IEEE J Biomed Health Inform. 2015 Sep;19(5):1734-46. doi: 10.1109/JBHI.2014.2361318. Epub 2014 Oct 3.
Content-based image retrieval (CBIR) is a search technique based on the similarity of visual features and has demonstrated potential benefits for medical diagnosis, education, and research. However, clinical adoption of CBIR is partially hindered by the difference between the computed image similarity and the user's search intent, the semantic gap, with the end result that relevant images with outlier features may not be retrieved. Furthermore, most CBIR algorithms do not provide intuitive explanations as to why the retrieved images were considered similar to the query (e.g., which subset of features were similar), hence, it is difficult for users to verify if relevant images, with a small subset of outlier features, were missed. Users, therefore, resort to examining irrelevant images and there are limited opportunities to discover these "missed" images. In this paper, we propose a new approach to medical CBIR by enabling a guided visual exploration of the search space through a tool, called visual analytics for medical image retrieval (VAMIR). The visual analytics approach facilitates interactive exploration of the entire dataset using the query image as a point-of-reference. We conducted a user study and several case studies to demonstrate the capabilities of VAMIR in the retrieval of computed tomography images and multimodality positron emission tomography and computed tomography images.
基于内容的图像检索（CBIR）是一种基于视觉特征相似性的搜索技术，已被证明对医学诊断、教育和研究具有潜在的益处。然而，由于计算出的图像相似性与用户的搜索意图（即语义鸿沟）之间存在差异，临床应用 CBIR 受到了部分阻碍，其结果是可能无法检索到具有异常特征的相关图像。此外，大多数 CBIR 算法并未提供直观的解释，说明为什么检索到的图像与查询相似（例如，哪些特征子集相似），因此，用户很难验证是否遗漏了具有小部分异常特征的相关图像。因此，用户只能通过检查不相关的图像来解决问题，并且发现这些“遗漏”图像的机会有限。在本文中，我们通过一种名为医学图像检索的可视化分析工具（VAMIR），提出了一种新的医学 CBIR 方法，从而能够引导对搜索空间进行可视化探索。可视化分析方法通过将查询图像用作参考点，促进了对整个数据集的交互式探索。我们进行了用户研究和几个案例研究，以展示 VAMIR 在计算断层扫描图像以及多模态正电子发射断层扫描和计算机断层扫描图像检索中的功能。
