Adenocarcinoma Segmentation Using Pre-trained Swin-UNet with Parallel Cross-Attention for Multi-Domain Imaging
This work addresses domain shift in histopathology for improved tumor diagnosis, though it is incremental as it builds on existing architectures.
The paper tackled adenocarcinoma segmentation across different organs and scanners by enhancing a pre-trained Swin-UNet with a parallel cross-attention module, achieving segmentation scores of 0.7469 for cross-organ and 0.7597 for cross-scanner tasks.
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.