Cross-Organ Domain Adaptive Neural Network for Pancreatic Endoscopic Ultrasound Image Segmentation

TL;DR

This paper introduces COTS-Nets, a novel domain adaptation framework for pancreatic EUS image segmentation that leverages cross-organ knowledge to improve tumor delineation despite limited data.

Contribution

The paper proposes a universal and auxiliary network architecture that utilizes boundary and consistency losses to bridge the domain gap across different organs in EUS images.

Findings

COTS-Nets significantly improve pancreatic tumor segmentation accuracy.

The auxiliary network enhances domain-invariant feature learning.

The PCEUS dataset provides a valuable resource for future research.

Abstract

Accurate segmentation of lesions in pancreatic endoscopic ultrasound (EUS) images is crucial for effective diagnosis and treatment. However, the collection of enough crisp EUS images for effective diagnosis is arduous. Recently, domain adaptation (DA) has been employed to address these challenges by leveraging related knowledge from other domains. Most DA methods only focus on multi-view representations of the same organ, which makes it still tough to clearly depict the tumor lesion area with limited semantic information. Although transferring homogeneous similarity from different organs could benefit the issue, there is a lack of relevant work due to the enormous domain gap between them. To address these challenges, we propose the Cross-Organ Tumor Segmentation Networks (COTS-Nets), consisting of a universal network and an auxiliary network. The universal network utilizes boundary loss to learn common boundary information of different tumors, enabling accurate delineation of tumors in EUS despite limited and low-quality data. Simultaneously, we incorporate consistency loss in the universal network to align the prediction of pancreatic EUS with tumor boundaries from other organs to mitigate the domain gap. To further reduce the cross-organ domain gap, the auxiliary network integrates multi-scale features from different organs, aiding the universal network in acquiring domain-invariant knowledge. Systematic experiments demonstrate that COTS-Nets significantly improves the accuracy of pancreatic cancer diagnosis. Additionally, we developed the Pancreatic Cancer Endoscopic Ultrasound (PCEUS) dataset, comprising 501 pathologically confirmed pancreatic EUS images, to facilitate model development.