通过保真度约束的位移编辑，提升多模态显微图像配准精度。
Fidelity-Imposed Displacement Editing for the Learn2Reg 2024 SHG-BF Challenge
- 引入保真度约束的位移编辑机制，增强图像对齐稳定性。
- 在SHG-BF配准挑战中取得线上排行榜第一，准确率显著提升。
- 适合医学图像分析、多模态影像融合等研究者参考。
双光子激发荧光（SHG）与明场（BF）显微成像联合分析可区分组织成分和胶原纤维，有助于乳腺癌和胰腺癌组织的病理分析。然而，SHG与BF图像间存在显著差异，给基于学习的图像配准模型带来挑战。本文提出一种新型多模态配准框架，采用保真度约束的位移编辑策略，整合批次对比学习、基于特征的预对齐和实例级优化。在Learn2Reg COMULISglobe SHG-BF挑战赛中的实验结果验证了该方法的有效性，在线上排行榜中获得第一名。
原文摘要 · Abstract (English)
Co-examination of second-harmonic generation (SHG) and bright-field (BF) microscopy enables the differentiation of tissue components and collagen fibers, aiding the analysis of human breast and pancreatic cancer tissues. However, large discrepancies between SHG and BF images pose challenges for current learning-based registration models in aligning SHG to BF. In this paper, we propose a novel multi-modal registration framework that employs fidelity-imposed displacement editing to address these challenges. The framework integrates batch-wise contrastive learning, feature-based pre-alignment, and instance-level optimization. Experimental results from the Learn2Reg COMULISglobe SHG-BF Challenge validate the effectiveness of our method, securing the 1st place on the online leaderboard.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。