{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["12"],"submitter":["Zhang Y"],"pubmed_abstract":["<h4>Background and aims</h4>Microvascular invasion (MVI) is a well-known risk factor for poor prognosis in hepatocellular carcinoma (HCC). This study aimed to develop a deep convolutional neural network (DCNN) model based on contrast-enhanced ultrasound (CEUS) to predict MVI, and thus to predict prognosis in patients with HCC.<h4>Methods</h4>A total of 436 patients with surgically resected HCC who underwent preoperative CEUS were retrospectively enrolled. Patients were divided into training (<i>n</i> = 301), validation (<i>n</i> = 102), and test (<i>n</i> = 33) sets. A clinical model (Clinical model), a CEUS video-based DCNN model (CEUS-DCNN model), and a fusion model based on CEUS video and clinical variables (CECL-DCNN model) were built to predict MVI. Survival analysis was used to evaluate the clinical performance of the predicted MVI.<h4>Results</h4>Compared with the Clinical model, the CEUS-DCNN model exhibited similar sensitivity, but higher specificity (71.4% vs. 38.1%, <i>p</i> = 0.03) in the test group. The CECL-DCNN model showed significantly higher specificity (81.0% vs. 38.1%, <i>p</i> = 0.005) and accuracy (78.8% vs. 51.5%, <i>p</i> = 0.009) than the Clinical model, with an AUC of 0.865. The Clinical predicted MVI could not significantly distinguish OS or RFS (both <i>p</i> > 0.05), while the CEUS-DCNN predicted MVI could only predict the earlier recurrence (hazard ratio [HR] with 95% confidence interval [CI 2.92 [1.1-7.75], <i>p</i> = 0.024). However, the CECL-DCNN predicted MVI was a significant prognostic factor for both OS (HR with 95% CI: 6.03 [1.7-21.39], <i>p</i> = 0.009) and RFS (HR with 95% CI: 3.3 [1.23-8.91], <i>p</i> = 0.011) in the test group.<h4>Conclusions</h4>The proposed CECL-DCNN model based on preoperative CEUS video can serve as a noninvasive tool to predict MVI status in HCC, thereby predicting poor prognosis."],"journal":["Frontiers in oncology"],"pagination":["878061"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9300962"],"repository":["biostudies-literature"],"pubmed_title":["Deep Learning of Liver Contrast-Enhanced Ultrasound to Predict Microvascular Invasion and Prognosis in Hepatocellular Carcinoma."],"pmcid":["PMC9300962"],"pubmed_authors":["Cao L","Liao Y","Hu Y","Mao R","Li Q","Yu J","Zhou X","Li L","Zou X","Yao Z","Huang Y","Wei Q","Zhang Y","Yan C","Han J","Wang Y","Lin M","Tang X","Zhou J"],"additional_accession":[]},"is_claimable":false,"name":"Deep Learning of Liver Contrast-Enhanced Ultrasound to Predict Microvascular Invasion and Prognosis in Hepatocellular Carcinoma.","description":"<h4>Background and aims</h4>Microvascular invasion (MVI) is a well-known risk factor for poor prognosis in hepatocellular carcinoma (HCC). This study aimed to develop a deep convolutional neural network (DCNN) model based on contrast-enhanced ultrasound (CEUS) to predict MVI, and thus to predict prognosis in patients with HCC.<h4>Methods</h4>A total of 436 patients with surgically resected HCC who underwent preoperative CEUS were retrospectively enrolled. Patients were divided into training (<i>n</i> = 301), validation (<i>n</i> = 102), and test (<i>n</i> = 33) sets. A clinical model (Clinical model), a CEUS video-based DCNN model (CEUS-DCNN model), and a fusion model based on CEUS video and clinical variables (CECL-DCNN model) were built to predict MVI. Survival analysis was used to evaluate the clinical performance of the predicted MVI.<h4>Results</h4>Compared with the Clinical model, the CEUS-DCNN model exhibited similar sensitivity, but higher specificity (71.4% vs. 38.1%, <i>p</i> = 0.03) in the test group. The CECL-DCNN model showed significantly higher specificity (81.0% vs. 38.1%, <i>p</i> = 0.005) and accuracy (78.8% vs. 51.5%, <i>p</i> = 0.009) than the Clinical model, with an AUC of 0.865. The Clinical predicted MVI could not significantly distinguish OS or RFS (both <i>p</i> > 0.05), while the CEUS-DCNN predicted MVI could only predict the earlier recurrence (hazard ratio [HR] with 95% confidence interval [CI 2.92 [1.1-7.75], <i>p</i> = 0.024). However, the CECL-DCNN predicted MVI was a significant prognostic factor for both OS (HR with 95% CI: 6.03 [1.7-21.39], <i>p</i> = 0.009) and RFS (HR with 95% CI: 3.3 [1.23-8.91], <i>p</i> = 0.011) in the test group.<h4>Conclusions</h4>The proposed CECL-DCNN model based on preoperative CEUS video can serve as a noninvasive tool to predict MVI status in HCC, thereby predicting poor prognosis.","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022","modification":"2025-04-25T19:44:52.999Z","creation":"2025-04-06T08:07:40.303Z"},"accession":"S-EPMC9300962","cross_references":{"pubmed":["35875110"],"doi":["10.3389/fonc.2022.878061"]}}