges remain on best harmonizing the mask prediction with the UIs. To address this, we propose the user-guided domain adaptation (UGDA) framework, which uses prediction-based adversarial domain adaptation (PADA) to model the combined distribution of UIs and mask predictions. The UIs are then used as anchors to guide and align the mask prediction. Importantly, UGDA can both learn from unlabelled data and also model the high-level semantic meaning behind different UIs. We test UGDA on annotating pathological livers using a clinically comprehensive dataset of 927 patient studies. Using only extreme-point UIs, we achieve a mean (worst-case) performance of 96.1%(94.9%), compared to 93.0% (87.0%) for deep extreme points (DEXTR). Furthermore, we also show UGDA can retain this state-of-the-art performance even when only seeing a fraction of available UIs, demonstrating an ability for robust and reliable UI-guided segmentation with extremely minimal labor demands.