Deep convolutional neural network for preoperative prediction of microvascular invasion and clinical outcomes in patients with HCCs

Li, Xinming; Qi, Zhendong; Du, Haiyan; Geng, Zhimin; Li, Zhipeng; Qin, Shuping; Zhang, Xuhui; Liang, Jianye; Zhang, Xiao; Wen, Liang; Yang, Wei; Xie, Chengsong; Quan, Xianyue

doi:10.1007/s00330-021-08198-w

Cited by 19 publications

(17 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interestingly, we found that, the younger the age, the worse the prognosis in the present study, which was inconsistent with some prior studies ( 27 , 28 ). However, Giannini et al ( 29 ) reported that older patients seem to have better prognosis than younger patients, most likely due to HCC characteristics, since older patients seem to have better pathological grades, as confirmed by Li et al ( 30 ). Younger patients had more aggressive tumor factors than older patients, although they had better liver functional reserve ( 31 , 32 ).…”

Section: Discussionmentioning

confidence: 85%

Nomograms for Predicting Hepatocellular Carcinoma Recurrence and Overall Postoperative Patient Survival

Deng

Zhang

et al. 2022

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

BackgroundFew studies have focused on the prognosis of patients with hepatocellular carcinoma (HCC) of Barcelona Clinic Liver Cancer (BCLC) stage 0‒C in terms of early recurrence and 5-years overall survival (OS). We sought to develop nomograms for predicting 5-year OS and early recurrence after curative resection of HCC, based on a clinicopathological‒radiological model. We also investigated whether different treatment methods influenced the OS of patients with early recurrence.MethodsRetrospective data, including clinical pathology, radiology, and follow-up data, were collected for 494 patients with HCC who underwent hepatectomy. Nomograms estimating OS and early recurrence were constructed using multivariate Cox regression analysis, based on the random survival forest (RSF) model. We evaluated the discrimination and calibration abilities of the nomograms using concordance indices (C-index), calibration curves, and Kaplan‒Meier curves. OS curves of different treatments for patients who had recurrence within 2 years after curative surgery were depicted and compared using the Kaplan–Meier method and the log-rank test.ResultsMultivariate Cox regression revealed that BCLC stage, non-smooth margin, maximum tumor diameter, age, aspartate aminotransferase levels, microvascular invasion, and differentiation were prognostic factors for OS and were incorporated into the nomogram with good predictive performance in the training (C-index: 0.787) and testing cohorts (C-index: 0.711). A nomogram for recurrence-free survival was also developed based on four prognostic factors (BCLC stage, non-smooth margin, maximum tumor diameter, and microvascular invasion) with good predictive performance in the training (C-index: 0.717) and testing cohorts (C-index: 0.701). In comparison to the BCLC staging system, the C-index (training cohort: 0.787 vs. 0.678, 0.717 vs. 0.675; external cohort 2: 0.748 vs. 0.624, 0.729 vs. 0.587 respectively, for OS and RFS; external cohort1:0.716 vs. 0.627 for RFS, all p value<0.05), and model calibration curves all showed improved performance. Patients who underwent surgery after tumor recurrence had a higher reOS than those who underwent comprehensive treatments and supportive care.ConclusionsThe nomogram, based on clinical, pathological, and radiological factors, demonstrated good accuracy in estimating OS and recurrence, which can guide follow-up and treatment of individual patients. Reoperation may be the best option for patients with recurrence in good condition.

show abstract

Section: Discussionmentioning

confidence: 85%

Nomograms for Predicting Hepatocellular Carcinoma Recurrence and Overall Postoperative Patient Survival

Deng

Zhang

et al. 2022

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among the selected studies, we found that the mean age of patients across the studies was 56 years, with the study size ranging between 16 [12] and 7512 [13] subjects with HCC. Many of the studies (n=24, 67%) used either Computed Tomography (CT) or Magnetic Resonance Imaging (MRI) scans as the basis of their algorithm development [12][13][14]16,17,[19][20][21][22][23][24][25][28][29][30][31][33][34][35]39,40,[42][43][44]. A modest number of images (100 to 1000) were used for these studies, except for Kim et.…”

Section: Resultsmentioning

confidence: 99%

“…However, studies using Ultrasonics [36] and DL radiomics based on Contrast-Enhanced Ultrasound (CEUS) [32] were based on Ultrasound images. Although all studies showed different AI models, 3 (21%) studies used CNN, Residual CNN and Deep Convolutional Network (DCNN) that were based on a common algorithm of CNN [13,33,35]. The fusion model, CNN and DCNN mainly helped to predict the postoperative microvascular invasion of HCC with an AUC of 0.81, 0.79 and 0.92, respectively [13,35,40].…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence Used for the Diagnosis, Treatment and Surveillance of Hepatocellular Carcinoma: A Systematic Review

2022

URNCST Journal

View full text Add to dashboard Cite

Introduction: Hepatocellular Carcinoma (HCC) is the most common type of liver cancer, compromising about 75% of all liver cancers. The advancement in artificial intelligence (AI) has paved the way in the field of liver cancers to help clinicians with early diagnosis, treatment guidance and surveillance for HCC. The aim of this review was to summarize different AI-assisted methods that could be used in the diagnosis, treatment, and surveillance of HCC throughout the literature. Methods: PubMed and MEDLINE OVID databases were searched for primary studies involving AI and HCC published from 2012 to February 2022. Data was obtained, including study characteristics and outcome measures: accuracy, area under curve (AUC), specificity, sensitivity, and errors. A narrative synthesis was used to summarize the findings. Results: The systematic search produced 340 studies, of which 36 met the pre-determined eligibility criteria. The studies were published between 2012 to 2020. All the studies with their respective AI models/algorithms were described and summarized in the tables according to their role in the diagnosis, treatment, or surveillance of HCC. All the studies included used different AI algorithms, out of which, most were used for diagnostic purposes (44%), followed by treatment prediction (38%) and then surveillance of HCC (18%). Among studies, 38% reported their results as AUC, 33% of the studies reported accuracy, 19% reported sensitivity and specificity, 4% reported concordance indices (C-indices), 3% reported the mean errors and 2% reported AUROC values for respective AI models used. The accuracy of the diagnostic, treatment and surveillance tools range from 40% to 99%, 50% to 90% and 70% to 95% respectively. Conclusion: Many AI models are available that show promising results for the different applications in diagnosis, treatment, and surveillance of HCC. However, the demand for the generalization of these results remains. Future research should focus on improving the results and accuracy of these algorithms used for HCC to reduce the risks in complicated procedures.

show abstract

“…Hepatocellular carcinoma (HCC) is one of the common malignant tumors and accounts for more than 90% of liver cancers ( 1 , 2 ). Curative hepatectomy is the preferred therapy for patients with HCC ( 3 , 4 ).…”

Section: Introductionmentioning

confidence: 99%

A Clinical-Radiomic Model for Predicting Indocyanine Green Retention Rate at 15 Min in Patients With Hepatocellular Carcinoma

Xie

et al. 2022

Front. Surg.

Self Cite

View full text Add to dashboard Cite

Purpose:The indocyanine green retention rate at 15 min (ICG-R15) is of great importance in the accurate assessment of hepatic functional reserve for safe hepatic resection. To assist clinicians to evaluate hepatic functional reserve in medical institutions that lack expensive equipment, we aimed to explore a novel approach to predict ICG-R15 based on CT images and clinical data in patients with hepatocellular carcinoma (HCC).MethodsIn this retrospective study, 350 eligible patients were enrolled and randomly assigned to the training cohort (245 patients) and test cohort (105 patients). Radiomics features and clinical factors were analyzed to pick out the key variables, and based on which, we developed the random forest regression, extreme gradient boosting regression (XGBR), and artificial neural network models for predicting ICG-R15, respectively. Pearson's correlation coefficient (R) was adopted to evaluate the performance of the models.ResultsWe extracted 660 CT image features in total from each patient. Fourteen variables significantly associated with ICG-R15 were picked out for model development. Compared to the other two models, the XGBR achieved the best performance in predicting ICG-R15, with a mean difference of 1.59% (median, 1.53%) and an R-value of 0.90. Delong test result showed no significant difference in the area under the receiver operating characteristic (AUROCs) for predicting post hepatectomy liver failure between actual and estimated ICG-R15.ConclusionThe proposed approach that incorporates the optimal radiomics features and clinical factors can allow for individualized prediction of ICG-R15 value of patients with HCC, regardless of the specific equipment and detection reagent (NO. ChiCTR2100053042; URL, http://www.chictr.org.cn).

show abstract

Deep convolutional neural network for preoperative prediction of microvascular invasion and clinical outcomes in patients with HCCs

Cited by 19 publications

References 37 publications

Nomograms for Predicting Hepatocellular Carcinoma Recurrence and Overall Postoperative Patient Survival

Nomograms for Predicting Hepatocellular Carcinoma Recurrence and Overall Postoperative Patient Survival

Artificial Intelligence Used for the Diagnosis, Treatment and Surveillance of Hepatocellular Carcinoma: A Systematic Review

A Clinical-Radiomic Model for Predicting Indocyanine Green Retention Rate at 15 Min in Patients With Hepatocellular Carcinoma

Contact Info

Product

Resources

About