Evaluation of Therapeutic Effects of Computed Tomography Imaging Classification Algorithm-Based Transcatheter Arterial Chemoembolization on Primary Hepatocellular Carcinoma

• Published in: Computational intelligence and neuroscience Vol. 2022; pp. 1 - 9
• Main Authors: Li, Qiang, Luo, Guang, Li, Jian
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2022; John Wiley & Sons, Inc
• Subjects: Algorithms; Cancer; Carcinoma, Hepatocellular - diagnostic imaging; Carcinoma, Hepatocellular - therapy; Care and treatment; Chemoembolization; Chemoembolization, Therapeutic; Classification; Computed tomography; CT imaging; Data mining; Evaluation; Feature extraction; Health aspects; Hepatocellular carcinoma; Hepatoma; Heterogeneity; Histograms; Humans; Image acquisition; Image processing; Image segmentation; Lagrange multiplier; Learning algorithms; Liver cancer; Liver Neoplasms - diagnostic imaging; Liver Neoplasms - therapy; Machine learning; Mathematical models; Medical imaging; Multiphase; Parameter sensitivity; Patients; Retrospective Studies; Support vector machines; Texture; Tomography; Tomography, X-Ray Computed; Tumors; China
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2022/5639820

To investigate the evaluation of therapeutic effects of computerized tomography (CT) imaging machine learning classification algorithm-based transcatheter arterial chemoembolization (TACE) on primary hepatocellular carcinoma (PHC), machine learning algorithm was optimized to propose the feature extraction of soft margin, analyze CT images, and acquire relevant texture features to assess if it can predict the multistage features of PHC for the application of the therapeutic effects of TACE on PHC. Besides, PHC patients receiving surgical excision were retrospectively collected, and then 483 patients with hepatocellular carcinoma (HCC) were determined from cases. After that, a total of 162 cases meeting the standards were selected. Besides, the features of images were classified and analyzed by machine learning algorithm, and volume of interest (VOI) images of patients in each group were acquired by image segmentation layer by layer. In addition, the texture features of images were extracted. The results showed that 5 CT image-based texture features, including 2 histogram features and 3 matrix-based features, all described the specificity and heterogeneity of tumors. The analysis of the diagnostic effectiveness of the evaluation of response group by each texture parameter demonstrated that its sensitivity, specificity, and area under curve (AUC) were 83.63%, 90.91%, and 0.08%, respectively. Based on CT prediction, machine learning algorithm was fused to realize excellent classification effects on multistage and multiphase features and offer imaging support to the clinical selection of reasonable therapeutic plans. In addition, multiphase and multifeature-based medical tumor classification method was put forward.