Abstract
To investigate the application of Magnetic Resonance Imaging (MRI) combined with Computed Tomography (CT) scan images based on deep learning in the evaluation of postoperative TACE efficacy as well as the prevention and treatment measures of Vasovagal Reflex (VVR). A total of 256 patients who were diagnosed with primary liver cancer in our hospital and were treated with Transcatheter Arterial Chemoembolization (TACE) for liver cancer. They were divided into a combined group (110 cases) and a control group (146 cases). The combined group underwent MRI and CT after the operation. The control group only underwent an MRI examination. To explore the role of CT and MRI images based on deep learning in the evaluation of interventional therapy for liver cancer, the MRI and CT images were processed by establishing a Convolutional Neural Networks (CNN) model. Then, the image information was counted and analyzed. The segmentation effect of the residual situation of the MRI and CT image enhancement regions processed by the deep learning model was relatively good, and can accurately display the presence of the lesion. Also, the diagnostic efficiency was above 0.7, and the diagnostic efficiency was better. The sensitivity, specificity, accuracy, and negative predictive value of diagnosis in the control group were significantly lower than those in the combined group (P < 0.05). After the measurement, the minimum short diameter of the control group was significantly higher than that of the combined group (P < 0.05). Proposed specific preventive measures for VVR from the three aspects, before, during, and after TACE surgery, can reduce the adverse consequences caused by VVR. The methods of the investigation can improve the accuracy of the effect evaluation after TACE treatment, reduce the occurrence of complications and adverse consequences, thereby improving the therapeutic effect of liver cancer patients.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.