Prediction Of Microvascular Invasion Research Articles

Prediction of Microvascular Invasion and Recurrence After Curative Resection of LI-RADS Category 5 Hepatocellular Carcinoma on Gd-BOPTA Enhanced MRI

Prediction of Microvascular Invasion and Recurrence After Curative Resection of LI-RADS Category 5 Hepatocellular Carcinoma on Gd-BOPTA Enhanced MRI

Development of a Better Nomogram for Prediction of Preoperative Microvascular Invasion and Postoperative Prognosis in Hepatocellular Carcinoma Patients: A Comparison Study.

Personalized precision medicine can be facilitated by clinically available preoperative microvascular invasion (MVI) prediction models that are reliable and postoperative MVI pathological grade-related recurrence prediction models that are accurate. In this study, we aimed to compare different mathematical models to derive the best preoperative prediction and postoperative recurrence prediction models for MVI. A total of 143 patients with hepatocellular carcinoma (HCC) whose clinical, laboratory, imaging, and pathological data were available were included in the analysis. Logistic regression, Cox proportional hazards regression, LASSO regression with 10-fold cross-validation, stepwise regression, and random forest methods were used for variable screening and predictive modeling. The accuracy and validity of seven preoperative MVI prediction models and five postoperative recurrence prediction models were compared in terms of C-index, net reclassification improvement, and integrated discrimination improvement. Multivariate logistic regression analysis revealed that a preoperative nomogram model with the variables cirrhosis diagnosis, alpha-fetoprotein > 400, and diameter, shape, and number of lesions can predict MVI in patients with HCC reliably. Postoperatively, a nomogram model with MVI grade, number of lesions, capsule involvement status, macrovascular invasion, and shape as the variables was selected after LASSO regression and 10-fold cross-validation analysis to accurately predict the prognosis for different MVI grades. The number and shape of the lesions were the most common predictors of MVI preoperatively and recurrence postoperatively. Our study identified the best statistical approach for the prediction of preoperative MVI as well as postoperative recurrence in patients with HCC based on clinical, imaging, and laboratory tests results. This could expedite preoperative treatment decisions and facilitate postoperative management.

MRI-based clinical-radiomics nomogram model for predicting microvascular invasion in hepatocellular carcinoma.

Preoperative microvascular invasion (MVI) of liver cancer is an effective method to reduce the recurrence rate of liver cancer. Hepatectomy with extended resection and additional adjuvant or targeted therapy can significantly improve the survival rate of MVI+ patients by eradicating micrometastasis. Preoperative prediction of MVI status is of great clinical significance for surgical decision-making and the selection of other adjuvant therapy strategies to improve the prognosis of patients. Established a radiomics machine learning model based on multimodal MRI and clinical data, and analyzed the preoperative prediction value of this model for microvascular invasion (MVI) of hepatocellular carcinoma (HCC). The preoperative liver MRI data and clinical information of 130 HCC patients who were pathologically confirmed to be pathologically confirmed were retrospectively studied. These patients were divided into MVI-positive group (MVI+) and MVI-negative group (MVI-) based on postoperative pathology. After a series of dimensionality reduction analysis, six radiomic features were finally selected. Then, linear support vector machine (linear SVM), support vector machine with rbf kernel function (rbf-SVM), logistic regression (LR), Random forest (RF) and XGBoost (XGB) algorithms were used to establish the MVI prediction model for preoperative HCC patients. Then, rbf-SVM with the best predictive performance was selected to construct the radiomics score (R-score). Finally, we combined R-score and clinical-pathology-image independent predictors to establish a combined nomogram model and corresponding individual models. The predictive performance of individual models and combined nomogram was evaluated and compared by receiver operating characteristic curve (ROC). Alpha-fetoprotein concentration, peritumor enhancement, maximum tumor diameter, smooth tumor margins, tumor growth pattern, presence of intratumor hemorrhage, and RVI were independent predictors of MVI. Compared with individual models, the final combined nomogram model (AUC: 0.968, 95% CI: 0.920-1.000) constructed by radiometry score (R-score) combined with clinicopathological parameters and apparent imaging features showed the optimal predictive performance. This multi-parameter combined nomogram model had a good performance in predicting MVI of HCC, and had certain auxiliary value for the formulation of surgical plan and evaluation of prognosis.

Application of texture signatures based on multiparameter-magnetic resonance imaging for predicting microvascular invasion in hepatocellular carcinoma: Retrospective study.

Despite continuous changes in treatment methods, the survival rate for advanced hepatocellular carcinoma (HCC) patients remains low, highlighting the importance of diagnostic methods for HCC. To explore the efficacy of texture analysis based on multi-parametric magnetic resonance (MR) imaging (MRI) in predicting microvascular invasion (MVI) in preoperative HCC. This study included 105 patients with pathologically confirmed HCC, categorized into MVI-positive and MVI-negative groups. We employed Original Data Analysis, Principal Component Analysis, Linear Discriminant Analysis (LDA), and Non-LDA (NDA) for texture analysis using multi-parametric MR images to predict preoperative MVI. The effectiveness of texture analysis was determined using the B11 program of the MaZda4.6 software, with results expressed as the misjudgment rate (MCR). Texture analysis using multi-parametric MRI, particularly the MI + PA + F dimensionality reduction method combined with NDA discrimination, demonstrated the most effective prediction of MVI in HCC. Prediction accuracy in the pulse and equilibrium phases was 83.81%. MCRs for the combination of T2-weighted imaging (T2WI), arterial phase, portal venous phase, and equilibrium phase were 22.86%, 16.19%, 20.95%, and 20.95%, respectively. The area under the curve for predicting MVI positivity was 0.844, with a sensitivity of 77.19% and specificity of 91.67%. Texture analysis of arterial phase images demonstrated superior predictive efficacy for MVI in HCC compared to T2WI, portal venous, and equilibrium phases. This study provides an objective, non-invasive method for preoperative prediction of MVI, offering a theoretical foundation for the selection of clinical therapy.

Dynamic radiomics based on contrast-enhanced MRI for predicting microvascular invasion in hepatocellular carcinoma

ObjectiveTo exploit the improved prediction performance based on dynamic contrast-enhanced (DCE) MRI by using dynamic radiomics for microvascular invasion (MVI) in hepatocellular carcinoma (HCC).MethodsWe retrospectively included 175 and 75 HCC patients who underwent preoperative DCE-MRI from September 2019 to August 2022 in institution 1 (development cohort) and institution 2 (validation cohort), respectively. Static radiomics features were extracted from the mask, arterial, portal venous, and equilibrium phase images and used to construct dynamic features. The static, dynamic, and dynamic–static radiomics (SR, DR, and DSR) signatures were separately constructed based on the feature selection method of LASSO and classification algorithm of logistic regression. The receiver operating characteristic (ROC) curves and the area under the curve (AUC) were plotted to evaluate and compare the predictive performance of each signature.ResultsIn the three radiomics signatures, the DSR signature performed the best. The AUCs of the SR, DR, and DSR signatures in the training set were 0.750, 0.751 and 0.805, respectively, while in the external validation set, the corresponding AUCs were 0.706, 0756 and 0.777. The DSR signature showed significant improvement over the SR signature in predicting MVI status (training cohort: P = 0.019; validation cohort: P = 0.044). After external validation, the AUC value of the SR signature decreased from 0.750 to 0.706, while the AUC value of the DR signature did not show a decline (AUCs: 0.756 vs. 0.751).ConclusionsThe dynamic radiomics had an improved effect on the MVI prediction in HCC, compared with the static DCE MRI-based radiomics models.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images.

Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans. Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110). The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001). Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

Prediction of microvascular invasion in hepatocellular carcinoma based on multi-phase dynamic enhanced CT radiomics feature and multi-classifier hierarchical fusion model

To predict microvascular invasion (MVI) in hepatocellular carcinoma (HCC) using a model based on multiphase dynamic-enhanced CT (DCE-CT) radiomics feature and hierarchical fusion of multiple classifiers. We retrospectively collected preoperative DCE-CT images from 111 patients with pathologically confirmed HCC in Guangzhou First People's Hospital between January, 2016 and April, 2020. The volume of interest was outlined in the early arterial phase, late arterial phase, portal venous phase and equilibrium phase, and radiomics features of these 4 phases were extracted. Seven classifiers based on different algorithms were trained using the filtered feature subsets to obtain multiple base classifiers under each phase. According to the hierarchical fusion strategy, a multi-criteria decision-making-based weight assignment algorithm was used for fusing each base classifier under the same phase with the model after extracting the phase information to obtain the prediction model. The proposed model was evaluated using a 5-fold cross-validation and assessed for area under the ROC curve (AUC), accuracy, sensitivity, and specificity. The prediction model was also compared with the fusion models using a single phase or multiple phases, models based on a single phase with a single classifier, models with different base classifier diversities, and 8 classifier models based on other ensemble methods. The experimental results showed that the performance of the proposed model for predicting HCCMVI was optimal after incorporating the 4 phases and 7 classifiers, with AUC, accuracy, sensitivity, and specificity of 0.828, 0.766, 0.877, and 0.648, respectively. Comparative experiments showed that this prediction model outperformed the models based on a single phase with a single classifier and other ensemble models. The proposed prediction model is effective for predicting MVI in HCC with superior performance to other models.

A Systematic Review and Meta-Analysis of MRI Radiomics for Predicting Microvascular Invasion in Patients with Hepatocellular Carcinoma.

The prediction power of MRI radiomics for microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) remains uncertain. To investigate the prediction performance of MRI radiomics for MVI in HCC. Original studies focusing on preoperative prediction performance of MRI radiomics for MVI in HCC, were systematically searched from databases of PubMed, Embase, Web of Science and Cochrane Library. Radiomics quality score (RQS) and risk of bias of involved studies were evaluated. Meta-analysis was carried out to demonstrate the value of MRI radiomics for MVI prediction in HCC. Influencing factors of the prediction performance of MRI radiomics were identified by subgroup analyses. 13 studies classified as type 2a or above according to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis statement were eligible for this systematic review and meta-analysis. The studies achieved an average RQS of 14 (ranging from 11 to 17), accounting for 38.9% of the total points. MRI radiomics achieved a pooled sensitivity of 0.82 (95%CI: 0.78 - 0.86), specificity of 0.79 (95%CI: 0.76 - 0.83) and area under the summary receiver operator characteristic curve (AUC) of 0.88 (95%CI: 0.84 - 0.91) to predict MVI in HCC. Radiomics models combined with clinical features achieved superior performances compared to models without the combination (AUC: 0.90 vs 0.85, P < 0.05). MRI radiomics has the potential for preoperative prediction of MVI in HCC. Further studies with high methodological quality should be designed to improve the reliability and reproducibility of the radiomics models for clinical application. The systematic review and meta-analysis was registered prospectively in the International Prospective Register of Systematic Reviews (No. CRD42022333822).

The potential of 18F-FDG PET/CT metabolic parameter-based nomogram inpredicting the microvascular invasion of hepatocellular carcinoma before liver transplantation.

Microvascular invasion (MVI) is a critical factor in predicting the recurrence and prognosis of hepatocellular carcinoma (HCC) after liver transplantation (LT). However, there is a lack of reliable preoperative predictors for MVI. The purpose of this study is to evaluate the potential of an 18F-FDG PET/CT-based nomogram in predicting MVI before LT for HCC. 83 HCC patients who obtained 18F-FDG PET/CT before LT were included in this retrospective research. To determine the parameters connected to MVI and to create a nomogram for MVI prediction, respectively, Logistic and Cox regression models were applied. Analyses of the calibration curve and receiver operating characteristic (ROC) curves were used to assess the model's capability to differentiate between clinical factors and metabolic data from PET/CT images. Among the 83 patients analyzed, 41% were diagnosed with histologic MVI. Multivariate logistic regression analysis revealed that Child-Pugh stage, alpha-fetoprotein, number of tumors, CT Dmax, and Tumor-to-normal liver uptake ratio (TLR) were significant predictors of MVI. A nomogram was constructed using these predictors, which demonstrated strong calibration with a close agreement between predicted and actual MVI probabilities. The nomogram also showed excellent differentiation with an AUC of 0.965 (95% CI 0.925-1.000). The nomogram based on 18F-FDG PET/CT metabolic characteristics is a reliable preoperative imaging biomarker for predicting MVI in HCC patients before undergoing LT. It has demonstrated excellent efficacy and high clinical applicability.

Predicting the microvascular invasion and tumor grading of intrahepatic mass-forming cholangiocarcinoma based on magnetic resonance imaging radiomics and morphological features.

Preoperative diagnosis of microvascular invasion (MVI) and tumor grading of intrahepatic mass-forming cholangiocarcinoma (IMCC) using imaging findings can facilitate patient treatment decision-making. This study was conducted to establish and validate nomograms based on magnetic resonance imaging (MRI) radiomics and morphological features for predicting the MVI and tumor grading of IMCC before radical hepatectomy. A total of 235 patients with resected IMCC at the Chinese Academy of Medical Sciences and Peking Union Medical College were divided into a training set (n=167) and a validation set (n=68), retrospectively. Clinical data and MRI morphological features were recorded. Univariate and multivariate analyses were conducted to identify the significant features for the prediction of MVI and tumor grading. Radiomics features were extracted from T2-weighted imaging fat-suppressed and diffusion-weighted imaging (DWI). Radiomics signatures (rad_scores) were built based on the least absolute shrinkage and selection operator (LASSO) method. Then, the nomograms were constructed by combining the rad_scores and the significant clinical or MRI morphologic features. The predictive performances for MVI and tumor grading were evaluated by the area under the receiver operating characteristic curve (AUC), calibration, and clinical utility. Totals of 16 and 9 radiomics features were selected to build the rad_scores for the prediction of MVI and tumor grading for the training and validation set, respectively. The nomogram for the prediction of MVI comprised the morphologic features including number of tumors, tumor margin, and rad_score. For the prediction of tumor grading, the nomogram comprised the number of tumors, tumor necrosis, and rad_score. The best discriminations were observed in the training and validation sets for the MVI nomogram [AUCs of 0.874, 95% confidence interval (CI): (0.822-0.926) and 0.869 (0.783-0955)] and tumor grading nomogram [AUCs of 0.827 (0.763-0.891) and 0.848 (0.759-0.937)]. Decision curve analysis (DCA) further confirmed the clinical utilities of the nomograms. Nomograms based on MRI radiomics and morphological features can effectively predict the individualized risks of MVI and tumor grading for IMCC.

Clinical and DCE-CT signs in predicting microvascular invasion in cHCC-ICC

BackgroundTo predict the microvascular invasion (MVI) in patients with cHCC-ICC.MethodsA retrospective analysis was conducted on 119 patients who underwent CT enhancement scanning (from September 2006 to August 2022). They were divided into MVI-positive and MVI-negative groups.ResultsThe proportion of patients with CEA elevation was higher in the MVI-positive group than in the MVI-negative group, with a statistically significant difference (P = 0.02). The MVI-positive group had a higher rate of peritumoral enhancement in the arterial phase (P = 0.01) whereas the MVI-negative group had more oval and lobulated masses (P = 0.04). According to the multivariate analysis, the increase in CEA (OR = 10.15, 95% CI: 1.11, 92.48, p = 0.04), hepatic capsular withdrawal (OR = 4.55, 95% CI: 1.44, 14.34, p = 0.01) and peritumoral enhancement (OR = 6.34, 95% CI: 2.18, 18.40, p < 0.01) are independent risk factors for predicting MVI. When these three imaging signs are combined, the specificity of MVI prediction was 70.59% (series connection), and the sensitivity was 100% (parallel connection).ConclusionsOur multivariate analysis found that CEA elevation, liver capsule depression, and arterial phase peritumoral enhancement were independent risk factors for predicting MVI in cHCC-ICC.

Deciphering intratumoral heterogeneity of hepatocellular carcinoma with microvascular invasion with radiogenomic analysis

Background and aimsThe recurrence and metastasis of hepatocellular carcinoma (HCC) are mainly caused by microvascular invasion (MVI). Our study aimed to uncover the cellular atlas of MVI+ HCC and investigate the underlying immune infiltration patterns with radiomics features.MethodsThree MVI positive HCC and three MVI negative HCC samples were collected for single-cell RNA-seq analysis. 26 MVI positive HCC and 30 MVI negative HCC tissues were underwent bulk RNA-seq analysis. For radiomics analysis, radiomics features score (Radscore) were built using preoperative contrast MRI for MVI prediction and overall survival prediction. We deciphered the metabolism profiles of MVI+ HCC using scMetabolism and scFEA. The correlation of Radscore with the level of APOE+ macrophages and iCAFs was identified. Whole Exome Sequencing (WES) was applied to distinguish intrahepatic metastasis (IM) and multicentric occurrence (MO). Transcriptome profiles were compared between IM and MO.ResultsElevated levels of APOE+ macrophages and iCAFs were detected in MVI+ HCC. There was a strong correlation between the infiltration of APOE+ macrophages and iCAFs, as confirmed by immunofluorescent staining. MVI positive tumors exhibited increased lipid metabolism, which was attributed to the increased presence of APOE+ macrophages. APOE+ macrophages and iCAFs were also found in high levels in IM, as opposed to MO. The difference of infiltration level and Radscore between two nodules in IM was relatively small. Furthermore, we developed Radscore for predicting MVI and HCC prognostication that were also able to predict the level of infiltration of APOE+ macrophages and iCAFs.ConclusionThis study demonstrated the interactions of cell subpopulations and distinct metabolism profiles in MVI+ HCC. Besides, MVI prediction Radscore and MVI prognostic Radscore were highly correlated with the infiltration of APOE+ macrophages and iCAFs, which helped to understand the biological significance of radiomics and optimize treatment strategy for MVI+ HCC.

A model based on adipose and muscle-related indicators evaluated by CT images for predicting microvascular invasion in HCC patients

Background and aimThe presence of microvascular invasion (MVI) will impair the surgical outcome of hepatocellular carcinoma (HCC). Adipose and muscle tissues have been confirmed to be associated with the prognosis of HCC. We aimed to develop and validate a nomogram based on adipose and muscle related-variables for preoperative prediction of MVI in HCC.MethodsOne hundred fifty-eight HCC patients from institution A (training cohort) and 53 HCC patients from institution B (validation cohort) were included, all of whom underwent preoperative CT scan and curative resection with confirmed pathological diagnoses. Least absolute shrinkage and selection operator (LASSO) logistic regression was applied to data dimensionality reduction and screening. Nomogram was constructed based on the independent variables, and evaluated by external validation, calibration curve, receiver operating characteristic (ROC) curve and decision curve analysis (DCA).ResultsHistopathologically identified MVI was found in 101 of 211 patients (47.9%). The preoperative imaging and clinical variables associated with MVI were visceral adipose tissue (VAT) density, intramuscular adipose tissue index (IMATI), skeletal muscle (SM) area, age, tumor size and cirrhosis. Incorporating these 6 factors, the nomogram achieved good concordance index of 0.79 (95%CI: 0.72–0.86) and 0.75 (95%CI: 0.62–0.89) in training and validation cohorts, respectively. In addition, calibration curve exhibited good consistency between predicted and actual MVI probabilities. ROC curve and DCA of the nomogram showed superior performance than that of models only depended on clinical or imaging variables. Based on the nomogram score, patients were divided into high (> 273.8) and low (< = 273.8) risk of MVI presence groups. For patients with high MVI risk, wide-margin resection or anatomical resection could significantly improve the 2-year recurrence free survival.ConclusionBy combining 6 preoperative independently predictive factors of MVI, a nomogram was constructed. This model provides an optimal preoperative estimation of MVI risk in HCC patients, and may help to stratify high-risk individuals and optimize clinical decision making.

Preoperative prediction of microvascular invasion in hepatocellular carcinoma using ultrasound features including elasticity.

Microvascular invasion (MVI) is an important predictor of poor prognosis in patients with hepatocellular carcinoma (HCC). Accurate preoperative prediction of MVI in HCC would provide useful information to guide the choice of therapeutic strategy. Shear wave elastography (SWE) plays an important role in hepatic imaging, but its value in the preoperative prediction of MVI in HCC has not yet been proven. To explore the value of conventional ultrasound features and SWE in the preoperative prediction of MVI in HCC. Patients with a postoperative pathological diagnosis of HCC and a definite diagnosis of MVI were enrolled in this study. Conventional ultrasound features and SWE features such as maximal elasticity (Emax) of HCCs and Emax of the periphery of HCCs were acquired before surgery. These features were compared between MVI-positive HCCs and MVI-negative HCCs and between mild MVI HCCs and severe MVI HCCs. This study included 86 MVI-negative HCCs and 102 MVI-positive HCCs, including 54 with mild MVI and 48 with severe MVI. Maximal tumor diameters, surrounding liver tissue, color Doppler flow, Emax of HCCs, and Emax of the periphery of HCCs were significantly different between MVI-positive HCCs and MVI-negative HCCs. In addition, Emax of the periphery of HCCs was significantly different between mild MVI HCCs and severe MVI HCCs. Higher Emax of the periphery of HCCs and larger maximal diameters were independent risk factors for MVI, with odds ratios of 2.820 and 1.021, respectively. HCC size and stiffness of the periphery of HCC are useful ultrasound criteria for predicting positive MVI. Preoperative ultrasound and SWE can provide useful information for the prediction of MVI in HCCs.

Radiomics nomogram based on optimal VOI of multi-sequence MRI for predicting microvascular invasion in intrahepatic cholangiocarcinoma.

Microvascular invasion (MVI) is a significant adverse prognostic indicator of intrahepatic cholangiocarcinoma (ICC) and affects the selection of individualized treatment regimens. This study sought to establish a radiomics nomogram based on the optimal VOI of multi-sequence MRI for predicting MVI in ICC tumors. 160 single ICC lesions with MRI scanning confirmed by postoperative pathology were randomly separated into training and validation cohorts (TC and VC). Multivariate analysis identified independent clinical and imaging MVI predictors. Radiomics features were obtained from images of 6 MRI sequences at 4 different VOIs. The least absolute shrinkage and selection operator algorithm was performed to enable the derivation of robust and effective radiomics features. Then, the best three sequences and the optimal VOI were obtained through comparison. The MVI prediction nomogram combined the independent predictors and optimal radiomics features, and its performance was evaluated via the receiver operating characteristics, calibration, and decision curves. Tumor size and intrahepatic ductal dilatation are independent MVI predictors. Radiomics features extracted from the best three sequences (T1WI-D, T1WI, DWI) with VOI10mm (including tumor and 10mm peritumoral region) showed the best predictive performance, with AUCTC = 0.987 and AUCVC = 0.859. The MVI prediction nomogram obtained excellent prediction efficacy in both TC (AUC = 0.995, 95%CI 0.987-1.000) and VC (AUC = 0.867, 95%CI 0.798-0.921) and its clinical significance was further confirmed by the decision curves. A nomogram combining tumor size, intrahepatic ductal dilatation, and the radiomics model of MRI multi-sequence fusion at VOI10mm may be a predictor of preoperative MVI status in ICC patients.

Radiomic Analysis of Intrahepatic Cholangiocarcinoma: Non-Invasive Prediction of Pathology Data: A Multicenter Study to Develop a Clinical-Radiomic Model.

Standard imaging cannot assess the pathology details of intrahepatic cholangiocarcinoma (ICC). We investigated whether CT-based radiomics may improve the prediction of tumor characteristics. All consecutive patients undergoing liver resection for ICC (2009-2019) in six high-volume centers were evaluated for inclusion. On the preoperative CT, we segmented the ICC (Tumor-VOI, i.e., volume-of-interest) and a 5-mm parenchyma rim around the tumor (Margin-VOI). We considered two types of pathology data: tumor grading (G) and microvascular invasion (MVI). The predictive models were internally validated. Overall, 244 patients were analyzed: 82 (34%) had G3 tumors and 139 (57%) had MVI. For G3 prediction, the clinical model had an AUC = 0.69 and an Accuracy = 0.68 at internal cross-validation. The addition of radiomic features extracted from the portal phase of CT improved the model performance (Clinical data+Tumor-VOI: AUC = 0.73/Accuracy = 0.72; +Tumor-/Margin-VOI: AUC = 0.77/Accuracy = 0.77). Also for MVI prediction, the addition of portal phase radiomics improved the model performance (Clinical data: AUC = 0.75/Accuracy = 0.70; +Tumor-VOI: AUC = 0.82/Accuracy = 0.73; +Tumor-/Margin-VOI: AUC = 0.82/Accuracy = 0.75). The permutation tests confirmed that a combined clinical-radiomic model outperforms a purely clinical one (p < 0.05). The addition of the textural features extracted from the arterial phase had no impact. In conclusion, the radiomic features of the tumor and peritumoral tissue extracted from the portal phase of preoperative CT improve the prediction of ICC grading and MVI.

Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism.

Preoperative prediction of microvascular invasion (MVI) is essential for management decision in hepatocellular carcinoma (HCC). Deep learning-based prediction models of MVI are numerous but lack clinical interpretation due to their "black-box" nature. Consequently, we aimed to use an attention-guided feature fusion network, including intra- and inter-attention modules, to solve this problem. This retrospective study recruited 210 HCC patients who underwent gadoxetate-enhanced MRI examination before surgery. The MRIs on pre-contrast, arterial, portal, and hepatobiliary phases (hepatobiliary phase: HBP) were used to develop single-phase and multi-phase models. Attention weights provided by attention modules were used to obtain visual explanations of predictive decisions. The four-phase fusion model achieved the highest area under the curve (AUC) of 0.92 (95% CI: 0.84-1.00), and the other models proposed AUCs of 0.75-0.91. Attention heatmaps of collaborative-attention layers revealed that tumor margins in all phases and peritumoral areas in the arterial phase and HBP were salient regions for MVI prediction. Heatmaps of weights in fully connected layers showed that the HBP contributed the most to MVI prediction. Our study firstly implemented self-attention and collaborative-attention to reveal the relationship between deep features and MVI, improving the clinical interpretation of prediction models. The clinical interpretability offers radiologists and clinicians more confidence to apply deep learning models in clinical practice, helping HCC patients formulate personalized therapies.

Vision-Guided Attention-Enhanced Network for Predicting Microvascular Invasion in Hepatocellular Carcinoma.

As the most common malignant tumor worldwide, hepatocellular carcinoma (HCC) has a high rate of death and recurrence, and microvascular invasion (MVI) is considered to be an independent risk factor affecting its early recurrence and poor survival rate. Accurate preoperative prediction of MVI is of great significance for the formulation of individualized treatment plans and long-term prognosis assessment for HCC patients. However, as the mechanism of MVI is still unclear, existing studies use deep learning methods to directly train CT or MR images, with limited predictive performance and lack of explanation. We map the pathological "7-point" baseline sampling method used to confirm the diagnosis of MVI onto MR images, propose a vision-guided attention-enhanced network to improve the prediction performance of MVI, and validate the prediction on the corresponding pathological images reliability of the results. Specifically, we design a learnable online class activation map (CAM) to guide the network to focus on high-incidence regions of MVI guided by an extended tumor mask. Further, an attention-enhanced module is proposed to force the network to learn image regions that can explain the MVI results. The generated attention maps capture long-distance dependencies and can be used as spatial priors for MVI to promote the learning of vision-guided module. The experimental results on the constructed multi-center dataset show that the proposed algorithm achieves the state-of-the-art compared to other models.

A novel nomogram for predicting microvascular invasion in hepatocellular carcinoma

Introduction and ObjectivesIn hepatocellular carcinoma (HCC), the prognosis of patients with microvascular invasion (MVI) is poor. Therefore, in this study, we established and evaluated the performance of a novel nomogram to predict MVI in patients with HCC. Materials and MethodsWe retrospectively obtained clinical data of 497 patients with HCC who underwent hepatectomy at Liaoning Cancer Hospital from November 1, 2018, to November 4, 2021. The patients (n = 497) were randomized in a 7:3 ratio into the training cohort (TC, n = 349) and the validation cohort (VC, n = 148). We performed Least Absolute Shrinkage and Selection Operator (LASSO) and univariate as well as multivariate logistic regression analyses (ULRA, MRLA) on patients in the TC to identify factors independently predicting MVI. ResultsPreoperative FIB-4, AFU, AFP levels, liver cirrhosis, and non-smooth tumor margin were independent risk factors for preoperative MVI prediction. The C-index of the TC, VC, and the entire cohort was 0.846, 0.786, and 0.829, respectively. The calibration curves demonstrated the outstanding agreement between predicted MVI incidences by our model and the actual MVI risk. Decision curve analysis (DCA) confirmed the significance of our predictive model in clinical settings. The Kaplan−Meier (KM) survival curve showed that the recurrence-free survival (RFS) and overall survival (OS) of patients in the high-MVI risk group were poor compared to those in the low-MVI risk group. ConclusionsWe constructed and evaluated the performance of the novel nomogram for predicting MVI risk. Our predictive model could adequately predict MVI risk and aid clinicians in selecting appropriate therapeutic strategies for patients.

Modality-based attention and dual-stream multiple instance convolutional neural network for predicting microvascular invasion of hepatocellular carcinoma.

The presence of microvascular invasion (MVI) is a crucial indicator of postoperative recurrence in patients with hepatocellular carcinoma (HCC). Detecting MVI before surgery can improve personalized surgical planning and enhance patient survival. However, existing automatic diagnosis methods for MVI have certain limitations. Some methods only analyze information from a single slice and overlook the context of the entire lesion, while others require high computational resources to process the entire tumor with a three-dimension (3D) convolutional neural network (CNN), which could be challenging to train. To address these limitations, this paper proposes a modality-based attention and dual-stream multiple instance learning(MIL) CNN. In this retrospective study, 283 patients with histologically confirmed HCC who underwent surgical resection between April 2017 and September 2019 were included. Five magnetic resonance (MR) modalities including T2-weighted, arterial phase, venous phase, delay phase and apparent diffusion coefficient images were used in image acquisition of each patient. Firstly, Each two-dimension (2D) slice of HCC magnetic resonance image (MRI) was converted into an instance embedding. Secondly, modality attention module was designed to emulates the decision-making process of doctors and helped the model to focus on the important MRI sequences. Thirdly, instance embeddings of 3D scans were aggregated into a bag embedding by a dual-stream MIL aggregator, in which the critical slices were given greater consideration. The dataset was split into a training set and a testing set in a 4:1 ratio, and model performance was evaluated using five-fold cross-validation. Using the proposed method, the prediction of MVI achieved an accuracy of 76.43% and an AUC of 74.22%, significantly surpassing the performance of the baseline methods. Our modality-based attention and dual-stream MIL CNN can achieve outstanding results for MVI prediction.