The scarcity of high quality medical image annotations hinders the implementation of accurate clinical applications for detecting and segmenting abnormal lesions. To mitigate this issue, the scientific community is working on the development of unsupervised anomaly detection (UAD) systems that learn from a training set containing only normal (i.e., healthy) images, where abnormal samples (i.e., unhealthy) are detected and segmented based on how much they deviate from the learned distribution of normal samples. One significant challenge faced by UAD methods is how to learn effective low-dimensional image representations that are sensitive enough to detect and segment abnormal lesions of varying size, appearance and shape. To address this challenge, we propose a novel self-supervised UAD pre-training algorithm, named Multi-centred Strong Augmentation via Contrastive Learning (MSACL). MSACL learns representations by separating several types of strong and weak augmentations of normal image samples, where the weak augmentations represent normal images and strong augmentations denote synthetic abnormal images. To produce such strong augmentations, we introduce MedMix, a novel data augmentation strategy that creates new training images with realistic looking lesions (i.e., anomalies) in normal images. The pre-trained representations from MSACL are generic and can be used to improve the efficacy of different types of off-the-shelf state-of-the-art (SOTA) UAD models. Comprehensive experimental results show that the use of MSACL largely improves these SOTA UAD models on four medical imaging datasets from diverse organs, namely colonoscopy, fundus screening and covid-19 chest-ray datasets.
翻译:缺乏高质量的医疗图像说明妨碍了准确的临床应用用于检测和分解异常损伤。为了缓解这一问题,科学界正在努力开发未经监督的异常现象检测(UAD)系统,这些系统从仅包含正常(即健康)图像的培训数据集中学习,其中非正常(即健康)样本(即不健康)的检测和分解基于其与正常样本的传播有多么不同。UAD方法面临的一个重大挑战是如何学习有效的低维图像显示,这种显示足够敏感,能够检测和分解大小、外观和形状不同的异常。为了应对这一挑战,我们建议开发一种新型的自我监督的UAD异常检测(UAD)系统培训前算法(UADAD)系统,其名称为多中心为“健康”图像。 MACLCL通过将正常图像样本的几类强而弱的增强量进行分解,其中薄弱的图像代表正常图像的增强度和合成图像的强烈增强度。为了产生如此强烈的增强,我们引入MedMix, 一种新型的数据增强战略,从现实的四类常规(即常规(SLA)图像的正常的改善数据。