期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2018
卷号：6
期号：6
页码：6337-6344
DOI：10.15680/IJIRCCE.2018.0606036
出版社：S&S Publications
摘要：Segmentation of Magnetic Resonance Imaging (MRI) and Computed Topography (CT) scan images in
medical analysis, especially brain , plays a vital role to inform major decisions of a particular disease. It is important to
be able to detect when an automatic method fails to avoid inclusion of wrong measurements into subsequent analysis
which could otherwise lead to incorrect conclusion. Sometimes due to absence of Ground Truth (manually labeled)
(GT) images it is difficult to detect the failure of automatic segmentation methods. Before deployment, performance is
quantified using different metrics. In some exceptional cases it becomes difficult to know about its real performance
after deployment when a reference is unavailable. To that end, this work aims to develop an improved and advanced
technique of Reverse Classification Accuracy (RCA) on new data which enables us to discriminate between the
successful and failed cases. Segmentation quality, performance and failure are assessed by considering the evaluation
metrics like Hausdorff distance (HD) and Average surface distance (ASD) and novel Random Forest algorithm for
Classi_cation purpose. Further, for correctly and accurately segmented and classified brain MRI and CT scan images,
early stages of Alzheimers disease (AD) are being detected using Random forest algorithm.
