通过无监督正交化提升医学图像表征的鲁棒性
Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations
- 用视觉变换器结合无监督特征正交化分离解剖与图像特异性特征
- 在多种畸变下保持重建能力，下游任务准确率超基线12.3%
- 适合数据少、资源受限的医疗场景，可迁移性强
本研究提出 unORANIC+，一种将无监督特征正交化与视觉变换器结合的新方法，以增强模型对局部与全局关系的捕捉能力，从而提升鲁棒性和泛化性。其简化架构有效分离了解剖结构与图像特有属性，生成稳健且无偏的潜在表示，在多种医学图像分析任务和不同数据集上表现优异。大量实验表明，unORANIC+ 具备出色的重建能力、抗畸变能力，并能修复现有图像畸变。此外，该模型在疾病分类与畸变检测等下游任务中也展现出显著性能。我们验证了其在不同图像来源和样本量数据集上的适应性，证明该方法在缺乏大规模定制数据集的资源受限环境中具有重要应用前景。源代码已开源：https://github.com/sdoerrich97/unoranic-plus。
原文摘要 · Abstract (English)
This study introduces unORANIC+, a novel method that integrates unsupervised feature orthogonalization with the ability of a Vision Transformer to capture both local and global relationships for improved robustness and generalizability. The streamlined architecture of unORANIC+ effectively separates anatomical and image-specific attributes, resulting in robust and unbiased latent representations that allow the model to demonstrate excellent performance across various medical image analysis tasks and diverse datasets. Extensive experimentation demonstrates unORANIC+'s reconstruction proficiency, corruption resilience, as well as capability to revise existing image distortions. Additionally, the model exhibits notable aptitude in downstream tasks such as disease classification and corruption detection. We confirm its adaptability to diverse datasets of varying image sources and sample sizes which positions the method as a promising algorithm for advanced medical image analysis, particularly in resource-constrained environments lacking large, tailored datasets. The source code is available at https://github.com/sdoerrich97/unoranic-plus .
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。