用直接路径修正脑影像异常，单步完成定位与修复。
REFLECT: Rectified Flows for Efficient Brain Anomaly Correction Transport
- 通过修正流建立异常到正常的直线映射，实现单步纠正。
- 在多个脑部分割基准上显著超越现有无监督检测方法。
- 适合需要快速、精准定位脑病灶的研究与临床应用。
脑影像中的无监督异常检测对识别病理至关重要，但因大脑解剖结构复杂且异常样本稀缺，精确定位仍具挑战。本文提出REFLECT框架，利用修正流构建从异常图像到正常分布的直接线性轨迹。通过学习单一一步的校正传输映射，该方法高效修正脑部异常，并通过对比异常输入与校正后图像的差异实现精确异常定位。相比依赖迭代随机采样的扩散模型，修正流提供直接传输路径，支持单步推理。在多个主流无监督脑部分割基准上的实验表明，REFLECT显著优于当前最先进方法。代码已公开于https://github.com/farzad-bz/REFLECT。
原文摘要 · Abstract (English)
Unsupervised anomaly detection (UAD) in brain imaging is crucial for identifying pathologies without the need for labeled data. However, accurately localizing anomalies remains challenging due to the intricate structure of brain anatomy and the scarcity of abnormal examples. In this work, we introduce REFLECT, a novel framework that leverages rectified flows to establish a direct, linear trajectory for correcting abnormal MR images toward a normal distribution. By learning a straight, one-step correction transport map, our method efficiently corrects brain anomalies and can precisely localize anomalies by detecting discrepancies between anomalous input and corrected counterpart. In contrast to the diffusion-based UAD models, which require iterative stochastic sampling, rectified flows provide a direct transport map, enabling single-step inference. Extensive experiments on popular UAD brain segmentation benchmarks demonstrate that REFLECT significantly outperforms state-of-the-art unsupervised anomaly detection methods. The code is available at https://github.com/farzad-bz/REFLECT.
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。