Application of a model based on deep learning for predicting recurrence of hepatocellular carcinoma after transarterial chemoembolization
WANG Yuqi
LIU Qiang
SU Meixia
Abstract：Objective Using magnetic resonance imaging,we established a preliminary AI model to evaluate the predictive value of this model for patients with HCC whether they occurred intrahepatic metastasis after the treatment of TACE.Methods 161 patients with HCC who underwent TACE treatment were enrolled as research subjects.The patients were divided into non-metastasis group(n=79)and intrahepatic metastasis group(n=82).All the above patients were subject to magnetic resonance scanners for collecting images before receiving TACE treatment.Then,we established a prediction AI model,evaluated the pre-diction efficiency of this model.13 clinical variables were collected to judge the clinical factors affecting the occurrence of intra-hepatic metastasis after TACE treatment.Results Univariate analysis showed that age,hepatitis,number of tumors and tumor size were risk factors for post-operative intrahepatic metastasis(P<0.05).Multiariable Cox regression analysis showed that tu-mor size(≤5 or>5cm)was an independent risk factor for predicting intrahepatic metastasis.10-fold cross-validation showed that the average accuracy of identification of this AI model reached(68.97±8.18)%,and 95%CI was 0.659～0.841.Conclusion AI model can effectively predict the high-risk recurrence of HCC after TACE treatment.These patients should be closely followed up after treatment and discharge,which is helpful for guiding the clinicians to adjust the treatment mode in time.
Keywords：Liver cancerDeep learningArtificial intelligenceTransarterial chemoembolization
Publication Date：2024-10-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 71-74 )