Cross-Domain Segmentation with Adversarial Loss and Covariate Shift for Biomedical Imaging

TL;DR

This paper introduces a novel cross-domain segmentation model that leverages adversarial loss and covariate shift properties to effectively segment biomedical images from multiple modalities without modality-specific information, demonstrating superior performance on CT, MRI, and Covid-19 datasets.

Contribution

The paper proposes a new model that learns robust, shared representations for multi-modal biomedical image segmentation without using modality information during training or inference.

Findings

Outperforms baseline methods on CT and MRI liver data.

Achieves superior results on Covid-19 CT dataset.

Uses a single parameter set for cross-domain segmentation.

Abstract

Despite the widespread use of deep learning methods for semantic segmentation of images that are acquired from a single source, clinicians often use multi-domain data for a detailed analysis. For instance, CT and MRI have advantages over each other in terms of imaging quality, artifacts, and output characteristics that lead to differential diagnosis. The capacity of current segmentation techniques is only allow to work for an individual domain due to their differences. However, the models that are capable of working on all modalities are essentially needed for a complete solution. Furthermore, robustness is drastically affected by the number of samples in the training step, especially for deep learning models. Hence, there is a necessity that all available data regardless of data domain should be used for reliable methods. For this purpose, this manuscript aims to implement a novel model that can learn robust representations from cross-domain data by encapsulating distinct and shared patterns from different modalities. Precisely, covariate shift property is retained with structural modification and adversarial loss where sparse and rich representations are obtained. Hence, a single parameter set is used to perform cross-domain segmentation task. The superiority of the proposed method is that no information related to modalities are provided in either training or inference phase. The tests on CT and MRI liver data acquired in routine clinical workflows show that the proposed model outperforms all other baseline with a large margin. Experiments are also conducted on Covid-19 dataset that it consists of CT data where significant intra-class visual differences are observed. Similarly, the proposed method achieves the best performance.