Brain Tumors Classification Based on 3D Shape

Brain tumors are the second leading cause of cancer death in children under 15 years and young adults up to the age of 34, early detection and correct treatments based on accurate diagnosis are important steps to improve disease outcome. In this paper, a new method for brain tumors identification based on quantitative three-dimensional shape analysis is proposed. According to the character of magnetic resonance imaging (MRI) data and doctor’s clinical experience, we defined three two-dimensional shape descriptors correlating with tumor type from different points of view; on this basis, four three-dimensional shape descriptors were defined to realize the automatic classification of brain tumors. The experiment result demonstrates that these shape descriptors can well represent the tumor character. The classification accuracy of regular/irregular tumor is 93.93% and that of benign/malignant tumor is 87.14%. To regular benign (RB)/regular malignant (RM)/irregular benign (IB)/irregular malignant (IM), the classification accuracy is 86.43%. This method can be used as a clinical image analysis tool for doctors or radiologists to tumor identification.