Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation

TL;DR

This paper introduces a novel unsupervised domain adaptation framework for multi-modal cardiac image segmentation, combining entropy minimisation, feature space alignment, and point-cloud shape adaptation to improve cross-domain performance.

Contribution

It proposes an end-to-end adversarial learning method that effectively adapts features across different imaging modalities and domains, addressing limitations of existing UDA approaches.

Findings

Improved segmentation accuracy on cross-modality cardiac datasets.

Effective domain adaptation from MRI to CT images.

Outperforms state-of-the-art UDA methods in experiments.

Abstract

Deep learning models are sensitive to domain shift phenomena. A model trained on images from one domain cannot generalise well when tested on images from a different domain, despite capturing similar anatomical structures. It is mainly because the data distribution between the two domains is different. Moreover, creating annotation for every new modality is a tedious and time-consuming task, which also suffers from high inter- and intra- observer variability. Unsupervised domain adaptation (UDA) methods intend to reduce the gap between source and target domains by leveraging source domain labelled data to generate labels for the target domain. However, current state-of-the-art (SOTA) UDA methods demonstrate degraded performance when there is insufficient data in source and target domains. In this paper, we present a novel UDA method for multi-modal cardiac image segmentation. The proposed method is based on adversarial learning and adapts network features between source and target domain in different spaces. The paper introduces an end-to-end framework that integrates: a) entropy minimisation, b) output feature space alignment and c) a novel point-cloud shape adaptation based on the latent features learned by the segmentation model. We validated our method on two cardiac datasets by adapting from the annotated source domain, bSSFP-MRI (balanced Steady-State Free Procession-MRI), to the unannotated target domain, LGE-MRI (Late-gadolinium enhance-MRI), for the multi-sequence dataset; and from MRI (source) to CT (target) for the cross-modality dataset. The results highlighted that by enforcing adversarial learning in different parts of the network, the proposed method delivered promising performance, compared to other SOTA methods.