Vertebral Tumor Detection and Segmentation Using Analytical Transform Assisted Statistical Characteristic Decomposition Model

Recently, vertebral tumor prediction using image-based vertebral bio-mathematical modeling with accurate segmentation has been considered as a significant area of research. Further, precise lumbar spinal segmentation is essential to the clinicians for tumor analysis. Therefore, precise and reliable segmentation process is required to help radiologists and doctors to identify different vertebrae tumors with better prediction ratio. The exact vertebral disks segmentation of spinal bones from medical images is a complex process in dealing with different deformities and pathologies in accordance to the conventional techniques such as Deep Convolutional Neural Network (DCNN), Finite Element Analysis (FEA), Principal Component and Factor Analysis (PCFA), Multi-Parameter Ensemble Learning (MPEL), Hierarchical Conditional Random Forest (HCRF), and Deep Siamese Neural Network (DSNN). Therefore, to overcome the present drawbacks, Analytical Transform Assisted Statistical Characteristic Decomposition Model (ATS-CDM) is proposed in this paper for the accurate prediction of vertebral tumor detection and segmentation. This technique is used for the calibration of the segmentation procedures in vertebral tumor image prediction and Receiver Operating Curve (ROC) grading for the lumbar spines. The significant objective of the model-fitting algorithm iterates the tumor regions and measures the current region's variance for the accurate identification of tumor. The outcomes show potential and promising results at lab scale evaluation through analyzing the vertebral datasets with Intra-Discal Pressure (IDP) images for experimental validation with 98.7% bending and 98.88 % segmentation accuracy leads to 94.2 ± 0.2 % to 97.02 ± 0.2 % average ROCgrading.