基于卷积变分自编码器的ADMANI乳腺钼靶数据集技术异常值检测
Technical outlier detection via convolutional variational autoencoder for the ADMANI breast mammogram dataset
AI总结：
本研究针对ADMANI乳腺钼靶数据集，采用CVAE结合腐蚀和胸大肌分析等传统图像处理技术检测七类技术异常值，在选取前5%图像时召回率达83%，为下游AI算法开发确保了数据质量。
摘要：
由澳大利亚BreastScreen Victoria运营的BRAIx（用AI改变乳腺癌筛查）项目提供的ADMANI数据集（标注数字乳腺钼靶及关联非图像数据集）是多中心、大规模、临床精选的真实世界数据库。这些数据集有望用于开发具有临床相关性的人工智能（AI）算法，以进行乳腺癌检测、早期诊断等应用。为确保高数据质量，在任何下游算法开发前必须剔除技术异常值。作为第一步，我们随机选取30,000张乳腺钼靶图像，使用卷积变分自编码器（CVAE）这一深度生成神经网络来检测异常值。CVAE有望检测各类异常值，尽管其检测性能因异常值类型而异。腐蚀和胸大肌分析等传统图像处理技术可弥补CVAE在某些异常类型上的性能不足。我们识别出七类技术异常值：植入物、起搏器、心脏循环记录器、不正确的放射摄影、非典型病灶/钙化、不正确的曝光参数和放置不当。若CVAE、腐蚀和胸大肌分析各自选取在每种检测方法下按图像异常值得分升序或降序排列的前1%图像，测试集的异常值召回率为61%；若各自选取前5%的图像，召回率为83%。本研究概述了ADMANI数据集中的技术异常值，并提出了未来改进异常值检测效果的方向。
英文摘要：
The ADMANI datasets (annotated digital mammograms and associated non-image datasets) from the Transforming Breast Cancer Screening with AI programme (BRAIx) run by BreastScreen Victoria in Australia are multi-centre, large scale, clinically curated, real-world databases. The datasets are expected to aid in the development of clinically relevant Artificial Intelligence (AI) algorithms for breast cancer detection, early diagnosis, and other applications. To ensure high data quality, technical outliers must be removed before any downstream algorithm development. As a first step, we randomly select 30,000 individual mammograms and use Convolutional Variational Autoencoder (CVAE), a deep generative neural network, to detect outliers. CVAE is expected to detect all sorts of outliers, although its detection performance differs among different types of outliers. Traditional image processing techniques such as erosion and pectoral muscle analysis can compensate for the poor performance of CVAE in certain outlier types. We identify seven types of technical outliers: implant, pacemaker, cardiac loop recorder, improper radiography, atypical lesion/calcification, incorrect exposure parameter and improper placement. The outlier recall rate for the test set is 61% if CVAE, erosion and pectoral muscle analysis each select the top 1% images ranked in ascending or descending order according to image outlier score under each detection method, and 83% if each selects the top 5% images. This study offers an overview of technical outliers in the ADMANI dataset and suggests future directions to improve outlier detection effectiveness.
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。
