Adenocarcinoma Segmentation Using Pre-trained Swin-UNet with Parallel Cross-Attention for Multi-Domain Imaging

TL;DR

This paper introduces a novel deep learning framework combining a pre-trained Swin-UNet with parallel cross-attention to improve adenocarcinoma segmentation across different organs and scanners, addressing domain shift challenges.

Contribution

The work presents a new architecture that enhances segmentation robustness across multiple domains using a pre-trained encoder and parallel cross-attention modules.

Findings

Achieved segmentation scores of 0.7469 and 0.7597 on challenge datasets.

Effectively handles morphological and scanner-induced domain variations.

Improves segmentation accuracy across diverse imaging conditions.

Abstract

Computer aided pathological analysis has been the gold standard for tumor diagnosis, however domain shift is a significant problem in histopathology. It may be caused by variability in anatomical structures, tissue preparation, and imaging processes challenges the robustness of segmentation models. In this work, we present a framework consist of pre-trained encoder with a Swin-UNet architecture enhanced by a parallel cross-attention module to tackle the problem of adenocarcinoma segmentation across different organs and scanners, considering both morphological changes and scanner-induced domain variations. Experiment conducted on Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation challenge dataset showed that our framework achieved segmentation scores of 0.7469 for the cross-organ track and 0.7597 for the cross-scanner track on the final challenge test sets, and effectively navigates diverse imaging conditions and improves segmentation accuracy across varying domains.