Unsupervised anomaly detection in medical images such as chest radiographs is stepping into the spotlight as it mitigates the scarcity of the labor-intensive and costly expert annotation of anomaly data. However, nearly all existing methods are formulated as a one-class classification trained only on representations from the normal class and discard a potentially significant portion of the unlabeled data. This paper focuses on a more practical setting, dual distribution anomaly detection for chest X-rays, using the entire training data, including both normal and unlabeled images. Inspired by a modern self-supervised vision transformer model trained using partial image inputs to reconstruct missing image regions -- we propose AMAE, a two-stage algorithm for adaptation of the pre-trained masked autoencoder (MAE). Starting from MAE initialization, AMAE first creates synthetic anomalies from only normal training images and trains a lightweight classifier on frozen transformer features. Subsequently, we propose an adaptation strategy to leverage unlabeled images containing anomalies. The adaptation scheme is accomplished by assigning pseudo-labels to unlabeled images and using two separate MAE based modules to model the normative and anomalous distributions of pseudo-labeled images. The effectiveness of the proposed adaptation strategy is evaluated with different anomaly ratios in an unlabeled training set. AMAE leads to consistent performance gains over competing self-supervised and dual distribution anomaly detection methods, setting the new state-of-the-art on three public chest X-ray benchmarks: RSNA, NIH-CXR, and VinDr-CXR.

翻译：无监督异常检测在胸部X光片等医学图像中正逐渐受到关注，因其能够缓解异常数据依赖人工标注的高成本与低效率问题。然而，现有方法几乎均被构建为仅基于正常类别表征训练的一类分类模型，忽视了未标注数据中可能蕴含的重要信息。本文聚焦于更具实用性的胸部X光片双分布异常检测场景，利用包含正常图像与未标注图像在内的全部训练数据。受现代自监督视觉Transformer模型（通过部分图像输入重建缺失区域）启发，我们提出AMAE——一种基于预训练掩码自编码器（MAE）自适应调整的两阶段算法。首先，以MAE初始化为基础，仅使用正常训练图像生成合成异常，并在冻结的Transformer特征上训练轻量级分类器。随后，我们提出一种自适应策略，利用包含异常的未标注图像：通过为未标注图像分配伪标签，并基于两个独立的MAE模块分别建模伪标签图像的规范分布与异常分布。我们评估了该自适应策略在不同异常比例未标注训练集下的有效性。AMAE在三个公开胸部X光基准数据集（RSNA、NIH-CXR和VinDr-CXR）上均取得一致性的性能提升，超越了现有自监督与双分布异常检测方法，确立了新的最优水平。