Goudas Theodosios, Doukas Charalampos, Chatziioannou Aristotle, Maglogiannis Ilias
University of Central Greece, Department of Computer Science and Biomedical Informatics, Greece.
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:4414-7. doi: 10.1109/EMBC.2012.6346945.
Correct annotation and identification of salient regions in Kidney biopsy images can provide an estimation of pathogenesis in obstructive nephropathy. This paper presents a tool for the automatic or manual segmentation of such regions along with methodology for their characterization in terms of the exhibited pathology. The proposed implementation is based on custom code written in Java and the utilization of open source tools (i.e. RapidMiner, ImageJ). The corresponding implementation details along with the initial evaluation of the proposed integrated system are also presented in the paper.
正确标注和识别肾活检图像中的显著区域可以为梗阻性肾病的发病机制提供评估。本文介绍了一种用于自动或手动分割此类区域的工具,以及根据所呈现的病理学特征对其进行表征的方法。所提出的实现基于用Java编写的自定义代码以及开源工具(即RapidMiner、ImageJ)的使用。本文还介绍了相应的实现细节以及对所提出的集成系统的初步评估。