Rossi Alberto, Giacomini Giorgia, Cicaloni Vittoria, Galderisi Silvia, Milella Maria Serena, Bernini Andrea, Millucci Lia, Spiga Ottavia, Bianchini Monica, Santucci Annalisa
University of Florence, Department of Information Engineering, Via di Santa Marta, Florence, Italy; University of Siena, Department of Information Engineering and Mathematics, Via Roma 56, Siena, Italy.
University of Siena, Department of Biotechnology, Chemistry and Pharmacy, Via Aldo Moro 2, Siena, Italy; University of Siena, Department of Information Engineering and Mathematics, Via Roma 56, Siena, Italy.
Comput Biol Med. 2020 Jul;122:103863. doi: 10.1016/j.compbiomed.2020.103863. Epub 2020 Jun 18.
ApreciseKUre is a multi-purpose digital platform facilitating data collection, integration and analysis for patients affected by Alkaptonuria (AKU), an ultra-rare autosomal recessive genetic disease. We present an ApreciseKUre plugin, called AKUImg, dedicated to the storage and analysis of AKU histopathological slides, in order to create a Precision Medicine Ecosystem (PME), where images can be shared among registered researchers and clinicians to extend the AKU knowledge network. AKUImg includes a new set of AKU images taken from cartilage tissues acquired by means of a microscopic technique. The repository, in accordance to ethical policies, is publicly available after a registration request, to give to scientists the opportunity to study, investigate and compare such precious resources. AKUImg is also integrated with a preliminary but accurate predictive system able to discriminate the presence/absence of AKU by comparing histopatological affected/control images. The algorithm is based on a standard image processing approach, namely histogram comparison, resulting to be particularly effective in performing image classification, and constitutes a useful guide for non-AKU researchers and clinicians.
ApreciseKUre是一个多用途数字平台，为患有黑尿症（AKU，一种极其罕见的常染色体隐性遗传病）的患者提供数据收集、整合和分析服务。我们展示了一个名为AKUImg的ApreciseKUre插件，专门用于存储和分析AKU组织病理学切片，以创建一个精准医疗生态系统（PME），在这个系统中，图像可以在注册的研究人员和临床医生之间共享，以扩展AKU知识网络。AKUImg包含一组新的AKU图像，这些图像取自通过显微技术获取的软骨组织。根据伦理政策，该存储库在收到注册请求后向公众开放，以便科学家有机会研究、调查和比较这些珍贵资源。AKUImg还集成了一个初步但准确的预测系统，该系统能够通过比较组织病理学受影响/对照图像来判别是否存在AKU。该算法基于一种标准的图像处理方法，即直方图比较，在执行图像分类方面特别有效，并且为非AKU研究人员和临床医生提供了有用的指导。
