Unsupervised classification of cross-section area of spinal canal

Cross section area (CSA) of spinal canal has been an important indicator for lumbar spinal stenosis (LSS), which remains the leading preoperative diagnosis for adults older than 65 years. Due to its irregularity in spatial shape and lack of spectral information, it is a challenging issue to utilize machine learning algorithms to classify this region accurately. Recently, two studies [1,2] shed some light on this topic by considering its spectral information jointly with spatial one as features and evaluated the performance of three popular machine learning algorithms for classification and measurement of CSA. Their experimental studies indicated that it is feasible to classify the CSA region based on its spectral and spatial information. However, the accuracy heavily relies on decent training samples picked from a region which could only be provided from manual marks of experienced doctors. This manuscript aimed to propose an automatic method to remove requirement of human intervention to determine the training region, and further make the supervised classification methods proposed in [1,2] become unsupervised classification methods. The utility and robustness of the proposed method would be demonstrated by the figures and statistical chart presented in the experimental section.