MIM-OOD：用于医学图像分布外检测的生成式掩码图像建模
MIM-OOD: Generative Masked Image Modelling for Out-of-Distribution Detection in Medical Images
AI总结：
MIM-OOD提出用两个任务特定的transformer替代自回归模型，分别用于识别和修复异常标记，在脑部MRI异常检测中显著提升了性能并实现近25倍加速。
摘要：
无监督分布外（OOD）检测旨在仅利用在健康解剖结构图像上训练的模型来识别图像中的异常区域。一种成熟的方法是将图像标记化，并使用自回归（AR）模型对标记的分布进行建模。AR模型被用于1）识别异常标记，以及2）用分布内标记对异常表示进行修复。然而，AR模型在推理时速度缓慢，且容易出现误差累积问题，这会对OOD检测性能产生负面影响。我们的新方法MIM-OOD通过用两个任务特定的网络替代AR模型，克服了速度和误差累积问题：1）一个优化用于识别异常标记的transformer，以及2）一个优化用于使用掩码图像建模（MIM）修复异常标记的transformer。我们在脑部MRI异常上的实验表明，MIM-OOD显著优于AR模型（DICE 0.458 vs 0.301），同时实现了近25倍的加速（9.5s vs 244s）。
英文摘要：
Unsupervised Out-of-Distribution (OOD) detection consists in identifying anomalous regions in images leveraging only models trained on images of healthy anatomy. An established approach is to tokenize images and model the distribution of tokens with Auto-Regressive (AR) models. AR models are used to 1) identify anomalous tokens and 2) in-paint anomalous representations with in-distribution tokens. However, AR models are slow at inference time and prone to error accumulation issues which negatively affect OOD detection performance. Our novel method, MIM-OOD, overcomes both speed and error accumulation issues by replacing the AR model with two task-specific networks: 1) a transformer optimized to identify anomalous tokens and 2) a transformer optimized to in-paint anomalous tokens using masked image modelling (MIM). Our experiments with brain MRI anomalies show that MIM-OOD substantially outperforms AR models (DICE 0.458 vs 0.301) while achieving a nearly 25x speedup (9.5s vs 244s).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
