Instituto de Engenharia Electrónica e Informática de Aveiro, DETI / IEETA - University of Aveiro, Campus Universitário de Santiago, 3810-193, Aveiro, Portugal.
J Med Syst. 2018 Jun 29;42(8):145. doi: 10.1007/s10916-018-1004-8.
The combination of textual data with visual features is known to enhance medical image search capabilities. However, the most advanced imaging archives today only index the studies' available meta-data, often containing limited amounts of clinically useful information. This work proposes an anatomic labeling architecture, integrated with an open source archive software, for improved multimodal content discovery in real-world medical imaging repositories. The proposed solution includes a technical specification for classifiers in an extensible medical imaging archive, a classification database for querying over the extracted information, and a set of proof-of-concept convolutional neural network classifiers for identifying the presence of organs in computed tomography scans. The system automatically extracts the anatomic region features, which are saved in the proposed database for later consumption by multimodal querying mechanisms. The classifiers were evaluated with cross-validation, yielding a best F1-score of 96% and an average accuracy of 97%. We expect these capabilities to become common-place in production environments in the future, as automated detection solutions improve in terms of accuracy, computational performance, and interoperability.
文本数据与视觉特征的结合被认为可以增强医学图像搜索能力。然而，当今最先进的成像档案仅对研究可用的元数据进行索引，这些元数据通常包含有限数量的临床有用信息。这项工作提出了一种解剖标记架构，与开源档案软件集成，用于改进真实世界医学成像存储库中的多模态内容发现。所提出的解决方案包括可扩展医学成像档案中的分类器技术规范、用于查询提取信息的分类数据库以及一组用于识别计算机断层扫描中器官存在的概念验证卷积神经网络分类器。该系统自动提取解剖区域特征，并将其保存在所提出的数据库中，以便以后通过多模态查询机制使用。使用交叉验证对分类器进行了评估，最佳 F1 得分为 96%，平均准确率为 97%。我们预计，随着自动化检测解决方案在准确性、计算性能和互操作性方面的不断提高，这些功能将在未来成为生产环境中的常见功能。
