Development And Applications Of The Open Microscopy Environment (OME)

在过去的几年里，我们重写了OME分析系统，使其更加健壮和高效(1)，增加了国际化层，包括将用户界面和底层语义框架完整地翻译成西班牙语，并为我们的合作做出了贡献，进一步完善了OME的用户界面及其底层基础设施(6)。然而，今年这个项目的大部分工作是对我们已经工作了几年的WND-Charm模式识别算法的验证。 WND-Charm是一种通用的模式识别算法，可用于分析任何类型的图像。我们已经使用机器视觉社区用于模式识别的标准基准套件来验证该方法的准确性和通用性，包括人脸识别、目标识别和其他非生物分类问题(2)。 由于缺乏面向生物和医学的机器视觉基准，我们开发了自己的基准套件，以培养更广泛的机器视觉社区的兴趣。这包括超过20 GB的图像数据，涉及11个不同的生物成像问题，从亚细胞细胞器识别到基于图像的筛选，再到医疗诊断。还介绍了不同的成像方式，包括荧光显微镜、差分干涉对比度、位相对比度和H&E染色亮场。这一图像收集和基准已向公众免费提供(http://ome.grc.nia.nih.gov/iicbu2008)(5)。 我们执行的WND-Charm验证之一来自我们在医学成像项目(AG000685-02：医学成像中的模式识别)中使用的图像数据集。在这里，我们能够使用膝关节X光进行生物识别，这是我们所知道的第一个使用内部组织结构来识别个人的例子(3)。 虽然WND-Charge还没有完全与OME集成，但我们发布了该实用程序的源代码以及它在成像问题上的实际应用的“现场手册”(4)。 来年，我们计划测试WND-Charm与我们现有的OME平台以及在苏格兰邓迪的Swedlow博士的实验室正在开发的Omero平台的集成。WND-Charm的计算量非常大，对图像信息学框架提出了巨大的要求，以便为其提供图像以进行分析以及消费和组织其输出。这两个系统的相对性能将是决定使用两个平台中的哪一个进行集成的关键。

In previous years, we've re-written the OME analysis system to make it more robust and efficient (1), added an internationalization layer that includes a complete translation of both the user interface and the underlying semantic framework into Spanish, and have contributed to our collaborations that have further refined OME's user interface, as well as its underlying infrastructure (6). However, the bulk of the work in this project this year has been the validation of the WND-CHARM pattern recognition algorithm we have worked on for several years. WND-CHARM is a generalized pattern-recognition algorithm that can be used to analyze any type of image. We have validated the accuracy and generality of this approach using standard benchmark suites used for pattern recognition by the machine vision community, including face recognition, object recognition, and other non-biological classification problems (2). Due to the lack of biologically and medically oriented machine-vision benchmarks, we have developed our own benchmark suite to foster interest by the wider machine vision community. This comprises over 20 GB of image data spanning 11 different biological imaging problems, ranging from sub-cellular organelle identification to image-based screening, to medical diagnosis. Different imaging modalities are also represented including fluorescence microscopy, differential-interference contrast, phase-contrast and H&E stained brightfield. This image collection and benchmark has been made freely available to the public (http://ome.grc.nia.nih.gov/iicbu2008) (5). One of the WND-CHARM validations we performed resulted from an image dataset we used in our medical imaging project (AG000685-02: Pattern recognition in medical imaging). Here we were able to use knee X-Rays for biometric identification, which is the first example we are aware of that used internal tissue structures to identify individuals (3). While WND-CHARM is not yet fully integrated with OME, we published the source-code for this utility as well as a "field manual" for its practical applications to imaging problems (4). In the coming year, we plan to test integrations of WND-CHARM with our existing OME platform as well as the OMERO platform being developed in Dr. Swedlow's lab in Dundee, Scotland. WND-CHARM is very computationally intensive and places enormous demands on an image informatics framework to supply it with images to analyze as well as consume and organize its outputs. The relative performance of these two systems will be critical for determining which of the two platforms to use in integration.