User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation
This work addresses the problem of reducing annotation labor for medical image segmentation, particularly for pathological livers, representing a strong specific gain in this domain.
The paper tackles the bottleneck of mask-based annotation for 3D medical images by proposing a user-guided domain adaptation framework that harmonizes user interactions with mask predictions, achieving a mean performance of 96.1% on pathological liver segmentation compared to 93.0% for a baseline method.
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.