Unsupervised Classification of Cerebrospinal Fluid by Statistical Indicators

Cross section area (CSA) of spinal canal has been a crucial indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for elder people. Recently, the machine learning algorithms have been investigated in[7-10] for automatic classification systems. The methods investigated in[7-10] exploited the characteristics of cerebrospinal fluid (CSF) in T1 and T2 sequences of MRI images. Nevertheless, in order to apply the trained classifiers, the differences among images need to be as small as possible due to the nature of classification. To address the issue, this paper reinvented the wheel to propose unsupervised segmentation method without requirement of training process. Based on the characteristic property of skewness, the proposed algorithm can also distinguish the finer details such as nerve roots from CSF. The experimental study further demonstrated the benefits of proposed framework.