Magnetic resonance imaging evaluation of vertebral tumor prediction using hierarchical hidden Markov random field model on Internet of Medical Things (IOMT) platform

摘要

Recently, prediction evaluation of the metastatic spine tumors in therapy is considered a significant area of research. Further, for spinal clinical diagnoses, a large amount of image data from different modalities is often used and interchangeably analyzed based on the automatic vertebra identification. It includes recognition of vertebral positions and recognition in several image modalities. Due to the differences in MR or CT images appearance or shape/size of the vertebras, the identification is however difficult in the present conventional medical research. The segmentation of vertebral tumors that are manually performed by MRI is an important and time-consuming process by the conventional research algorithms. The accuracy of identification of the size and location of spine tumors plays a major role in effective tumor diagnosis and treatment. Therefore, this paper presents the Hierarchical Hidden Markov Random Field Model (HHMRF) to predict the vertebral tumor for the early detection and diagnosis treatment in an effective and efficient manner. The importance of this research is to implement a state-of-the-art strategy for detection of tumors using HHMRF and threshold techniques in MRI images on the Internet of Medical Things Platform (IoMT). HHMRF can coordinate the final section of vertebral tumor homogeneous areas of tissue while preserving the edges between different tissue constituents more effectively using mathematical computation. The proposed method attains the state-of-the-art performance on the diagnosis and segmentation of lumbar spinal stenosis using deep neural network and experimentally analyzed with 97.44% accuracy and 97.11% efficiency ratio on IoMT platform whereas proposed HHMRF achieves 98.5% high precision ratio compared to other existing TDCN (78.2%), DLA (81.6%), M-CNN (78.9%), and DCE-MRI (80.2%) methods. (C) 2020 Elsevier Ltd. All rights reserved.