Improving Parotid Gland Tumor Segmentation and Classification Using Geometric Active Contour Model and Deep Neural Network Framework

Manual assessment of parotid gland status from magnetic resonance imaging is a subjective, time consuming and error prone process. Automatic image analysis methods offer the possibility to get consistent, objective rapid diagnoses tumor. In this kind cancer, large variety in their characteristics, that brings various difficulties for traditional methods. paper, we propose an automatic method perform both segmentation classification Parotid region order give quantitative uniform indicators PGs will help pathologists diagnostic. The experimental result illustrates high accuracy results proposed compared ground truth. Furthermore, comparative study with existing techniques presented demonstrate efficiency superiority method.