用于医学图像近似与重复检测的预训练视觉嵌入基准测试
Benchmarking Pretrained Vision Embeddings for Near- and Duplicate Detection in Medical Images
AI总结：
针对医学数据集中相似或重复3D图像导致的数据泄漏问题，本文提出利用公开2D视觉预训练嵌入和向量索引进行检测，并基于Medical Segmentation Decathlon构建基准，验证了方法的有效性。
摘要：
近似与重复图像检测是医学成像领域的一个关键问题。医学数据集通常包含来自各种来源的相似或重复图像，这可能导致显著的性能问题和评估偏差，尤其在机器学习任务中，原因是训练子集与测试子集之间存在数据泄漏。本文提出一种利用公开可用的2D计算机视觉嵌入来识别近似与重复3D医学图像的方法。我们通过比较从两个最先进的自监督预训练模型和两种不同的用于相似性检索的向量索引结构中提取的嵌入，对该方法进行了评估。我们基于公开可用的Medical Segmentation Decathlon数据集生成了一个实验基准。所提出的方法在近似与重复图像检测方面取得了有前景的结果，平均灵敏度和特异度分别达到0.9645和0.8559。
英文摘要：
Near- and duplicate image detection is a critical concern in the field of medical imaging. Medical datasets often contain similar or duplicate images from various sources, which can lead to significant performance issues and evaluation biases, especially in machine learning tasks due to data leakage between training and testing subsets. In this paper, we present an approach for identifying near- and duplicate 3D medical images leveraging publicly available 2D computer vision embeddings. We assessed our approach by comparing embeddings extracted from two state-of-the-art self-supervised pretrained models and two different vector index structures for similarity retrieval. We generate an experimental benchmark based on the publicly available Medical Segmentation Decathlon dataset. The proposed method yields promising results for near- and duplicate image detection achieving a mean sensitivity and specificity of 0.9645 and 0.8559, respectively.
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。
