期刊
MEDICAL IMAGE ANALYSIS
卷 86, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.media.2023.102794
关键词
Anomaly detection; Reconstruction networks; Self-supervised learning; Benchmark
Medical anomaly detection is essential for recognizing abnormal images in order to assist in diagnosis. Most methods only utilize known normal images during training, ignoring readily available unlabeled images containing anomalies and limiting performance. To address this problem, we propose a one-class semi-supervised learning approach called Dual-distribution Discrepancy for Anomaly Detection (DDAD), which utilizes both known normal and unlabeled images for training. Our method achieves significant gains and outperforms state-of-the-art methods on various medical datasets.
Medical anomaly detection is a crucial yet challenging task aimed at recognizing abnormal images to assist in diagnosis. Due to the high-cost annotations of abnormal images, most methods utilize only known normal images during training and identify samples deviating from the normal profile as anomalies in the testing phase. Many readily available unlabeled images containing anomalies are thus ignored in the training phase, restricting the performance. To solve this problem, we introduce one-class semi-supervised learning (OC-SSL) to utilize known normal and unlabeled images for training, and propose Dual-distribution Discrepancy for Anomaly Detection (DDAD) based on this setting. Ensembles of reconstruction networks are designed to model the distribution of normal images and the distribution of both normal and unlabeled images, deriving the normative distribution module (NDM) and unknown distribution module (UDM). Subsequently, the intra-discrepancy of NDM and inter-discrepancy between the two modules are designed as anomaly scores. Furthermore, we propose a new perspective on self-supervised learning, which is designed to refine the anomaly scores rather than directly detect anomalies. Five medical datasets, including chest X-rays, brain MRIs and retinal fundus images, are organized as benchmarks for evaluation. Experiments on these benchmarks comprehensively compare a wide range of anomaly detection methods and demonstrate that our method achieves significant gains and outperforms the state-of-the-art. Code and organized benchmarks are available at https://github.com/caiyu6666/DDAD-ASR.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据