Using deep learning to predict microvascular invasion in hepatocellular carcinoma based on dynamic contrast-enhanced MRI combined with clinical parameters. J Cancer Res Clin Oncol. 2021 epub ahead of print. [PMID: 33839938 DOI: 10.1007/s00432-021-03617-3]

Radiomics Diagnosis of Microvascular Invasion in Hepatocellular Carcinoma Using 3D Ultrasound and Whole-Slide Image Fusion

This study aims to develop a machine learning model that accurately diagnoses microvascular invasion (MVI) in hepatocellular carcinoma by using radiomic features from MVI-positive regions of interest (ROIs). Unlike previous studies, which do not account for the location and distribution of MVI, this research focuses on correlating preoperative imaging with postoperative pathological MVI. This study involves obtaining ex vivo 3D ultrasound images of 36 hepatic specimens from nine rabbits. These images are fused with whole-slide images to localize MVI regions precisely. The identified MVI regions are segmented into MVI-positive ROIs, with a 1:3 ratio of positive to negative ROIs. Radiomic features are extracted from each ROI, and 30 features highly associated with MVI are selected for model development. The performance of several machine learning models is evaluated using metrics such as sensitivity, specificity, accuracy, the area under the curve (AUC), and F1 score. The GBDT model achieves the best results, with an AUC of 0.91, an F1 score of 0.85, a sensitivity of 0.76, a specificity of 0.92, and an accuracy of 0.86. The high diagnostic accuracy of these models highlights the potential for future clinical application in the precise diagnosis of MVI using radiomic features from MVI-positive ROIs.

Advances in multi-omics studies of microvascular invasion in hepatocellular carcinoma

Microvascular invasion (MVI) represents a pivotal independent prognostic factor for the recurrence of hepatocellular carcinoma (HCC) after surgery. It contributes to early intervention for potentially recurrent HCC to enhance patient outcomes and increase survival rates. Traditionally, the diagnosis of MVI has relied on postoperative pathological analysis, and accurate preoperative detection methodologies are lacking. Recent research suggests that multi-omics strategies play a role in definitively diagnosing MVI before surgery and offering personalized selection for clinical decision-making in HCC management. This review meticulously examines a multi-omics approach for the preoperative prediction of MVI in HCC patients, aiming to innovate diagnostic paradigms to anticipate postsurgical recurrence, thereby facilitating earlier and more personalized therapeutic strategies.

AI in Hepatology: Revolutionizing the Diagnosis and Management of Liver Disease

The integration of artificial intelligence (AI) into hepatology is revolutionizing the diagnosis and management of liver diseases amidst a rising global burden of conditions like metabolic-associated steatotic liver disease (MASLD). AI harnesses vast datasets and complex algorithms to enhance clinical decision making and patient outcomes. AI's applications in hepatology span a variety of conditions, including autoimmune hepatitis, primary biliary cholangitis, primary sclerosing cholangitis, MASLD, hepatitis B, and hepatocellular carcinoma. It enables early detection, predicts disease progression, and supports more precise treatment strategies. Despite its transformative potential, challenges remain, including data integration, algorithm transparency, and computational demands. This review examines the current state of AI in hepatology, exploring its applications, limitations, and the opportunities it presents to enhance liver health and care delivery.

Artificial intelligence techniques in liver cancer

Hepatocellular Carcinoma (HCC), the most common primary liver cancer, is a significant contributor to worldwide cancer-related deaths. Various medical imaging techniques, including computed tomography, magnetic resonance imaging, and ultrasound, play a crucial role in accurately evaluating HCC and formulating effective treatment plans. Artificial Intelligence (AI) technologies have demonstrated potential in supporting physicians by providing more accurate and consistent medical diagnoses. Recent advancements have led to the development of AI-based multi-modal prediction systems. These systems integrate medical imaging with other modalities, such as electronic health record reports and clinical parameters, to enhance the accuracy of predicting biological characteristics and prognosis, including those associated with HCC. These multi-modal prediction systems pave the way for predicting the response to transarterial chemoembolization and microvascular invasion treatments and can assist clinicians in identifying the optimal patients with HCC who could benefit from interventional therapy. This paper provides an overview of the latest AI-based medical imaging models developed for diagnosing and predicting HCC. It also explores the challenges and potential future directions related to the clinical application of AI techniques.

Tumor habitat and peritumoral region evolution-based imaging features to assess risk categorization of thymomas

AIM

To develop an aggregate model that integrated clinical data, habitat characteristics, and intratumoral and peritumoral features to assess the risk categorization of thymomas.

MATERIALS AND METHODS

We retrospectively analyzed 140 thymoma patients (70 low-risk and 70 high-risk), including pathological data. The patients were randomly divided into training cohort (n = 114) and test cohort (n = 26). The k-means clustering was utilized to partition the primary tumor into habitats based on intratumoral radiomic features, 6 distinct habitats were identified. By expanding the region of interest (ROI) mask, 2 peritumoral regions were obtained. Finally, 7 clinical characteristics, 3 habitat values, 20 radiomic features were utilized to develop an aggregated model, to predict the risk of thymoma. Shapley additive explanations (SHAP) interpretation was used for features importance ranking. The accuracy and area under curve (AUC) were used to analyze the performance of the models.

RESULTS

The aggregated model, which utilized the XGBoost classifier, demonstrated the best performance with an AUC of 0.811 and an accuracy of 0.769. In comparison, the radiomic model produced an AUC of 0.654 and an accuracy of 0.692. Additionally, the Intratumoral + peritumoral model exhibited an AUC of 0.728 and an accuracy of 0.769.

CONCLUSION

Our study establishes a novel tool to predict the risk of thymoma with a good performance. If prospectively validated, the model may refine thymoma patient selection for risk-adaptative therapy and improve prognosis.

Preoperative prediction of microvascular invasion risk in hepatocellular carcinoma with MRI: peritumoral versus tumor region

OBJECTIVES

To explore the predictive performance of tumor and multiple peritumoral regions on dynamic contrast-enhanced magnetic resonance imaging (MRI), to identify optimal regions of interest for developing a preoperative predictive model for the grade of microvascular invasion (MVI).

METHODS

A total of 147 patients who were surgically diagnosed with hepatocellular carcinoma, and had a maximum tumor diameter ≤ 5 cm were recruited and subsequently divided into a training set (n = 117) and a testing set (n = 30) based on the date of surgery. We utilized a pre-trained AlexNet to extract deep learning features from seven different regions of the maximum transverse cross-section of tumors in various MRI sequence images. Subsequently, an extreme gradient boosting (XGBoost) classifier was employed to construct the MVI grade prediction model, with evaluation based on the area under the curve (AUC).

RESULTS

The XGBoost classifier trained with data from the 20-mm peritumoral region showed superior AUC compared to the tumor region alone. AUC values consistently increased when utilizing data from 5-mm, 10-mm, and 20-mm peritumoral regions. Combining arterial and delayed-phase data yielded the highest predictive performance, with micro- and macro-average AUCs of 0.78 and 0.74, respectively. Integration of clinical data further improved AUCs values to 0.83 and 0.80.

CONCLUSION

Compared with those of the tumor region, the deep learning features of the peritumoral region provide more important information for predicting the grade of MVI. Combining the tumor region and the 20-mm peritumoral region resulted in a relatively ideal and accurate region within which the grade of MVI can be predicted.

CLINICAL RELEVANCE STATEMENT

The 20-mm peritumoral region holds more significance than the tumor region in predicting MVI grade. Deep learning features can indirectly predict MVI by extracting information from the tumor region and directly capturing MVI information from the peritumoral region.

KEY POINTS

We investigated tumor and different peritumoral regions, as well as their fusion. MVI predominantly occurs in the peritumoral region, a superior predictor compared to the tumor region. The peritumoral 20 mm region is reasonable for accurately predicting the three-grade MVI.

Precision and Robust Models on Healthcare Institution Federated Learning for Predicting HCC on Portal Venous CT Images

Hepatocellular carcinoma (HCC), the most common type of liver cancer, poses significant challenges in detection and diagnosis. Medical imaging, especially computed tomography (CT), is pivotal in non-invasively identifying this disease, requiring substantial expertise for interpretation. This research introduces an innovative strategy that integrates two-dimensional (2D) and three-dimensional (3D) deep learning models within a federated learning (FL) framework for precise segmentation of liver and tumor regions in medical images. The study utilized 131 CT scans from the Liver Tumor Segmentation (LiTS) challenge and demonstrated the superior efficiency and accuracy of the proposed Hybrid-ResUNet model with a Dice score of 0.9433 and an AUC of 0.9965 compared to ResNet and EfficientNet models. This FL approach is beneficial for conducting large-scale clinical trials while safeguarding patient privacy across healthcare settings. It facilitates active engagement in problem-solving, data collection, model development, and refinement. The study also addresses data imbalances in the FL context, showing resilience and highlighting local models' robust performance. Future research will concentrate on refining federated learning algorithms and their incorporation into the continuous implementation and deployment (CI/CD) processes in AI system operations, emphasizing the dynamic involvement of clients. We recommend a collaborative human-AI endeavor to enhance feature extraction and knowledge transfer. These improvements are intended to boost equitable and efficient data collaboration across various sectors in practical scenarios, offering a crucial guide for forthcoming research in medical AI.

A Transvaginal Ultrasound-Based Deep Learning Model for the Noninvasive Diagnosis of Myometrial Invasion in Patients with Endometrial Cancer: Comparison with Radiologists

RATIONALE AND OBJECTIVES

This study aimed to determine the feasibility of using the deep learning (DL) method to determine the degree (whether myometrial invasion [MI] >50%) of MI in patients with endometrial cancer (EC) based on ultrasound (US) images.

MATERIALS AND METHODS

From September 2017 to April 2023, 1289 US images of 604 patients with EC who underwent surgical resection at center 1, center 2 or center 3 were obtained and divided into a training set and an internal validation set. Ninety-five patients from center 4 and center 5 were randomly selected as the external testing set according to the same criteria as those for the primary cohort. This study evaluated three DL models trained on the training set and tested them on the validation and testing sets. The models' performance was analyzed based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), and the performance of the models was subsequently compared with that of 15 radiologists.

RESULTS

In the final clinical diagnosis of MI in patients with EC, EfficientNet-B6 showed the best performance in the testing set in terms of area under the curve (AUC) [0.814, 95% CI (0.746-0.882]; accuracy [0.802, 95% CI (0.733-0.855]; sensitivity [0.623]; specificity [0.879]; positive likelihood ratio (PLR) [6.750]; and negative likelihood ratio (NLR) [0.389]. The diagnostic efficacy of EfficientNet-B6 was significantly better than that of the 15 radiologists, with an average diagnostic accuracy of 0.681, average AUC of 0.678, AUC of the best performance of 0.739, accuracy of 0.716, sensitivity of 0.806, specificity 0.672, PLR2.457, and NLR 0.289.

CONCLUSION

Based on the preoperative US images of patients with EC, the DL model can accurately determine the degree of endometrial MI; the performance of this model is significantly better than that of radiologists, and it can effectively assist in clinical treatment decisions.

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

BACKGROUND AND AIMS

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.

METHODS

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).

RESULTS

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).

CONCLUSIONS

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.

CEMRI-Based Quantification of Intratumoral Heterogeneity for Predicting Aggressive Characteristics of Hepatocellular Carcinoma Using Habitat Analysis: Comparison and Combination of Deep Learning

RATIONALE AND OBJECTIVES

To explore both an intratumoral heterogeneity (ITH) model based on habitat analysis and a deep learning (DL) model based on contrast-enhanced magnetic resonance imaging (CEMRI) and validate its efficiency for predicting microvascular invasion (MVI) and pathological differentiation in hepatocellular carcinoma (HCC).

METHODS

CEMRI images were retrospectively obtained from 277 HCCs in 265 patients. Habitat analysis and DL features were extracted from the CEMRI images and selected with the least absolute shrinkage and selection operator approach to develop ITH and DL models, respectively, and these robust features were then integrated to design a fusion model for predicting MVI and poorly differentiated HCC (pHCC). The predictive value of the three models was assessed using the area under the receiver operating characteristic curve (AUC).

RESULTS

The training and validation sets comprised 221 HCCs and 56 HCCs, respectively. The ITH and DL models presented AUC values of (0.90 vs. 0.87) for predicting MVI in the training set, with AUC values of 0.86 and 0.83 in the validation set. The AUC values of the ITH model to predict pHCC were 0.90 and 0.86 in the two sets, respectively; they were 0.84 and 0.80 for the DL model. The fusion model yielded the best performance for predicting MVI and pHCC in the training set (AUC=0.95, 0.90) and in the validation set (AUC=0.89, 0.87), respectively.

CONCLUSION

A fusion model integrating ITH and DL features derived from CEMRI images can serve as an excellent imaging biomarker for predicting aggressive characteristics in HCC.

Prognostication of Hepatocellular Carcinoma Using Artificial Intelligence

Hepatocellular carcinoma (HCC) is a biologically heterogeneous tumor characterized by varying degrees of aggressiveness. The current treatment strategy for HCC is predominantly determined by the overall tumor burden, and does not address the diverse prognoses of patients with HCC owing to its heterogeneity. Therefore, the prognostication of HCC using imaging data is crucial for optimizing patient management. Although some radiologic features have been demonstrated to be indicative of the biologic behavior of HCC, traditional radiologic methods for HCC prognostication are based on visually-assessed prognostic findings, and are limited by subjectivity and inter-observer variability. Consequently, artificial intelligence has emerged as a promising method for image-based prognostication of HCC. Unlike traditional radiologic image analysis, artificial intelligence based on radiomics or deep learning utilizes numerous image-derived quantitative features, potentially offering an objective, detailed, and comprehensive analysis of the tumor phenotypes. Artificial intelligence, particularly radiomics has displayed potential in a variety of applications, including the prediction of microvascular invasion, recurrence risk after locoregional treatment, and response to systemic therapy. This review highlights the potential value of artificial intelligence in the prognostication of HCC as well as its limitations and future prospects.

Role of microvascular invasion in early recurrence of hepatocellular carcinoma after liver resection: A literature review

Hepatectomy is widely considered a potential treatment for hepatocellular carcinoma (HCC). Unfortunately, one-third of HCC patients have tumor recurrence within 2 years after surgery (early recurrence), accounting for more than 60% of all recurrence patients. Early recurrence is associated with a worse prognosis. Previous studies have shown that microvascular invasion (MVI) is one of the key factors for early recurrence and poor prognosis in patients with HCC after surgery. This paper reviews the latest literature and summarizes the predictors of MVI, the correlation between MVI and early recurrence, the identification of suspicious nodules or subclinical lesions, and the treatment strategies for MVI-positive HCC. The aim is to explore the management of patients with MVI-positive HCC.

Predicting microvascular invasion in hepatocellular carcinoma with a CT- and MRI-based multimodal deep learning model

PURPOSE

To investigate the value of a multimodal deep learning (MDL) model based on computed tomography (CT) and magnetic resonance imaging (MRI) for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC).

METHODS

A total of 287 patients with HCC from our institution and 58 patients from another individual institution were included. Among these, 119 patients with only CT data and 116 patients with only MRI data were selected for single-modality deep learning model development, after which select parameters were migrated for MDL model development with transfer learning (TL). In addition, 110 patients with simultaneous CT and MRI data were divided into a training cohort (n = 66) and a validation cohort (n = 44). We input the features extracted from DenseNet121 into an extreme learning machine (ELM) classifier to construct a classification model.

RESULTS

The area under the curve (AUC) of the MDL model was 0.844, which was superior to that of the single-phase CT (AUC = 0.706-0.776, P < 0.05), single-sequence MRI (AUC = 0.706-0.717, P < 0.05), single-modality DL model (AUCall-phase CT = 0.722, AUCall-sequence MRI = 0.731; P < 0.05), clinical (AUC = 0.648, P < 0.05), but not to that of the delay phase (DP) and in-phase (IP) MRI and portal venous phase (PVP) CT models. The MDL model achieved better performance than models described above (P < 0.05). When combined with clinical features, the AUC of the MDL model increased from 0.844 to 0.871. A nomogram, combining deep learning signatures (DLS) and clinical indicators for MDL models, demonstrated a greater overall net gain than the MDL models (P < 0.05).

CONCLUSION

The MDL model is a valuable noninvasive technique for preoperatively predicting MVI in HCC.

BAF-Net: bidirectional attention-aware fluid pyramid feature integrated multimodal fusion network for diagnosis and prognosis

Objective. To go beyond the deficiencies of the three conventional multimodal fusion strategies (i.e. input-, feature- and output-level fusion), we propose a bidirectional attention-aware fluid pyramid feature integrated fusion network (BAF-Net) with cross-modal interactions for multimodal medical image diagnosis and prognosis.Approach. BAF-Net is composed of two identical branches to preserve the unimodal features and one bidirectional attention-aware distillation stream to progressively assimilate cross-modal complements and to learn supplementary features in both bottom-up and top-down processes. Fluid pyramid connections were adopted to integrate the hierarchical features at different levels of the network, and channel-wise attention modules were exploited to mitigate cross-modal cross-level incompatibility. Furthermore, depth-wise separable convolution was introduced to fuse the cross-modal cross-level features to alleviate the increase in parameters to a great extent. The generalization abilities of BAF-Net were evaluated in terms of two clinical tasks: (1) an in-house PET-CT dataset with 174 patients for differentiation between lung cancer and pulmonary tuberculosis. (2) A public multicenter PET-CT head and neck cancer dataset with 800 patients from nine centers for overall survival prediction.Main results. On the LC-PTB dataset, improved performance was found in BAF-Net (AUC = 0.7342) compared with input-level fusion model (AUC = 0.6825;p< 0.05), feature-level fusion model (AUC = 0.6968;p= 0.0547), output-level fusion model (AUC = 0.7011;p< 0.05). On the H&N cancer dataset, BAF-Net (C-index = 0.7241) outperformed the input-, feature-, and output-level fusion model, with 2.95%, 3.77%, and 1.52% increments of C-index (p= 0.3336, 0.0479 and 0.2911, respectively). The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets.Significance. Extensive experiments on two datasets demonstrated better performance and robustness of BAF-Net than three conventional fusion strategies and PET or CT unimodal network in terms of diagnosis and prognosis.

Artificial intelligence in liver imaging: methods and applications

Liver disease is regarded as one of the major health threats to humans. Radiographic assessments hold promise in terms of addressing the current demands for precisely diagnosing and treating liver diseases, and artificial intelligence (AI), which excels at automatically making quantitative assessments of complex medical image characteristics, has made great strides regarding the qualitative interpretation of medical imaging by clinicians. Here, we review the current state of medical-imaging-based AI methodologies and their applications concerning the management of liver diseases. We summarize the representative AI methodologies in liver imaging with focusing on deep learning, and illustrate their promising clinical applications across the spectrum of precise liver disease detection, diagnosis and treatment. We also address the current challenges and future perspectives of AI in liver imaging, with an emphasis on feature interpretability, multimodal data integration and multicenter study. Taken together, it is revealed that AI methodologies, together with the large volume of available medical image data, might impact the future of liver disease care.

A Transformer-Based microvascular invasion classifier enhances prognostic stratification in HCC following radiofrequency ablation

BACKGROUND & AIMS

We aimed to develop a Transformer-based deep learning (DL) network for prognostic stratification in hepatocellular carcinoma (HCC) patients undergoing RFA.

METHODS

A Swin Transformer DL network was trained to establish associations between magnetic resonance imaging (MRI) datasets and the ground truth of microvascular invasion (MVI) based on 696 surgical resection (SR) patients with solitary HCC ≤3 cm, and was validated in an external cohort (n = 180). The multiphase MRI-based DL risk outputs using an optimal threshold of .5 was employed as a MVI classifier for prognosis stratification in the RFA cohort (n = 180).

RESULTS

Over 90% of all enrolled patients exhibited hepatitis B virus infection. Liver cirrhosis was significantly more prevalent in the RFA cohort compared to the SR cohort (72.2% vs. 44.1%, p < .001). The MVI risk outputs exhibited good performance (area under the curve values = .938 and .883) for predicting MVI in the training and validation cohort, respectively. The RFA patients at high risk of MVI classified by the MVI classifier demonstrated significantly lower recurrence-free survival (RFS) and overall survival rates at 1, 3 and 5 years compared to those classified as low risk (p < .001). Multivariate cox regression modelling of a-fetoprotein > 20 ng/mL [hazard ratio (HR) = 1.53; 95% confidence interval (95% CI): 1.02-2.33, p = .047], high risk of MVI (HR = 3.76; 95% CI: 2.40-5.88, p < .001) and unfavourable tumour location (HR = 2.15; 95% CI: 1.40-3.29, p = .001) yielded a c-index of .731 (bootstrapped 95% CI: .667-.778) for evaluating RFS after RFA. Among the three risk factors, MVI was the most powerful predictor for intrahepatic distance recurrence.

CONCLUSIONS

The proposed MVI classifier can serve as a valuable imaging biomarker for prognostic stratification in early-stage HCC patients undergoing RFA.

A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma

PURPOSE

This study aimed to build and evaluate a deep learning (DL) model to predict vessels encapsulating tumor clusters (VETC) and prognosis preoperatively in patients with hepatocellular carcinoma (HCC).

METHODS

320 pathologically confirmed HCC patients (58 women and 262 men) from two hospitals were included in this retrospective study. Institution 1 (n = 219) and Institution 2 (n = 101) served as the training and external test cohorts, respectively. Tumors were evaluated three-dimensionally and regions of interest were segmented manually in the arterial, portal venous, and delayed phases (AP, PP, and DP). Three ResNet-34 DL models were developed, consisting of three models based on a single sequence. The fusion model was developed by inputting the prediction probability of the output from the three single-sequence models into logistic regression. The area under the receiver operating characteristic curve (AUC) was used to compare performance, and the Delong test was used to compare AUCs. Early recurrence (ER) was defined as recurrence within two years of surgery and early recurrence-free survival (ERFS) rate was evaluated by Kaplan-Meier survival analysis.

RESULTS

Among the 320 HCC patients, 227 were VETC- and 93 were VETC+ . In the external test cohort, the fusion model showed an AUC of 0.772, a sensitivity of 0.80, and a specificity of 0.61. The fusion model-based prediction of VETC high-risk and low-risk categories exhibits a significant difference in ERFS rates, akin to the outcomes observed in VETC + and VETC- confirmed through pathological analyses (p < 0.05).

CONCLUSIONS

A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.

Current status of magnetic resonance imaging radiomics in hepatocellular carcinoma: A quantitative review with Radiomics Quality Score

BACKGROUND

Radiomics is a promising tool that may increase the value of magnetic resonance imaging (MRI) for different tasks related to the management of patients with hepatocellular carcinoma (HCC). However, its implementation in clinical practice is still far, with many issues related to the methodological quality of radiomic studies.

AIM

To systematically review the current status of MRI radiomic studies concerning HCC using the Radiomics Quality Score (RQS).

METHODS

A systematic literature search of PubMed, Google Scholar, and Web of Science databases was performed to identify original articles focusing on the use of MRI radiomics for HCC management published between 2017 and 2023. The methodological quality of radiomic studies was assessed using the RQS tool. Spearman's correlation (ρ) analysis was performed to explore if RQS was correlated with journal metrics and characteristics of the studies. The level of statistical signi-ficance was set at P < 0.05.

RESULTS

One hundred and twenty-seven articles were included, of which 43 focused on HCC prognosis, 39 on prediction of pathological findings, 16 on prediction of the expression of molecular markers outcomes, 18 had a diagnostic purpose, and 11 had multiple purposes. The mean RQS was 8 ± 6.22, and the corresponding percentage was 24.15% ± 15.25% (ranging from 0.0% to 58.33%). RQS was positively correlated with journal impact factor (IF; ρ = 0.36, P = 2.98 × 10-5), 5-years IF (ρ = 0.33, P = 1.56 × 10-4), number of patients included in the study (ρ = 0.51, P < 9.37 × 10-10) and number of radiomics features extracted in the study (ρ = 0.59, P < 4.59 × 10-13), and time of publication (ρ = -0.23, P < 0.0072).

CONCLUSION

Although MRI radiomics in HCC represents a promising tool to develop adequate personalized treatment as a noninvasive approach in HCC patients, our study revealed that studies in this field still lack the quality required to allow its introduction into clinical practice.

Preoperative evaluation of microvascular invasion in hepatocellular carcinoma with a radiological feature-based nomogram: a bi-centre study

PURPOSE

To develop a nomogram for preoperative assessment of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) based on the radiological features of enhanced CT and to verify two imaging techniques (CT and MRI) in an external centre.

METHOD

A total of 346 patients were retrospectively included (training, n = 185, CT images; external testing 1, n = 90, CT images; external testing 2, n = 71, MRI images), including 229 MVI-negative patients and 117 MVI-positive patients. The radiological features and clinical information of enhanced CT images were analysed, and the independent variables associated with MVI in HCC were determined by logistic regression analysis. Then, a nomogram prediction model was constructed. External validation was performed on CT (n = 90) and MRI (n = 71) images from another centre.

RESULTS

Among the 23 radiological and clinical features, size, arterial peritumoral enhancement (APE), tumour margin and alpha-fetoprotein (AFP) were independent influencing factors for MVI in HCC. The nomogram integrating these risk factors had a good predictive effect, with AUC, specificity and sensitivity values of 0.834 (95% CI: 0.774-0.895), 75.0% and 83.5%, respectively. The AUC values of external verification based on CT and MRI image data were 0.794 (95% CI: 0.700-0.888) and 0.883 (95% CI: 0.807-0.959), respectively. No statistical difference in AUC values among training set and testing sets was found.

CONCLUSION

The proposed nomogram prediction model for MVI in HCC has high accuracy, can be used with different imaging techniques, and has good clinical applicability.

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

BACKGROUND

The prediction power of MRI radiomics for microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) remains uncertain.

OBJECTIVE

To investigate the prediction performance of MRI radiomics for MVI in HCC.

METHODS

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.

RESULTS

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).

CONCLUSION

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).

18F-FDG PET/CT-based deep learning radiomics predicts 5-years disease-free survival after failure to achieve pathologic complete response to neoadjuvant chemotherapy in breast cancer

BACKGROUND

This study aimed to assess whether a combined model incorporating radiomic and depth features extracted from PET/CT can predict disease-free survival (DFS) in patients who failed to achieve pathologic complete response (pCR) after neoadjuvant chemotherapy.

RESULTS

This study retrospectively included one hundred and five non-pCR patients. After a median follow-up of 71 months, 15 and 7 patients experienced recurrence and death, respectively. The primary tumor volume underwent feature extraction, yielding a total of 3644 radiomic features and 4096 depth features. The modeling procedure employed Cox regression for feature selection and utilized Cox proportional-hazards models to make predictions on DFS. Time-dependent receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) were utilized to evaluate and compare the predictive performance of different models. 2 clinical features (RCB, cT), 4 radiomic features, and 7 depth features were significant predictors of DFS and were included to develop models. The integrated model incorporating RCB, cT, and radiomic and depth features extracted from PET/CT images exhibited the highest accuracy for predicting 5-year DFS in the training (AUC 0.943) and the validation cohort (AUC 0.938).

CONCLUSION

The integrated model combining radiomic and depth features extracted from PET/CT images can accurately predict 5-year DFS in non-pCR patients. It can help identify patients with a high risk of recurrence and strengthen adjuvant therapy to improve survival.

Dynamic Contrast-Enhanced Study in the mpMRI of the Prostate-Unnecessary or Underutilised? A Narrative Review

The aim of this review is to summarise recent scientific literature regarding the clinical use of DCE-MRI as a component of multiparametric resonance imaging of the prostate. This review presents the principles of DCE-MRI acquisition and analysis, the current role of DCE-MRI in clinical practice with special regard to its role in presently available categorisation systems, and an overview of the advantages and disadvantages of DCE-MRI described in the current literature. DCE-MRI is an important functional sequence that requires intravenous administration of a gadolinium-based contrast agent and gives information regarding the vascularity and capillary permeability of the lesion. Although numerous studies have confirmed that DCE-MRI has great potential in the diagnosis and monitoring of prostate cancer, its role is still inadequate in the PI-RADS categorisation. Moreover, there have been numerous scientific discussions about abandoning the intravenous application of gadolinium-based contrast as a routine part of MRI examination of the prostate. In this review, we summarised the recent literature on the advantages and disadvantages of DCE-MRI, focusing on an overview of currently available data on bpMRI and mpMRI, as well as on studies providing information on the potential better usability of DCE-MRI in improving the sensitivity and specificity of mpMRI examinations of the prostate.

Characterization of Microvascular Invasion in Hepatocellular Carcinoma Using Computational Modeling of Interstitial Fluid Pressure and Velocity

BACKGROUND

Most solid tumors show increased interstitial fluid pressure (IFP), and this increased IFP is an obstacle to treatment. A noninvasive model for measuring IFP in hepatocellular carcinoma (HCC) is an unresolved issue.

PURPOSE

To develop a noninvasive model to measure IFP and interstitial fluid velocity (IFV) in HCC and to characterize the microvascular invasion (MVI) status by using this model.

STUDY TYPE

Retrospective.

POPULATION

A total of 97 HCC patients (mean age 57.6 ± 10.9 years, 77.3% males), 53 of them with MVI and 44 of them without MVI.

FIELD STRENGTH/SEQUENCE

A 3-T, three-dimensional spoiled gradient-recalled echo.

ASSESSMENT

MVI was defined as microscopic vascular invasion of small vessels within the peritumoral liver tissue. The volumes of interest (VOIs) were manually delineated and enclosed the tumor lesion and healthy liver parenchyma, respectively. The extended Tofts model (ETM) was used to estimate permeability parameters from all the VOIs. Subsequently, the continuity partial differential equation (PDE) was implemented and IFP and IFV were acquired.

STATISTICAL TESTS

Wilcoxon signed-ranks tests, histogram analysis, Mann-Whitney U test, Fisher's exact test, least absolute shrinkage and selection operator (LASSO) logistic regression, receiver operating characteristic (ROC) curve analysis with the area under the curve (AUC), Youden index, DeLong test, and Benjamini-Hochberg correction. A P value <0.05 was considered statistically significant.

RESULTS

The HCC lesions exhibited elevated IFP and reduced IFV. There were no significant differences in any measured demographic and clinical features between the MVI-positive and MVI-negative groups, except for tumor size. Nine IFP histogram analysis-derived parameters and seven IFV histogram analysis-derived parameters could be used to characterize the MVI status. LASSO regression selected five features: IFP maximum, IFP 10th percentile, IFP 90th percentile, IFV SD, and IFV 10th percentile. The combination of these features showed the highest AUC (0.781) and specificity (77.3%).

DATA CONCLUSION

A noninvasive IFP and IFV measurement model for HCC was developed. Specific IFP- and IFV-derived parameters exhibited significant association with the MVI status.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 2.

Multimodal deep learning for liver cancer applications: a scoping review

Background

Hepatocellular carcinoma is a malignant neoplasm of the liver and a leading cause of cancer-related deaths worldwide. The multimodal data combines several modalities, such as medical images, clinical parameters, and electronic health record (EHR) reports, from diverse sources to accomplish the diagnosis of liver cancer. The introduction of deep learning models with multimodal data can enhance the diagnosis and improve physicians' decision-making for cancer patients.

Objective

This scoping review explores the use of multimodal deep learning techniques (i.e., combining medical images and EHR data) in diagnosing and prognosis of hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA).

Methodology

A comprehensive literature search was conducted in six databases along with forward and backward references list checking of the included studies. PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extension for scoping review guidelines were followed for the study selection process. The data was extracted and synthesized from the included studies through thematic analysis.

Results

Ten studies were included in this review. These studies utilized multimodal deep learning to predict and diagnose hepatocellular carcinoma (HCC), but no studies examined cholangiocarcinoma (CCA). Four imaging modalities (CT, MRI, WSI, and DSA) and 51 unique EHR records (clinical parameters and biomarkers) were used in these studies. The most frequently used medical imaging modalities were CT scans followed by MRI, whereas the most common EHR parameters used were age, gender, alpha-fetoprotein AFP, albumin, coagulation factors, and bilirubin. Ten unique deep-learning techniques were applied to both EHR modalities and imaging modalities for two main purposes, prediction and diagnosis.

Conclusion

The use of multimodal data and deep learning techniques can help in the diagnosis and prediction of HCC. However, there is a limited number of works and available datasets for liver cancer, thus limiting the overall advancements of AI for liver cancer applications. Hence, more research should be undertaken to explore further the potential of multimodal deep learning in liver cancer applications.

Preoperative prediction and risk assessment of microvascular invasion in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is one of the most common and highly lethal tumors worldwide. Microvascular invasion (MVI) is a significant risk factor for recurrence and poor prognosis after surgical resection for HCC patients. Accurately predicting the status of MVI preoperatively is critical for clinicians to select treatment modalities and improve overall survival. However, MVI can only be diagnosed by pathological analysis of postoperative specimens. Currently, numerous indicators in serology (including liquid biopsies) and imaging have been identified to effective in predicting the occurrence of MVI, and the multi-indicator model based on deep learning greatly improves accuracy of prediction. Moreover, several genes and proteins have been identified as risk factors that are strictly associated with the occurrence of MVI. Therefore, this review evaluates various predictors and risk factors, and provides guidance for subsequent efforts to explore more accurate predictive methods and to facilitate the conversion of risk factors into reliable predictors.

Improving the malignancy prediction of breast cancer based on the integration of radiomics features from dual-view mammography and clinical parameters

Radiomics has been a promising imaging biomarker for many malignant diseases. We developed a novel radiomics strategy that incorporating radiomics features extracted from dual-view mammograms and clinical parameters for identifying benign and malignant breast lesions, and validated whether the radiomics assessment could improve the accurate diagnosis of breast cancer. A total of 380 patients (mean age, 52 ± 7 years) with 621 breast lesions utilizing mammograms on craniocaudal (CC) and mediolateral oblique (MLO) views were randomly allocated into the training (n = 486) and testing (n = 135) sets in this retrospective study. A total of 1184 and 2368 radiomics features were extracted from single-position region of interest (ROI) and position-paired ROI, separately. Clinical parameters were then combined for better prediction. Recursive feature elimination and least absolute shrinkage and selection operator methods were applied to select optimal predictive features. Random forest was used to conduct the predictive model. Intraclass correlation coefficient test was used to assess repeatability and reproducibility of features. After preprocessing, 467 radiomics features and clinical parameters remained in the single-view and dual-view models. The performance and significance of models were quantified by the area under the curve (AUC), sensitivity, specificity, and accuracy. The correlation analysis between variables was evaluated using the correlation ratio and Pearson correlation coefficient. The model using a combination of dual-view radiomics and clinical parameters achieved a favorable performance (AUC: 0.804, 95% CI: 0.668-0.916), outperformed single-view model and model without clinical parameters. Incorporating with radiomics features of dual-view (CC&MLO) mammogram, age, breast density, and type of suspicious lesions can provide a noninvasive approach to evaluate the malignancy of breast lesions and facilitate clinical decision-making.

Contrast-Enhanced Ultrasound with Deep Learning with Attention Mechanisms for Predicting Microvascular Invasion in Single Hepatocellular Carcinoma

RATIONALE AND OBJECTIVES

Prediction of microvascular invasion (MVI) status of hepatocellular carcinoma (HCC) holds clinical significance for decision-making regarding the treatment strategy and evaluation of patient prognosis. We developed a deep learning (DL) model based on contrast-enhanced ultrasound (CEUS) to predict MVI of HCC.

MATERIALS AND METHODS

We retrospectively analyzed the data for single primary HCCs that were evaluated with CEUS 1 week before surgical resection from December 2014 to February 2022. The study population was divided into training (n = 198) and test (n = 54) cohorts. In this study, three DL models (Resnet50, Resnet50+BAM, Resnet50+SE) were trained using the training cohort and tested in the test cohort. Tumor characteristics were also evaluated by radiologists, and multivariate regression analysis was performed to determine independent indicators for the development of predictive nomogram models. The performance of the three DL models was compared to that of the MVI prediction model based on radiologist evaluations.

RESULTS

The best-performing model, ResNet50+SE model achieved the ROC of 0.856, accuracy of 77.2, specificity of 93.9%, and sensitivity of 52.4% in the test group. The MVI prediction model based on a combination of three independent predictors showed a C-index of 0.729, accuracy of 69.4, specificity of 73.8%, and sensitivity of 62%.

CONCLUSION

The DL algorithm can accurately predict MVI of HCC on the basis of CEUS images, to help identify high-risk patients for the assist treatment.

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.

Estimating Microvascular Invasion in Patients with Resectable Multinodular Hepatocellular Carcinoma by Using Preoperative Contrast-Enhanced MRI: Establishment and Validation of a Risk Score

Objective

To determine the preoperative clinicoradiological factors to predict microvascular invasion (MVI) in patients with resectable multinodular hepatocellular carcinoma (mHCC), and further to establish and validate a stratified risk scoring system.

Methods

Two hundred and seventy-three patients with pathologically confirmed mHCC (≥2 lesions) without major vascular invasion and biliary tract tumor thrombosis, who underwent preoperative contrast-enhanced MRI and hepatectomy, were consecutively enrolled (training/validation cohort=193/80). Preoperative clinicoradiological variables were collected and analyzed. The multivariable logistic regression was performed to determine the independent predictors of MVI and create a risk score system. The C-index, calibration curve and decision curve were used to evaluate the performance of the risk score. A risk score-based prognostic stratification system was performed in mHCC patients. The risk score system was further verified in the validation cohort.

Results

AFP > 400 ng/mL, presence of satellite nodule, mosaic architecture and increased total tumor diameter were independent predictors of MVI while fat in mass was an independent protective factor of MVI. The risk score yielded satisfactory C-index values (training/validation cohort: 0.777/0.758) and fitted well in calibration curves. Decision curve analysis further confirmed its clinical utility. Based on the risk score, mHCC patients were stratified into high-/low-MVI-risk subgroups with significantly different recurrence-free survival (both P < 0.001).

Conclusion

The presented risk score incorporating clinicoradiological parameters could stratify mHCC patients into high-risk and low-risk subgroups and predict prognosis in patients with resectable mHCC.

Deep learning nomogram based on Gd-EOB-DTPA MRI for predicting early recurrence in hepatocellular carcinoma after hepatectomy

OBJECTIVES

The accurate prediction of post-hepatectomy early recurrence in patients with hepatocellular carcinoma (HCC) is crucial for decision-making regarding postoperative adjuvant treatment and monitoring. We aimed to explore the feasibility of deep learning (DL) features derived from gadoxetate disodium (Gd-EOB-DTPA) MRI, qualitative features, and clinical variables for predicting early recurrence.

METHODS

In this bicentric study, 285 patients with HCC who underwent Gd-EOB-DTPA MRI before resection were divided into training (n = 195) and validation (n = 90) sets. DL features were extracted from contrast-enhanced MRI images using VGGNet-19. Three feature selection methods and five classification methods were combined for DL signature construction. Subsequently, an mp-MR DL signature fused with multiphase DL signatures of contrast-enhanced images was constructed. Univariate and multivariate logistic regression analyses were used to identify early recurrence risk factors including mp-MR DL signature, microvascular invasion (MVI), and tumor number. A DL nomogram was built by incorporating deep features and significant clinical variables to achieve early recurrence prediction.

RESULTS

MVI (p = 0.039), tumor number (p = 0.001), and mp-MR DL signature (p < 0.001) were independent risk factors for early recurrence. The DL nomogram outperformed the clinical nomogram in the training set (AUC: 0.949 vs. 0.751; p < 0.001) and validation set (AUC: 0.909 vs. 0.715; p = 0.002). Excellent DL nomogram calibration was achieved in both training and validation sets. Decision curve analysis confirmed the clinical usefulness of DL nomogram.

CONCLUSION

The proposed DL nomogram was superior to the clinical nomogram in predicting early recurrence for HCC patients after hepatectomy.

KEY POINTS

• Deep learning signature based on Gd-EOB-DTPA MRI was the predominant independent predictor of early recurrence for hepatocellular carcinoma (HCC) after hepatectomy. • Deep learning nomogram based on clinical factors and Gd-EOB-DTPA MRI features is promising for predicting early recurrence of HCC. • Deep learning nomogram outperformed the conventional clinical nomogram in predicting early recurrence.

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.

Clinical applications of artificial intelligence in liver imaging

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

Time to surgery is not an oncological risk factor in HCC patients undergoing liver resection

PURPOSE

Given limitations of the health care systems in case of unforeseeable events, e.g., the COVID pandemic as well as trends in prehabilitation, time from diagnosis to surgery (time to surgery, (TTS)) has become a research issue in malignancies. Thus, we investigated whether TTS is associated with oncological outcome in HCC patients undergoing surgery.

METHODS

A monocentric cohort of 217 patients undergoing liver resection for HCC between 2009 and 2021 was analyzed. Individuals were grouped according to TTS and compared regarding clinical characteristics. Overall survival (OS) and recurrence-free survival (RFS) was compared using Kaplan-Meier analysis and investigated by univariate and multivariable Cox regressions.

RESULTS

TTS was not associated with OS (p=0.126) or RFS (p=0.761) of the study cohort in univariate analysis. In multivariable analysis age (p=0.028), ASA (p=0.027), INR (0.016), number of HCC nodules (p=0.026), microvascular invasion (MVI; p<0.001), and postoperative complications (p<0.001) were associated with OS and INR (p=0.005), and number of HCC nodules (p<0.001) and MVI (p<0.001) were associated with RFS. A comparative analysis of TTS subgroups was conducted (group 1, ≤30 days, n=55; group 2, 31-60 days, n=79; group 3, 61-90 days, n=45; group 4, >90 days, n=38). Here, the median OS were 62, 41, 38, and 40 months (p=0.602 log rank) and median RFS were 21, 26, 26, and 25 months (p=0.994 log rank). No statistical difference regarding oncological risk factors were observed between these groups.

CONCLUSION

TTS is not associated with earlier tumor recurrence or reduced overall survival in surgically treated HCC patients.

Are deep models in radiomics performing better than generic models? A systematic review

BACKGROUND

Application of radiomics proceeds by extracting and analysing imaging features based on generic morphological, textural, and statistical features defined by formulas. Recently, deep learning methods were applied. It is unclear whether deep models (DMs) can outperform generic models (GMs).

METHODS

We identified publications on PubMed and Embase to determine differences between DMs and GMs in terms of receiver operating area under the curve (AUC).

RESULTS

Of 1,229 records (between 2017 and 2021), 69 studies were included, 61 (88%) on tumours, 68 (99%) retrospective, and 39 (56%) single centre; 30 (43%) used an internal validation cohort; and 18 (26%) applied cross-validation. Studies with independent internal cohort had a median training sample of 196 (range 41-1,455); those with cross-validation had only 133 (43-1,426). Median size of validation cohorts was 73 (18-535) for internal and 94 (18-388) for external. Considering the internal validation, in 74% (49/66), the DMs performed better than the GMs, vice versa in 20% (13/66); no difference in 6% (4/66); and median difference in AUC 0.045. On the external validation, DMs were better in 65% (13/20), GMs in 20% (4/20) cases; no difference in 3 (15%); and median difference in AUC 0.025. On internal validation, fused models outperformed GMs and DMs in 72% (20/28), while they were worse in 14% (4/28) and equal in 14% (4/28); median gain in AUC was + 0.02. On external validation, fused model performed better in 63% (5/8), worse in 25% (2/8), and equal in 13% (1/8); median gain in AUC was + 0.025.

CONCLUSIONS

Overall, DMs outperformed GMs but in 26% of the studies, DMs did not outperform GMs.

The utility of Vision Transformer in preoperatively predicting microvascular invasion status of hepatocellular carcinoma

BACKGROUND

Microvascular invasion (MVI) is a risk factor for early recurrence and poor prognosis of hepatocellular carcinoma (HCC). Preoperative assessment of MVI status is beneficial for clinical therapy and prognosis evaluation.

METHODS

A total of 305 surgically resected patients were included retrospectively. All recruited patients underwent plain and contrast-enhanced abdominal CT. They were then randomly divided into training and validation sets in a ratio of 8:2. Self-attention-based ViT-B/16 and ResNet-50 analyzed CT images to predict MVI status preoperatively. Then, Grad-CAM was used to generate an attention map showing the high-risk MVI patches. Using five-fold cross validation, the performance of each model was evaluated.

RESULTS

Among 305 HCC patients, 99 patients were pathologically MVI-positive and 206 were MVI-negative. ViT-B/16 with fusion phase predicted the MVI status with an AUC of 0.882 and an accuracy of 86.8% in the validation set, which is similar to ResNet-50 with an AUC of 0.875 and an accuracy of 87.2%. The fusion phase improved performance a bit as compared to the single phase used for MVI prediction. The influence of peritumoral tissue on predictive ability was limited. A color visualization of the suspicious patches where microvascular has invaded was presented by attention maps.

CONCLUSION

ViT-B/16 model can predict preoperative MVI status in CT images of HCC patients. Assisted by attention maps, it can assist patients in making tailored treatment decisions.

PET-guided attention for prediction of microvascular invasion in preoperative hepatocellular carcinoma on PET/CT

PURPOSE

To achieve PET/CT-based preoperative prediction of microvascular invasion in hepatocellular carcinoma by combining the advantages of PET and CT.

METHODS

This retrospective study included a total of 100 patients from two institutions who underwent PET/CT imaging. The above patients were divided into a training cohort (n = 70) and a validation cohort (n = 30). This study was based on PET/CT images to evaluate the possibility of microvascular invasion (MVI) of patients. In this study, we proposed a two-branch PET-guided attention network to predict MVI. The model used a two-branch network to extract image features from PET and CT, respectively. The PET-guided attention module aimed to enable the model to focus on the lesion region and reduce the disturbance of irrelevant and redundant information. Model performance was evaluated by the area under the curve (AUC) of the receiver operating characteristic (ROC) curve.

RESULTS

The method outperformed the single-modality prediction model for preoperative hepatocyte microvascular invasion, achieving an AUC of 0.907. On the validation set, accuracy reached 0.846, precision reached 0.881, recall 0.793, and F1-score 0.835.

CONCLUSION

The model exploits the particularities of the molecular metabolic function of PET and the anatomical structure of CT and can strongly improve the accuracy of clinical diagnosis of MVI.

Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma

The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.

A novel multimodal deep learning model for preoperative prediction of microvascular invasion and outcome in hepatocellular carcinoma

BACKGROUND

Accurate preoperative identification of the microvascular invasion (MVI) can relieve the pressure from personalized treatment adaptation and improve the poor prognosis for hepatocellular carcinoma (HCC). This study aimed to develop and validate a novel multimodal deep learning (DL) model for predicting MVI based on multi-parameter magnetic resonance imaging (MRI) and contrast-enhanced computed tomography (CT).

METHODS

A total of 397 HCC patients underwent both CT and MRI examinations before surgery. We established the radiological models (R^CT, R^MRI) by support vector machine (SVM), DL models (DL^CT_ALL, DL^MRI_ALL, DL^CT + MRI) by ResNet18. The comprehensive model (C^ALL) involving multi-modality DL features and clinical and radiological features was constructed using SVM. Model performance was quantified by the area under the receiver operating characteristic curve (AUC) and compared by net reclassification index (NRI) and integrated discrimination improvement (IDI).

RESULTS

The DL^CT + MRI model exhibited superior predicted efficiency over single-modality models, especially over the DL^CT_ALL model (AUC: 0.819 vs. 0.742, NRI > 0, IDI > 0). The DL^MRI_ALL model improved the performance over the R^MRI model (AUC: 0.794 vs. 0.766, NRI > 0, IDI < 0), but no such difference was found between the DL^CT_ALL model and R^CT model (AUC: 0.742 vs. 0.710, NRI < 0, IDI < 0). Furthermore, both the DL^CT + MRI and C^ALL models revealed the prognostic power in recurrence-free survival stratification (P < 0.001).

CONCLUSION

The proposed DL^CT + MRI model showed robust capability in predicting MVI and outcomes for HCC. Besides, the identification ability of the multi-modality DL model was better than any single modality, especially for CT.

Preoperative and Prognostic Prediction of Microvascular Invasion in Hepatocellular Carcinoma: A Review Based on Artificial Intelligence

Microvascular invasion of hepatocellular carcinoma is an important factor affecting tumor recurrence after liver resection and liver transplantation. There are many ways to classify microvascular invasion, however, an international consensus is urgently needed. Recently, artificial intelligence has emerged as an important tool for improving the clinical management of hepatocellular carcinoma. Many studies about microvascular invasion currently focus on preoperative and prognosis prediction of microvascular invasion using artificial intelligence. In this paper, we review the definition and staging of microvascular invasion, especially the diagnosis of it by using artificial intelligence. In preoperative prediction, deep learning based on multimodal data modeling of radiomics-screened features, clinical features, and medical images is currently the most effective means. In prognostic prediction, pathology is the gold standard, and the techniques used should more effectively utilize the global features of the pathology images.

Artificial intelligence: A review of current applications in hepatocellular carcinoma imaging

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and currently the third-leading cause of cancer-related death worldwide. Recently, artificial intelligence (AI) has emerged as an important tool to improve clinical management of HCC, including for diagnosis, prognostication and evaluation of treatment response. Different AI approaches, such as machine learning and deep learning, are both based on the concept of developing prediction algorithms from large amounts of data, or big data. The era of digital medicine has led to a rapidly expanding amount of routinely collected health data which can be leveraged for the development of AI models. Various studies have constructed AI models by using features extracted from ultrasound imaging, computed tomography imaging and magnetic resonance imaging. Most of these models have used convolutional neural networks. These tools have shown promising results for HCC detection, characterization of liver lesions and liver/tumor segmentation. Regarding treatment, studies have outlined a role for AI in evaluation of treatment response and improvement of pre-treatment planning. Several challenges remain to fully integrate AI models in clinical practice. Future research is still needed to robustly evaluate AI algorithms in prospective trials, and improve interpretability, generalizability and transparency. If such challenges can be overcome, AI has the potential to profoundly change the management of patients with HCC. The purpose of this review was to sum up current evidence on AI approaches using imaging for the clinical management of HCC.

Microvascular invasion risk scores affect the estimation of early recurrence after resection in patients with hepatocellular carcinoma: a retrospective study

BACKGROUND

Microvascular invasion (MVI) is a histological factor that is closely related to the early recurrence of hepatocellular carcinoma (HCC) after resection. To investigate whether a noninvasive risk score system based on MVI status can be established to estimate early recurrence of HCC after resection.

METHODS

Between January 2018 to March 2021, a total of 108 patients with surgically treated single HCC was retrospectively included in our study. Fifty-one patients were pathologically confirmed with MVI and 57 patients were absent of MVI. Univariate and multivariate logistic regression analysis of preoperative laboratory and magnetic resonance imaging (MRI) features were used to screen noninvasive risk factors in association with MVI in HCC. Risk scores based on the odds ratio (OR) values of MVI-related risk factors were calculated to estimate the early recurrence after resection of HCC.

RESULTS

In multivariate logistic regression analysis, tumor size > 2 cm (P = 0.024, OR 3.05, 95% CI 1.19-11.13), Prothrombin induced by vitamin K absence-II > 32 mAU/ml (P = 0.001, OR 4.13, 95% CI 1.23-11.38), irregular tumor margin (P = 0.018, OR 3.10, 95% CI 1.16-8.31) and apparent diffusion coefficient value < 1007 × 10^- 3mm²/s (P = 0.035, OR 2.27, 95% CI 1.14-7.71) were independent risk factors correlated to MVI in HCC. Risk scores of patients were calculated and were then categorized into high or low-risk levels. In multivariate cox survival analysis, only high-risk score of MVI was the independent risk factor of early recurrence (P = 0.009, OR 2.11, 95% CI 1.20-3.69), with a sensitivity and specificity of 0.52, 0.88, respectively.

CONCLUSION

A risk score system based on MVI status can help stratify patients in high-risk of early recurrence after resection of HCC.

Preoperative prediction of intrahepatic cholangiocarcinoma lymph node metastasis by means of machine learning: a multicenter study in China

BACKGROUND

Hepatectomy is currently the most effective modality for the treatment of intrahepatic cholangiocarcinoma (ICC). The status of the lymph nodes directly affects the choice of surgical method and the formulation of postoperative treatment plans. Therefore, a preoperative judgment of lymph node status is of great significance for patients diagnosed with this condition. Previous prediction models mostly adopted logistic regression modeling, and few relevant studies applied random forests in the prediction of ICC lymph node metastasis (LNM).

METHODS

A total of 149 ICC patients who met clinical conditions were enrolled in the training group. Taking into account preoperative clinical data and imaging features, 21 indicators were included for analysis and modeling. Logistic regression was used to filter variables through multivariate analysis, and random forest regression was used to rank the importance of these variables through the use of algorithms. The model's prediction accuracy was assessed by the concordance index (C-index) and calibration curve and validated with external data.

RESULT

Multivariate analysis shows that Carcinoembryonic antigen (CEA), Carbohydrate antigen19-9 (CA19-9), and lymphadenopathy on imaging are independent risk factors for lymph node metastasis. The random forest algorithm identifies the top four risk factors as CEA, CA19-9, and lymphadenopathy on imaging and Aspartate Transaminase (AST). The predictive power of random forest is significantly better than the nomogram established by logistic regression in both the validation group and the training group (Area Under Curve reached 0.758 in the validation group).

CONCLUSIONS

We constructed a random forest model for predicting lymph node metastasis that, compared with the traditional nomogram, has higher prediction accuracy and simultaneously plays an auxiliary role in imaging examinations.

Deep Learning of Liver Contrast-Enhanced Ultrasound to Predict Microvascular Invasion and Prognosis in Hepatocellular Carcinoma

Background and Aims

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.

Methods

A total of 436 patients with surgically resected HCC who underwent preoperative CEUS were retrospectively enrolled. Patients were divided into training (n = 301), validation (n = 102), and test (n = 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.

Results

Compared with the Clinical model, the CEUS-DCNN model exhibited similar sensitivity, but higher specificity (71.4% vs. 38.1%, p = 0.03) in the test group. The CECL-DCNN model showed significantly higher specificity (81.0% vs. 38.1%, p = 0.005) and accuracy (78.8% vs. 51.5%, p = 0.009) than the Clinical model, with an AUC of 0.865. The Clinical predicted MVI could not significantly distinguish OS or RFS (both p > 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], p = 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], p = 0.009) and RFS (HR with 95% CI: 3.3 [1.23–8.91], p = 0.011) in the test group.

Conclusions

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.

Application of a Convolutional Neural Network for Multitask Learning to Simultaneously Predict Microvascular Invasion and Vessels that Encapsulate Tumor Clusters in Hepatocellular Carcinoma

Background

Hepatocellular carcinoma (HCC) is the fourth most common cause of cancer death worldwide, and the prognosis remains dismal. In this study, two pivotal factors, microvascular invasion (MVI) and vessels encapsulating tumor clusters (VETC) were preoperatively predicted simultaneously to assess prognosis.

Methods

A total of 133 HCC patients who underwent surgical resection and preoperative gadolinium ethoxybenzyl-diethylenetriaminepentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) were included. The statuses of MVI and VETC were obtained from the pathological report and CD34 immunohistochemistry, respectively. A three-dimensional convolutional neural network (3D CNN) for single-task learning aimed at MVI prediction and for multitask learning aimed at simultaneous prediction of MVI and VETC was established by using multiphase Gd-EOB-DTPA-enhanced MRI.

Results

The 3D CNN for single-task learning achieved an area under receiver operating characteristics curve (AUC) of 0.896 (95% CI: 0.797–0.994). Multitask learning with simultaneous extraction of MVI and VETC features improved the performance of MVI prediction, with an AUC value of 0.917 (95% CI: 0.825–1.000), and achieved an AUC value of 0.860 (95% CI: 0.728–0.993) for the VETC prediction. The multitask learning framework could stratify high- and low-risk groups regarding overall survival (p < 0.0001) and recurrence-free survival (p < 0.0001), revealing that patients with MVI+/VETC+ were associated with poor prognosis.

Conclusions

A deep learning framework based on 3D CNN for multitask learning to predict MVI and VETC simultaneously could improve the performance of MVI prediction while assessing the VETC status. This combined prediction can stratify prognosis and enable individualized prognostication in HCC patients before curative resection.

Supplementary Information

The online version contains supplementary material available at 10.1245/s10434-022-12000-6.

Deep-learning-based analysis of preoperative MRI predicts microvascular invasion and outcome in hepatocellular carcinoma

Background

Preoperative prediction of microvascular invasion (MVI) is critical for treatment strategy making in patients with hepatocellular carcinoma (HCC). We aimed to develop a deep learning (DL) model based on preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict the MVI status and clinical outcomes in patients with HCC.

Methods

We retrospectively included a total of 321 HCC patients with pathologically confirmed MVI status. Preoperative DCE-MRI of these patients were collected, annotated, and further analyzed by DL in this study. A predictive model for MVI integrating DL-predicted MVI status (DL-MVI) and clinical parameters was constructed with multivariate logistic regression.

Results

Of 321 HCC patients, 136 patients were pathologically MVI absent and 185 patients were MVI present. Recurrence-free survival (RFS) and overall survival (OS) were significantly different between the DL-predicted MVI-absent and MVI-present. Among all clinical variables, only DL-predicted MVI status and a-fetoprotein (AFP) were independently associated with MVI: DL-MVI (odds ratio [OR] = 35.738; 95% confidence interval [CI] 14.027–91.056; p < 0.001), AFP (OR = 4.634, 95% CI 2.576–8.336; p < 0.001). To predict the presence of MVI, DL-MVI combined with AFP achieved an area under the curve (AUC) of 0.824.

Conclusions

Our predictive model combining DL-MVI and AFP achieved good performance for predicting MVI and clinical outcomes in patients with HCC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12957-022-02645-8.

Artificial Intelligence Algorithm in Classification and Recognition of Primary Hepatic Carcinoma Images under Magnetic Resonance Imaging

This study aimed to discuss the application value of the bias field correction algorithm in magnetic resonance imaging (MRI) images of patients with primary hepatic carcinoma (PHC). In total, 52 patients with PHC were selected as the experimental group and divided into three subgroups: mild (15 cases), moderate (19 cases), and severe (18 cases) according to pathological grading. Another 52 patients with hepatic nodules in the same period were included in the control group. All the patients underwent dynamic contrast-enhanced (DCE) MRI examination, and the image qualities of MRI before and after bias field correction were compared. The DCE-MRI perfusion parameters were measured, including the transport constant Ktrans, reverse rate constant Kep, extravascular extracellular volume fraction (Ve), plasma volume (Vp), microvascular density (MVD), hepatic artery perfusion index (HPI), mean transit time of contrast agent (MTT), time to peak (TTP), blood volume (BV), hepatic arterial perfusion (HAP), full perfusion (FP), and portal venous perfusion (PVP). It was found that the sensitivity (93.63%), specificity (71.62%), positive predictive value (95.63%), negative predictive value (71.62%), and accuracy (90.01%) of MRI examination processed by the bias field correction algorithm were all significantly greater than those before processing (P < 0.05). The Ktrans, Kep, Ve, Vp, and MVD of patients in the experimental group were significantly larger than those of the control group, and severe group> moderate group> mild group (P < 0.05). HPI, MTT, TTP, BV, and HAP of patients in the experimental group were also significantly greater than those of the control group, which was shown as severe group > moderate group > mild group (P < 0.05). FP and PVP of the experimental group were significantly lower than those of the control group, and severe group < moderate group < mild group (P < 0.05). It was suggested that in MRI images of patients with PHC, the bias field correction algorithm could significantly improve the diagnosis rate. Each perfusion parameter was related to the pathological grading, which could be used to evaluate the prognosis of patients.

Artificial intelligence for the prevention and clinical management of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) currently represents the fifth most common malignancy and the third-leading cause of cancer-related death worldwide, with incidence and mortality rates that are increasing. Recently, artificial intelligence (AI) has emerged as a unique opportunity to improve the full spectrum of HCC clinical care, by improving HCC risk prediction, diagnosis, and prognostication. AI approaches include computational search algorithms, machine learning (ML) and deep learning (DL) models. ML consists of a computer running repeated iterations of models, in order to progressively improve performance of a specific task, such as classifying an outcome. DL models are a subtype of ML, based on neural network structures that are inspired by the neuroanatomy of the human brain. A growing body of recent data now apply DL models to diverse data sources - including electronic health record data, imaging modalities, histopathology and molecular biomarkers - to improve the accuracy of HCC risk prediction, detection and prediction of treatment response. Despite the promise of these early results, future research is still needed to standardise AI data, and to improve both the generalisability and interpretability of results. If such challenges can be overcome, AI has the potential to profoundly change the way in which care is provided to patients with or at risk of HCC.

Radiomics for the Preoperative Evaluation of Microvascular Invasion in Hepatocellular Carcinoma: A Meta-Analysis

Background

Microvascular invasion (MVI) is an independent risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). To perform a meta-analysis to investigate the diagnostic performance of radiomics for the preoperative evaluation of MVI in HCC and the effect of potential factors.

Materials and Methods

A systematic literature search was performed in PubMed, Embase, and the Cochrane Library for studies focusing on the preoperative evaluation of MVI in HCC with radiomics methods. Data extraction and quality assessment of the retrieved studies were performed. Statistical analysis included data pooling, heterogeneity testing and forest plot construction. Meta-regression and subgroup analyses were performed to reveal the effect of potential explanatory factors [design, combination of clinical factors, imaging modality, number of participants, and Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) applicability risk] on the diagnostic performance.

Results

Twenty-two studies with 4,129 patients focusing on radiomics for the preoperative prediction of MVI in HCC were included. The pooled sensitivity, specificity and area under the receiver operating characteristic curve (AUC) were 84% (95% CI: 81, 87), 83% (95% CI: 78, 87) and 0.90 (95% CI: 0.87, 0.92). Substantial heterogeneity was observed among the studies (I²=94%, 95% CI: 88, 99). Meta-regression showed that all investigative covariates contributed to the heterogeneity in the sensitivity analysis (P < 0.05). Combined clinical factors, MRI, CT and number of participants contributed to the heterogeneity in the specificity analysis (P < 0.05). Subgroup analysis showed that the pooled sensitivity, specificity and AUC estimates were similar among studies with CT or MRI.

Conclusion

Radiomics is a promising noninvasive method that has high preoperative diagnostic performance for MVI status. Radiomics based on CT and MRI had a comparable predictive performance for MVI in HCC. Prospective, large-scale and multicenter studies with radiomics methods will improve the diagnostic power for MVI in the future.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=259363, identifier CRD42021259363.

Diagnostic Accuracy of Artificial Intelligence Based on Imaging Data for Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma: A Systematic Review and Meta-Analysis

Background

The presence of microvascular invasion (MVI) is considered an independent prognostic factor associated with early recurrence and poor survival in hepatocellular carcinoma (HCC) patients after resection. Artificial intelligence (AI), mainly consisting of non-deep learning algorithms (NDLAs) and deep learning algorithms (DLAs), has been widely used for MVI prediction in medical imaging.

Aim

To assess the diagnostic accuracy of AI algorithms for non-invasive, preoperative prediction of MVI based on imaging data.

Methods

Original studies reporting AI algorithms for non-invasive, preoperative prediction of MVI based on quantitative imaging data were identified in the databases PubMed, Embase, and Web of Science. The quality of the included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) scale. The pooled sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) were calculated using a random-effects model with 95% CIs. A summary receiver operating characteristic curve and the area under the curve (AUC) were generated to assess the diagnostic accuracy of the deep learning and non-deep learning models. In the non-deep learning group, we further performed meta-regression and subgroup analyses to identify the source of heterogeneity.

Results

Data from 16 included studies with 4,759 cases were available for meta-analysis. Four studies on deep learning models, 12 studies on non-deep learning models, and two studies compared the efficiency of the two types. For predictive performance of deep learning models, the pooled sensitivity, specificity, PLR, NLR, and AUC values were 0.84 [0.75–0.90], 0.84 [0.77–0.89], 5.14 [3.53–7.48], 0.2 [0.12–0.31], and 0.90 [0.87–0.93]; and for non-deep learning models, they were 0.77 [0.71–0.82], 0.77 [0.73–0.80], 3.30 [2.83–3.84], 0.30 [0.24–0.38], and 0.82 [0.79–0.85], respectively. Subgroup analyses showed a significant difference between the single tumor subgroup and the multiple tumor subgroup in the pooled sensitivity, NLR, and AUC.

Conclusion

This meta-analysis demonstrates the high diagnostic accuracy of non-deep learning and deep learning methods for MVI status prediction and their promising potential for clinical decision-making. Deep learning models perform better than non-deep learning models in terms of the accuracy of MVI prediction, methodology, and cost-effectiveness.

Systematic Review Registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php? RecordID=260891, ID:CRD42021260891.

A predictive model integrating deep and radiomics features based on gadobenate dimeglumine-enhanced MRI for postoperative early recurrence of hepatocellular carcinoma

PURPOSE

Hepatocellular carcinoma (HCC) is the most common liver cancer worldwide, and early recurrence of HCC after curative hepatic resection is indicative of poor prognoses. We aim to develop a predictive model for postoperative early recurrence of HCC based on deep and radiomics features from multi-phasic magnetic resonance imaging (MRI).

MATERIALS AND METHODS

A total of 472 HCC patients were included and divided into the training (n = 378) and validation (n = 94) cohorts in the retrospective study. We separately extracted radiomics features and deep features from eight phases of gadoxetic acid-enhanced MRI and utilized the least absolute shrinkage and selection operator logistic regression algorithm for feature selection and model construction. We integrated the selected two types of features into a combined model and established a radiomics model as well as a deep learning (DL) model for comparison.

RESULTS

In the training and validation cohorts, the combined model demonstrated better performance for stratifying patients at high risk of early recurrence (AUC of 0.911 and 0.840, accuracy of 0.779 and 0.777, sensitivity of 0.927 and 0.769, specificity 0.720 and 0.779) than the radiomics model (AUC of 0.740 and 0.780) and the DL model (AUC of 0.887 and 0.813).

CONCLUSION

The combined model integrating deep and radiomics features from multi-phasic MRI is efficient for noninvasively stratifying patients at high risk of early HCC recurrence after resection.