基于内容的多类体数据放射学图像检索：一项基准研究
Content-Based Image Retrieval for Multi-Class Volumetric Radiology Images: A Benchmark Study
- Bayer AG（拜耳公司）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文针对三维医学图像检索缺乏基准的问题，基于TotalSegmentator数据集构建多器官体数据与区域级检索基准，并采用后期交互重排序方法在多种解剖结构上实现了1.0的检索召回率。
中文摘要 AI 辅助
尽管基于内容的图像检索（CBIR）在自然图像检索中已被广泛研究，但其在医学图像中的应用仍面临持续挑战，主要原因是医学图像具有三维特性。近期研究表明，预训练视觉嵌入在放射学图像检索的CBIR中具有潜在应用价值。然而，目前仍缺乏针对三维体数据医学图像检索的基准，这阻碍了对医学成像中各类CBIR方法效率的客观评估与比较。在本研究中，我们扩展了先前工作，并利用具有详细多器官标注的TotalSegmentator数据集（TS）建立了一个面向区域级和局部化多器官检索的基准。我们在体数据级和区域级上，对来自医学图像预训练监督模型的嵌入与来自非医学图像预训练无监督模型的嵌入进行了基准测试，覆盖29个粗粒度解剖结构和104个细粒度解剖结构。对于体数据图像检索，我们采用了一种受文本匹配启发的后期交互重排序方法。我们将其与先前针对体数据和区域检索提出的原始方法进行了比较，并在尺寸范围广泛的多种解剖区域上实现了1.0的检索召回率。本文提出的发现和方法为医学成像背景下CBIR方法的进一步发展和评估提供了见解与基准。
英文摘要
While content-based image retrieval (CBIR) has been extensively studied in natural image retrieval, its application to medical images presents ongoing challenges, primarily due to the 3D nature of medical images. Recent studies have shown the potential use of pre-trained vision embeddings for CBIR in the context of radiology image retrieval. However, a benchmark for the retrieval of 3D volumetric medical images is still lacking, hindering the ability to objectively evaluate and compare the efficiency of proposed CBIR approaches in medical imaging. In this study, we extend previous work and establish a benchmark for region-based and localized multi-organ retrieval using the TotalSegmentator dataset (TS) with detailed multi-organ annotations. We benchmark embeddings derived from pre-trained supervised models on medical images against embeddings derived from pre-trained unsupervised models on non-medical images for 29 coarse and 104 detailed anatomical structures in volume and region levels. For volumetric image retrieval, we adopt a late interaction re-ranking method inspired by text matching. We compare it against the original method proposed for volume and region retrieval and achieve a retrieval recall of 1.0 for diverse anatomical regions with a wide size range. The findings and methodologies presented in this paper provide insights and benchmarks for further development and evaluation of CBIR approaches in the context of medical imaging.
