Radiomics models for diagnosing microvascular invasion in hepatocellular carcinoma: which model is the best model?

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.

Radiomics-Based Prediction of Microvascular Invasion Grade in Nodular Hepatocellular Carcinoma Using Contrast-Enhanced Magnetic Resonance Imaging

Objective

The aim of this study is to develop and verify a magnetic resonance imaging (MRI)-based radiomics model for predicting the microvascular invasion grade (MVI) before surgery in individuals diagnosed with nodular hepatocellular carcinoma (HCC).

Methods

A total of 198 patients were included in the study and were randomly stratified into two groups: a training group consisting of 139 patients and a test group comprising 59 patients. The tumor lesion was manually segmented on the largest cross-sectional slice using ITK SNAP, with agreement reached between two radiologists. The selection of radiomics features was carried out using the LASSO (Least Absolute Shrinkage and Selection Operator) algorithm. Radiomics models were then developed through maximum correlation, minimum redundancy, and logistic regression analyses. The performance of the models in predicting MVI grade was assessed using the area under the receiver operating characteristic curve (AUC) and metrics derived from the confusion matrix.

Results

There were no notable statistical differences in sex, age, BMI (body mass index), tumor size, and location between the training and test groups. The AP and PP radiomic model constructed for predicting MVI grade demonstrated an AUC of 0.83 (0.75-0.88) and 0.73 (0.64-0.80) in the training group and an AUC of 0.74 (0.61-0.85) and 0.62 (0.48-0.74) in test group, respectively. The combined model consists of imaging data and clinical data (age and AFP), achieved an AUC of 0.85 (0.78-0.91) and 0.77 (0.64-0.87) in the training and test groups, respectively.

Conclusion

A radiomics model utilizing-contrast-enhanced MRI demonstrates strong predictive capability for differentiating MVI grades in individuals with nodular HCC. This model could potentially function as a dependable and resilient tool to support hepatologists and radiologists in their preoperative decision-making processes.

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.

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

BACKGROUND

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.

AIM

To explore the efficacy of texture analysis based on multi-parametric magnetic resonance (MR) imaging (MRI) in predicting microvascular invasion (MVI) in preoperative HCC.

METHODS

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).

RESULTS

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%.

CONCLUSION

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.

Prediction of microvascular invasion and pathological differentiation of hepatocellular carcinoma based on a deep learning model

PURPOSE

To develop a deep learning (DL) model based on preoperative contrast-enhanced computed tomography (CECT) images to predict microvascular invasion (MVI) and pathological differentiation of hepatocellular carcinoma (HCC).

METHODS

This retrospective study included 640 consecutive patients who underwent surgical resection and were pathologically diagnosed with HCC at two medical institutions from April 2017 to May 2022. CECT images and relevant clinical parameters were collected. All the data were divided into 368 training sets, 138 test sets and 134 validation sets. Through DL, a segmentation model was used to obtain a region of interest (ROI) of the liver, and a classification model was established to predict the pathological status of HCC.

RESULTS

The liver segmentation model based on the 3D U-Network had a mean intersection over union (mIoU) score of 0.9120 and a Dice score of 0.9473. Among all the classification prediction models based on the Swin transformer, the fusion models combining image information and clinical parameters exhibited the best performance. The area under the curve (AUC) of the fusion model for predicting the MVI status was 0.941, its accuracy was 0.917, and its specificity was 0.908. The AUC values of the fusion model for predicting poorly differentiated, moderately differentiated and highly differentiated HCC based on the test set were 0.962, 0.957 and 0.996, respectively.

CONCLUSION

The established DL models established can be used to noninvasively and effectively predict the MVI status and the degree of pathological differentiation of HCC, and aid in clinical diagnosis and treatment.

Machine learning-based identification of contrast-enhancement phase of computed tomography scans

Contrast-enhanced computed tomography scans (CECT) are routinely used in the evaluation of different clinical scenarios, including the detection and characterization of hepatocellular carcinoma (HCC). Quantitative medical image analysis has been an exponentially growing scientific field. A number of studies reported on the effects of variations in the contrast enhancement phase on the reproducibility of quantitative imaging features extracted from CT scans. The identification and labeling of phase enhancement is a time-consuming task, with a current need for an accurate automated labeling algorithm to identify the enhancement phase of CT scans. In this study, we investigated the ability of machine learning algorithms to label the phases in a dataset of 59 HCC patients scanned with a dynamic contrast-enhanced CT protocol. The ground truth labels were provided by expert radiologists. Regions of interest were defined within the aorta, the portal vein, and the liver. Mean density values were extracted from those regions of interest and used for machine learning modeling. Models were evaluated using accuracy, the area under the curve (AUC), and Matthew's correlation coefficient (MCC). We tested the algorithms on an external dataset (76 patients). Our results indicate that several supervised learning algorithms (logistic regression, random forest, etc.) performed similarly, and our developed algorithms can accurately classify the phase of contrast enhancement.

Enhancing preoperative diagnosis of microvascular invasion in hepatocellular carcinoma: domain-adaptation fusion of multi-phase CT images

Objectives

In patients with hepatocellular carcinoma (HCC), accurately predicting the preoperative microvascular invasion (MVI) status is crucial for improving survival rates. This study proposes a multi-modal domain-adaptive fusion model based on deep learning methods to predict the preoperative MVI status in HCC.

Materials and methods

From January 2008 to May 2022, we collected 163 cases of HCC from our institution and 42 cases from another medical facility, with each case including Computed Tomography (CT) images from the pre-contrast phase (PCP), arterial phase (AP), and portal venous phase (PVP). We divided our institution's dataset (n=163) into training (n=119) and test sets (n=44) in an approximate 7:3 ratio. Additionally, we included cases from another institution (n=42) as an external validation set (test1 set). We constructed three single-modality models, a simple concatenated multi-modal model, two current state-of-the-art image fusion model and a multi-modal domain-adaptive fusion model (M-DAFM) based on deep learning methods. We evaluated and analyzed the performance of these constructed models in predicting preoperative MVI using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI) methods.

Results

In comparison with all models, M-DAFM achieved the highest AUC values across the three datasets (0.8013 for the training set, 0.7839 for the test set, and 0.7454 for the test1 set). Notably, in the test set, M-DAFM's Decision Curve Analysis (DCA) curves consistently demonstrated favorable or optimal net benefits within the 0-0.65 threshold probability range. Additionally, the Net Reclassification Improvement (NRI) values between M-DAFM and the three single-modal models, as well as the simple concatenation model, were all greater than 0 (all p < 0.05). Similarly, the NRI values between M-DAFM and the two current state-of-the-art image fusion models were also greater than 0. These findings collectively indicate that M-DAFM effectively integrates valuable information from multi-phase CT images, thereby enhancing the model's preoperative predictive performance for MVI.

Conclusion

The M-DAFM proposed in this study presents an innovative approach to improve the preoperative predictive performance of MVI.

CT radiomics for prediction of microvascular invasion in hepatocellular carcinoma: A systematic review and meta-analysis

The power of computed tomography (CT) radiomics for preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) demonstrated in current research is variable. This systematic review and meta-analysis aim to evaluate the value of CT radiomics for MVI prediction in HCC, and to investigate the methodologic quality in the workflow of radiomics research. Databases of PubMed, Embase, Web of Science, and Cochrane Library were systematically searched. The methodologic quality of included studies was assessed. Validation data from studies with Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement type 2a or above were extracted for meta-analysis. Eleven studies were included, among which nine were eligible for meta-analysis. Radiomics quality scores of the enrolled eleven studies varied from 6 to 17, accounting for 16.7%-47.2% of the total points, with an average score of 14. Pooled sensitivity, specificity, and Area Under the summary receiver operator Characteristic Curve (AUC) were 0.82 (95% CI 0.77-0.86), 0.79 (95% CI 0.75-0.83), and 0.87 (95% CI 0.84-0.91) for the predictive performance of CT radiomics, respectively. Meta-regression and subgroup analyses showed radiomics model based on 3D tumor segmentation, and deep learning model achieved superior performances compared to 2D segmentation and non-deep learning model, respectively (AUC: 0.93 vs. 0.83, and 0.97 vs. 0.83, respectively). This study proves that CT radiomics could predict MVI in HCC. The heterogeneity of the included studies precludes a definition of the role of CT radiomics in predicting MVI, but methodology warrants uniformization in the radiology community regarding radiomics in HCC.

A Reliable and Repeatable Model for Predicting Microvascular Invasion in Patients With Hepatocellular Carcinoma

RATIONALE AND OBJECTIVES

The reproducibility of imaging models for predicting microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) remains questionable due to inconsistent interpretation of image signs. Our aim was to screen for high-consensus MRI features to develop a repeatable model for predicting MVI.

MATERIALS AND METHODS

We included 219 patients with HCC who underwent surgical resection, and patients were divided into a training cohort (n = 145) and a validation cohort (n = 74). Morphological characteristics, signal features on hepatobiliary phases, and dynamic enhancement patterns were qualitatively interobserver evaluated. Interobserver agreement was assessed using Cohen's κ for selecting features with high interobserver agreement. Risk factors that were significant in stepwise multivariate analysis and that could be measured with good interobserver agreement were used to construct a predictive model, which was assessed in the validation cohort. The diagnostic performance of the model was evaluated based on area under the receiver operating characteristic curve (AUC).

RESULTS

Multivariate analysis identified nonsmooth tumor margin, absence of radiologic capsule, and intratumoral artery as independent risk factors of MVI. These MRI-based features showed good or nearly perfect interobserver agreement between radiologists (κ > 0.6). The predictive model predicted MVI well in the training (AUC 0.734) and validation cohorts (AUC 0.759) and fitted well to calibration curves.

CONCLUSION

MRI features included nonsmooth tumor margin, absence of radiologic capsule, and intratumoral artery that can be assessed with high interobserver agreement can predict MVI in HCC patients. The predictive model described here may be useful to radiologists, regardless of experience level.

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.

Precision diagnosis of hepatocellular carcinoma

ABSTRACT

Hepatocellular carcinoma (HCC) is the most common type of primary hepatocellular carcinoma (PHC). Early diagnosis of HCC remains the key to improve the prognosis. In recent years, with the promotion of the concept of precision medicine and more in-depth analysis of the biological mechanism underlying HCC, new diagnostic methods, including emerging serum markers, liquid biopsies, molecular diagnosis, and advances in imaging (novel contrast agents and radiomics), have emerged one after another. Herein, we reviewed and analyzed scientific advances in the early diagnosis of HCC and discussed their application and shortcomings. This review aimed to provide a reference for scientific research and clinical practice of HCC.

Predicting Microvascular Invasion in Hepatocellular Carcinoma Using CT-based Radiomics Model

Background Prediction of microvascular invasion (MVI) may help determine treatment strategies for hepatocellular carcinoma (HCC). Purpose To develop a radiomics approach for predicting MVI status based on preoperative multiphase CT images and to identify MVI-associated differentially expressed genes. Materials and Methods Patients with pathologically proven HCC from May 2012 to September 2020 were retrospectively included from four medical centers. Radiomics features were extracted from tumors and peritumor regions on preoperative registration or subtraction CT images. In the training set, these features were used to build five radiomics models via logistic regression after feature reduction. The models were tested using internal and external test sets against a pathologic reference standard to calculate area under the receiver operating characteristic curve (AUC). The optimal AUC radiomics model and clinical-radiologic characteristics were combined to build the hybrid model. The log-rank test was used in the outcome cohort (Kunming center) to analyze early recurrence-free survival and overall survival based on high versus low model-derived score. RNA sequencing data from The Cancer Image Archive were used for gene expression analysis. Results A total of 773 patients (median age, 59 years; IQR, 49-64 years; 633 men) were divided into the training set (n = 334), internal test set (n = 142), external test set (n = 141), outcome cohort (n = 121), and RNA sequencing analysis set (n = 35). The AUCs from the radiomics and hybrid models, respectively, were 0.76 and 0.86 for the internal test set and 0.72 and 0.84 for the external test set. Early recurrence-free survival (P < .01) and overall survival (P < .007) can be categorized using the hybrid model. Differentially expressed genes in patients with findings positive for MVI were involved in glucose metabolism. Conclusion The hybrid model showed the best performance in prediction of MVI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Summers in this issue.

Radiomics in the diagnosis and treatment of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a common malignant tumor. At present, early diagnosis of HCC is difficult and therapeutic methods are limited. Radiomics can achieve accurate quantitative evaluation of the lesions without invasion, and has important value in the diagnosis and treatment of HCC. Radiomics features can predict the development of cancer in patients, serve as the basis for risk stratification of HCC patients, and help clinicians distinguish similar diseases, thus improving the diagnostic accuracy. Furthermore, the prediction of the treatment outcomes helps determine the treatment plan. Radiomics is also helpful in predicting the HCC recurrence, disease-free survival and overall survival. This review summarized the role of radiomics in the diagnosis, treatment and prognosis of HCC.

Clinical application of AI-based PET images in oncological patients

Based on the advantages of revealing the functional status and molecular expression of tumor cells, positron emission tomography (PET) imaging has been performed in numerous types of malignant diseases for diagnosis and monitoring. However, insufficient image quality, the lack of a convincing evaluation tool and intra- and interobserver variation in human work are well-known limitations of nuclear medicine imaging and restrict its clinical application. Artificial intelligence (AI) has gained increasing interest in the field of medical imaging due to its powerful information collection and interpretation ability. The combination of AI and PET imaging potentially provides great assistance to physicians managing patients. Radiomics, an important branch of AI applied in medical imaging, can extract hundreds of abstract mathematical features of images for further analysis. In this review, an overview of the applications of AI in PET imaging is provided, focusing on image enhancement, tumor detection, response and prognosis prediction and correlation analyses with pathology or specific gene mutations in several types of tumors. Our aim is to describe recent clinical applications of AI-based PET imaging in malignant diseases and to focus on the description of possible future developments.

Quality of radiomics for predicting microvascular invasion in hepatocellular carcinoma: a systematic review

OBJECTIVES

To comprehensively evaluate the reporting quality, risk of bias, and radiomics methodology quality of radiomics models for predicting microvascular invasion in hepatocellular carcinoma.

METHODS

A systematic search of available literature was performed in PubMed, Embase, Web of Science, Scopus, and the Cochrane Library up to January 21, 2022. Studies that developed and/or validated machine learning models based on radiomics data to predict microvascular invasion in hepatocellular carcinoma were included. These studies were reviewed by two investigators and the consensus data were used for analyzing. The reporting quality, risk of bias, and radiomics methodological quality were evaluated by Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD), Prediction model Risk of Bias Assessment Tool, and Radiomics Quality Score (RQS), respectively.

RESULTS

A total of 30 studies met eligibility criteria with 24 model developing studies and 6 model developing and external validation studies. The median overall TRIPOD adherence was 75.4% (range 56.7-94.3%). All studies were at high risk of bias with at least 2 of 20 sources of bias. Furthermore, 28 studies showed unclear risks of bias in up to 5 signaling questions because of the lack of specified reports. The median RQS score was 37.5% (range 25-61.1%).

CONCLUSION

Current radiomic models for MVI-status prediction have moderate to good reporting quality, moderate radiomics methodology quality, and high risk of bias in model development and validation.

KEY POINTS

• Current microvascular invasion prediction radiomics studies have moderate to good reporting quality, moderate radiomics methodology quality, and high risk of bias in model development and validation. • Data representativeness, feature robustness, events-per-variable ratio, evaluation metrics, and appropriate validation are five main aspects futures studies should focus more on to improve the quality of radiomics. • Both Radiomics Quality Score and Prediction model Risk of Bias Assessment Tool are needed to comprehensively evaluate a radiomics study.

Performance of Radiomics in Microvascular Invasion Risk Stratification and Prognostic Assessment in Hepatocellular Carcinoma: A Meta-Analysis

BACKGROUND

Primary liver cancer is the sixth most commonly diagnosed cancer and the third leading cause of cancer death. Advances in phenomenal imaging are paving the way for application in diagnosis and research. The poor prognosis of advanced HCC warrants a personalized approach. The objective was to assess the value of imaging phenomics for risk stratification and prognostication of HCC.

METHODS

We performed a meta-analysis of manuscripts published to January 2023 on MEDLINE addressing the value of imaging phenomics for HCC risk stratification and prognostication. Publication information for each were collected using a standardized data extraction form.

RESULTS

Twenty-seven articles were analyzed. Our study shows the importance of imaging phenomics in HCC MVI prediction. When the training and validation datasets were analyzed separately by the random-effects model, in the training datasets, radiomics had good MVI prediction (AUC of 0.81 (95% CI 0.76-0.86)). Similar results were found in the validation datasets (AUC of 0.79 (95% CI 0.72-0.85)). Using the fixed effects model, the mean AUC of all datasets was 0.80 (95% CI 0.76-0.84).

CONCLUSIONS

Imaging phenomics is an effective solution to predict microvascular invasion risk, prognosis, and treatment response in patients with HCC.

New insights into a microvascular invasion prediction model in hepatocellular carcinoma: A retrospective study from the SEER database and China

Background and Aims

The prognosis of liver cancer is strongly influenced by microvascular infiltration (MVI). Accurate preoperative MVI prediction can aid clinicians in the selection of suitable treatment options. In this study, we constructed a novel, reliable, and adaptable nomogram for predicting MVI.

Methods

Using the Surveillance, Epidemiology, and End Results (SEER) database, we extracted the clinical data of 1,063 patients diagnosed with hepatocellular carcinoma (HCC) and divided it into either a training (n = 739) or an internal validation cohort (n = 326). Based on multivariate analysis, the training cohort data were analyzed and a nomogram was generated for MVI prediction. This was further verified using an internal validation cohort and an external validation cohort involving 293 Chinese patients. Furthermore, to evaluate the efficacy, accuracy, and clinical use of the nomogram, we used concordance index (C-index), calibration curve, and decision curve analysis (DCA) techniques.

Results

In accordance with the multivariate analysis, tumor size, tumor number, alpha-fetoprotein (AFP), and histological grade were independently associated with MVI. The established model exhibited satisfactory performance in predicting MVI. The C-indices were 0.719, 0.704, and 0.718 in the training, internal validation, and external validation cohorts, respectively. The calibration curves showed an excellent consistency between the predictions and actual observations. Finally, DCA demonstrated that the newly developed nomogram had favorable clinical utility.

Conclusions

We established and verified a novel preoperative MVI prediction model in HCC patients. This model can be a beneficial tool for clinicians in selecting an optimal treatment plan for HCC patients.

Preoperative prediction model of microvascular invasion in patients with hepatocellular carcinoma

BACKGROUND

Microvascular invasion (MVI) is an adverse factor for the prognosis of patients with hepatocellular carcinoma (HCC). We aimed to construct a preoperative prediction model for MVI, thereby providing a reference for clinicians in formulating treatment options for HCC.

METHODS

A total of 360 patients with non-metastatic HCC were retrospectively enrolled. We used logistic regression analysis to screen out independent risk factors for MVI and further constructed a predictive model for MVI. The performance of the model was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).

RESULTS

Logistic regression analysis revealed that fibrinogen (>4 g/L) (OR: 6.529), alpha-fetoprotein (≥ 400 ng/mL) (OR: 2.676), cirrhosis (OR: 2.25), tumor size (OR: 1.239), and poor tumor border (OR: 3.126) were independent risk factors of MVI. The prediction model of MVI had C-index of 0.746 and 0.772 in the training and validation cohorts, respectively. The calibration curves showed good agreement between actual and predicted MVI risk. Finally, DCA reveals that this model has good clinical utility.

CONCLUSION

The nomogram-based model we established can predict the preoperative MVI well and provides reference for surgeons to make clinical treatment decisions.

The Role of Radiomics and AI Technologies in the Segmentation, Detection, and Management of Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is the most common primary hepatic neoplasm. Thanks to recent advances in computed tomography (CT) and magnetic resonance imaging (MRI), there is potential to improve detection, segmentation, discrimination from HCC mimics, and monitoring of therapeutic response. Radiomics, artificial intelligence (AI), and derived tools have already been applied in other areas of diagnostic imaging with promising results. In this review, we briefly discuss the current clinical applications of radiomics and AI in the detection, segmentation, and management of HCC. Moreover, we investigate their potential to reach a more accurate diagnosis of HCC and to guide proper treatment planning.

Radiomics models for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a systematic review and meta-analysis

PURPOSE

To assess the methodological quality and to evaluate the predictive performance of radiomics studies for preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC).

METHODS

Publications between 2017 and 2021 on radiomic MVI prediction in HCC based on CT, MR, ultrasound, and PET/CT were included. The risk of bias was assessed using the prediction model risk of bias assessment tool (PROBAST). Methodological quality was assessed through the radiomics quality score (RQS). Fourteen studies classified as TRIPOD Type 2a or above were used for meta-analysis using random-effects model. Further analyses were performed to investigate the technical factors influencing the predictive performance of radiomics models.

RESULTS

Twenty-three studies including 4947 patients were included. The risk of bias was mainly related to analysis domain. The RQS reached an average of (37.7 ± 11.4)% with main methodological insufficiencies of scientific study design, external validation, and open science. The pooled areas under the receiver operating curve (AUC) were 0.85 (95% CI 0.82-0.89), 0.87 (95% CI 0.83-0.92), and 0.74 (95% CI 0.67-0.80), respectively, for CT, MR, and ultrasound radiomics models. The pooled AUC of ultrasound radiomics model was significantly lower than that of CT (p = 0.002) and MR (p < 0.001). Portal venous phase for CT and hepatobiliary phase for MR were superior to other imaging sequences for radiomic MVI prediction. Segmentation of both tumor and peritumor regions showed better performance than tumor region.

CONCLUSION

Radiomics models show promising prediction performance for predicting MVI in HCC. However, improvements in standardization of methodology are required for feasibility confirmation and clinical translation.

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.

Computed Tomography Radiomics-Based Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Background

Due to the high recurrence rate in hepatocellular carcinoma (HCC) after resection, preoperative prognostic prediction of HCC is important for appropriate patient management. Exploring and developing preoperative diagnostic methods has great clinical value in treating patients with HCC. This study sought to develop and evaluate a novel combined clinical predictive model based on standard triphasic computed tomography (CT) to discriminate microvascular invasion (MVI) in hepatocellular carcinoma (HCC).

Methods

The preoperative findings of 82 patients with HCC, including conventional clinical factors, CT imaging findings, and CT texture analysis (TA), were analyzed retrospectively. All included cases were divided into MVI-negative (n = 33; no MVI) and MVI-positive (n = 49; low or high risk of MVI) groups. TA parameters were extracted from non-enhanced, arterial, portal venous, and equilibrium phase images and subsequently calculated using the Artificial Intelligence Kit. After statistical analyses, a clinical model comprising conventional clinical and CT image risk factors, radiomics signature models, and a novel combined model (fused radiomic signature) was constructed. The area under the curve (AUC) of the receiver operating characteristics (ROC) curve was used to assess the performance of the various models in discriminating MVI.

Results

We found that tumor diameter and pathological grade were effective clinical predictors in clinical model and 12 radiomics features were effective for MVI prediction of each CT phase. The AUCs of the clinical, plain, artery, venous, and delay models were 0.77 (95% CI: 0.67–0.88), 0.75 (95% CI: 0.64–0.87), 0.79 (95% CI: 0.69–0.89), 0.73 (95% CI: 0.61–0.85), and 0.80 (95% CI: 0.70–0.91), respectively. The novel combined model exhibited the best performance, with an AUC of 0.83 (95% CI: 0.74–0.93).

Conclusions

Models derived from triphasic CT can preoperatively predict MVI in patients with HCC. Of the models tested here, the novel combined model was most predictive and could become a useful tool to guide subsequent personalized treatment of HCC.

Preoperative Prediction of Microvascular Invasion Risk Grades in Hepatocellular Carcinoma Based on Tumor and Peritumor Dual-Region Radiomics Signatures

Objective

To predict preoperative microvascular invasion (MVI) risk grade by analyzing the radiomics signatures of tumors and peritumors on enhanced magnetic resonance imaging (MRI) images of hepatocellular carcinoma (HCC).

Methods

A total of 501 HCC patients (training cohort n = 402, testing cohort n = 99) who underwent preoperative Gd-EOB-DTPA-enhanced MRI and curative liver resection within a month were studied retrospectively. Radiomics signatures were selected using the least absolute shrinkage and selection operator (Lasso) algorithm. Unimodal radiomics models based on tumors and peritumors (10mm or 20mm) were established using the Logistic algorithm, using plain T1WI, arterial phase (AP), portal venous phase (PVP), and hepatobiliary phase (HBP) images. Multimodal radiomics models based on different regions of interest (ROIs) were established using a combinatorial modeling approach. Moreover, we merged radiomics signatures and clinico-radiological features to build unimodal and multimodal clinical radiomics models.

Results

In the testing cohort, the AUC of the dual-region (tumor & peritumor 20 mm)radiomics model and single-region (tumor) radiomics model were 0.741 vs 0.694, 0.733 vs 0.725, 0.667 vs 0.710, and 0.559 vs 0.677, respectively, according to AP, PVP, T1WI, and HBP images. The AUC of the final clinical radiomics model based on tumor and peritumoral 20mm incorporating radiomics features in AP&PVP&T1WI images for predicting MVI classification in the training and testing cohorts were 0.962 and 0.852, respectively.

Conclusion

The radiomics signatures of the dual regions for tumor and peritumor on AP and PVP images are of significance to predict MVI.

Automatically Extracted Machine Learning Features from Preoperative CT to Early Predict Microvascular Invasion in HCC: The Role of the Zone of Transition (ZOT)

Background: Microvascular invasion (MVI) is a consolidated predictor of hepatocellular carcinoma (HCC) recurrence after treatments. No reliable radiological imaging findings are available for preoperatively diagnosing MVI, despite some progresses of radiomic analysis. Furthermore, current MVI radiomic studies have not been designed for small HCC nodules, for which a plethora of treatments exists. This study aimed to identify radiomic MVI predictors in nodules ≤3.0 cm by analysing the zone of transition (ZOT), crossing tumour and peritumour, automatically detected to face the uncertainties of radiologist’s tumour segmentation. Methods: The study considered 117 patients imaged by contrast-enhanced computed tomography; 78 patients were finally enrolled in the radiomic analysis. Radiomic features were extracted from the tumour and the ZOT, detected using an adaptive procedure based on local image contrast variations. After data oversampling, a support vector machine classifier was developed and validated. Classifier performance was assessed using receiver operating characteristic (ROC) curve analysis and related metrics. Results: The original 89 HCC nodules (32 MVI+ and 57 MVI−) became 169 (62 MVI+ and 107 MVI−) after oversampling. Of the four features within the signature, three are ZOT heterogeneity measures regarding both arterial and venous phases. On the test set (19MVI+ and 33MVI−), the classifier predicts MVI+ with area under the curve of 0.86 (95%CI (0.70–0.93), p∼10−5), sensitivity = 79% and specificity = 82%. The classifier showed negative and positive predictive values of 87% and 71%, respectively. Conclusions: The classifier showed the highest diagnostic performance in the literature, disclosing the role of ZOT heterogeneity in predicting the MVI+ status.

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.

Radiomics Models for Predicting Microvascular Invasion in Hepatocellular Carcinoma: A Systematic Review and Radiomics Quality Score Assessment

Preoperative prediction of microvascular invasion (MVI) is of importance in hepatocellular carcinoma (HCC) patient treatment management. Plenty of radiomics models for MVI prediction have been proposed. This study aimed to elucidate the role of radiomics models in the prediction of MVI and to evaluate their methodological quality. The methodological quality was assessed by the Radiomics Quality Score (RQS), and the risk of bias was evaluated by the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Twenty-two studies using CT, MRI, or PET/CT for MVI prediction were included. All were retrospective studies, and only two had an external validation cohort. The AUC values of the prediction models ranged from 0.69 to 0.94 in the test cohort. Substantial methodological heterogeneity existed, and the methodological quality was low, with an average RQS score of 10 (28% of the total). Most studies demonstrated a low or unclear risk of bias in the domains of QUADAS-2. In conclusion, a radiomics model could be an accurate and effective tool for MVI prediction in HCC patients, although the methodological quality has so far been insufficient. Future prospective studies with an external validation cohort in accordance with a standardized radiomics workflow are expected to supply a reliable model that translates into clinical utilization.

Radiomics Models for Predicting Microvascular Invasion in Hepatocellular Carcinoma: A Systematic Review and Radiomics Quality Score Assessment

Simple Summary

Microvascular invasion (MVI) is regarded as a sign of early metastasis in liver cancer and can be only diagnosed by a histopathology exam in the resected specimen. Preoperative prediction of MVI status may exert an effect on patient treatment management, for instance, to expand the resection margin. Radiomics can identify delicate imaging features from routinely used radiological images that are invisible to the naked eye and has been increasingly adopted to predict MVI. We reviewed the available radiomics models to evaluate their role in the prediction of MVI. The discriminative capacity of the models ranged from 0.69 to 0.94. Even though the studies were preliminary and the methodologic quality was suboptimal, radiomics models hold promise for the accurate and non-invasive prediction of MVI. In accordance with a standardized radiomics workflow, future prospective studies with external validation are expected to provide a reliable and robust prediction tool for clinical implementation.

Abstract

Preoperative prediction of microvascular invasion (MVI) is of importance in hepatocellular carcinoma (HCC) patient treatment management. Plenty of radiomics models for MVI prediction have been proposed. This study aimed to elucidate the role of radiomics models in the prediction of MVI and to evaluate their methodological quality. The methodological quality was assessed by the Radiomics Quality Score (RQS), and the risk of bias was evaluated by the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Twenty-two studies using CT, MRI, or PET/CT for MVI prediction were included. All were retrospective studies, and only two had an external validation cohort. The AUC values of the prediction models ranged from 0.69 to 0.94 in the test cohort. Substantial methodological heterogeneity existed, and the methodological quality was low, with an average RQS score of 10 (28% of the total). Most studies demonstrated a low or unclear risk of bias in the domains of QUADAS-2. In conclusion, a radiomics model could be an accurate and effective tool for MVI prediction in HCC patients, although the methodological quality has so far been insufficient. Future prospective studies with an external validation cohort in accordance with a standardized radiomics workflow are expected to supply a reliable model that translates into clinical utilization.

Predicting microvascular invasion in hepatocellular carcinoma: a deep learning model validated across hospitals

BACKGROUND

The accuracy of estimating microvascular invasion (MVI) preoperatively in hepatocellular carcinoma (HCC) by clinical observers is low. Most recent studies constructed MVI predictive models utilizing radiological and/or radiomics features extracted from computed tomography (CT) images. These methods, however, rely heavily on human experiences and require manual tumor contouring. We developed a deep learning-based framework for preoperative MVI prediction by using CT images of arterial phase (AP) with simple tumor labeling and without the need of manual feature extraction. The model was further validated on CT images that were originally scanned at multiple different hospitals.

METHODS

CT images of AP were acquired for 309 patients from China Medical University Hospital (CMUH). Images of 164 patients, who took their CT scanning at 54 different hospitals but were referred to CMUH, were also collected. Deep learning (ResNet-18) and machine learning (support vector machine) models were constructed with AP images and/or patients' clinical factors (CFs), and their performance was compared systematically. All models were independently evaluated on two patient cohorts: validation set (within CMUH) and external set (other hospitals). Subsequently, explainability of the best model was visualized using gradient-weighted class activation map (Grad-CAM).

RESULTS

The ResNet-18 model built with AP images and patients' clinical factors was superior than other models achieving a highest AUC of 0.845. When evaluating on the external set, the model produced an AUC of 0.777, approaching its performance on the validation set. Model interpretation with Grad-CAM revealed that MVI relevant imaging features on CT images were captured and learned by the ResNet-18 model.

CONCLUSIONS

This framework provide evidence showing the generalizability and robustness of ResNet-18 in predicting MVI using CT images of AP scanned at multiple different hospitals. Attention heatmaps obtained from model explainability further confirmed that ResNet-18 focused on imaging features on CT overlapping with the conditions used by radiologists to estimate MVI clinically.

Preoperative Prediction of Microvascular Invasion in Patients With Hepatocellular Carcinoma Based on Radiomics Nomogram Using Contrast-Enhanced Ultrasound

PURPOSE

This study aimed to develop a radiomics nomogram based on contrast-enhanced ultrasound (CEUS) for preoperatively assessing microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients.

METHODS

A retrospective dataset of 313 HCC patients who underwent CEUS between September 20, 2016 and March 20, 2020 was enrolled in our study. The study population was randomly grouped as a primary dataset of 192 patients and a validation dataset of 121 patients. Radiomics features were extracted from the B-mode (BM), artery phase (AP), portal venous phase (PVP), and delay phase (DP) images of preoperatively acquired CEUS of each patient. After feature selection, the BM, AP, PVP, and DP radiomics scores (Rad-score) were constructed from the primary dataset. The four radiomics scores and clinical factors were used for multivariate logistic regression analysis, and a radiomics nomogram was then developed. We also built a preoperative clinical prediction model for comparison. The performance of the radiomics nomogram was evaluated via calibration, discrimination, and clinical usefulness.

RESULTS

Multivariate analysis indicated that the PVP and DP Rad-score, tumor size, and AFP (alpha-fetoprotein) level were independent risk predictors associated with MVI. The radiomics nomogram incorporating these four predictors revealed a superior discrimination to the clinical model (based on tumor size and AFP level) in the primary dataset (AUC: 0.849 vs. 0.690; p < 0.001) and validation dataset (AUC: 0.788 vs. 0.661; p = 0.008), with a good calibration. Decision curve analysis also confirmed that the radiomics nomogram was clinically useful. Furthermore, the significant improvement of net reclassification index (NRI) and integrated discriminatory improvement (IDI) implied that the PVP and DP radiomics signatures may be very useful biomarkers for MVI prediction in HCC.

CONCLUSION

The CEUS-based radiomics nomogram showed a favorable predictive value for the preoperative identification of MVI in HCC patients and could guide a more appropriate surgical planning.

Application of artificial intelligence in preoperative imaging of hepatocellular carcinoma: Current status and future perspectives

Hepatocellular carcinoma (HCC) is the most common primary malignant liver tumor in China. Preoperative diagnosis of HCC is challenging because of atypical imaging manifestations and the diversity of focal liver lesions. Artificial intelligence (AI), such as machine learning (ML) and deep learning, has recently gained attention for its capability to reveal quantitative information on images. Currently, AI is used throughout the entire radiomics process and plays a critical role in multiple fields of medicine. This review summarizes the applications of AI in various aspects of preoperative imaging of HCC, including segmentation, differential diagnosis, prediction of histopathology, early detection of recurrence after curative treatment, and evaluation of treatment response. We also review the limitations of previous studies and discuss future directions for diagnostic imaging of HCC.

Artificial intelligence in assessment of hepatocellular carcinoma treatment response

Artificial Intelligence (AI) continues to shape the practice of radiology, with imaging of hepatocellular carcinoma (HCC) being of no exception. This article prepared by members of the LI-RADS Treatment Response (TR LI-RADS) work group and associates, presents recent trends in the utility of AI applications for the volumetric evaluation and assessment of HCC treatment response. Various topics including radiomics, prognostic imaging findings, and locoregional therapy (LRT) specific issues will be discussed in the framework of HCC treatment response classification systems with focus on the Liver Reporting and Data System treatment response algorithm (LI-RADS TRA).

Application of radiomics in hepatocellular carcinoma: A review

Hepatocellular carcinoma (HCC) is the most common form of primary liver cancer with low 5-year survival rate. The high molecular heterogeneity in HCC poses huge challenges for clinical practice or trial design and has become a major barrier to improving the management of HCC. However, current clinical practice based on single bioptic or archived tumor tissue has been deficient in identifying useful biomarkers. The concept of radiomics was first proposed in 2012 and is different from the traditional imaging analysis based on the qualitative or semi-quantitative analysis by radiologists. Radiomics refers to high-throughput extraction of large amounts number of high-dimensional quantitative features from medical images through machine learning or deep learning algorithms. Using the radiomics method could quantify tumoral phenotypes and heterogeneity, which may provide benefits in clinical decision-making at a lower cost. Here, we review the workflow and application of radiomics in HCC.

Radiomics in Oncology, Part 1: Technical Principles and Gastrointestinal Application in CT and MRI

Simple Summary

Part I is an overview aimed to investigate some technical principles and the main fields of radiomic application in gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy in gastrointestinal cancers, describing mostly the results for each pre-eminent tumor. In particular, this paper provides a general description of the main radiomic drawbacks and future challenges, which limit radiomic application in clinical setting as routine. Further investigations need to standardize and validate the Radiomics as a helpful tool in management of oncologic patients. In that context, Radiomics has been playing a relevant role and could be considered as a future imaging landscape.

Abstract

Radiomics has been playing a pivotal role in oncological translational imaging, particularly in cancer diagnosis, prediction prognosis, and therapy response assessment. Recently, promising results were achieved in management of cancer patients by extracting mineable high-dimensional data from medical images, supporting clinicians in decision-making process in the new era of target therapy and personalized medicine. Radiomics could provide quantitative data, extracted from medical images, that could reflect microenvironmental tumor heterogeneity, which might be a useful information for treatment tailoring. Thus, it could be helpful to overcome the main limitations of traditional tumor biopsy, often affected by bias in tumor sampling, lack of repeatability and possible procedure complications. This quantitative approach has been widely investigated as a non-invasive and an objective imaging biomarker in cancer patients; however, it is not applied as a clinical routine due to several limitations related to lack of standardization and validation of images acquisition protocols, features segmentation, extraction, processing, and data analysis. This field is in continuous evolution in each type of cancer, and results support the idea that in the future Radiomics might be a reliable application in oncologic imaging. The first part of this review aimed to describe some radiomic technical principles and clinical applications to gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy.

Considerable effects of imaging sequences, feature extraction, feature selection, and classifiers on radiomics-based prediction of microvascular invasion in hepatocellular carcinoma using magnetic resonance imaging

Background

Microvascular invasion (MVI) has a significant effect on the prognosis of hepatocellular carcinoma (HCC), but its preoperative identification is challenging. Radiomics features extracted from medical images, such as magnetic resonance (MR) images, can be used to predict MVI. In this study, we explored the effects of different imaging sequences, feature extraction and selection methods, and classifiers on the performance of HCC MVI predictive models.

Methods

After screening against the inclusion criteria, 69 patients with HCC and preoperative gadoxetic acid-enhanced MR images were enrolled. In total, 167 features were extracted from the MR images of each sequence for each patient. Experiments were designed to investigate the effects of imaging sequence, number of gray levels (Ng), quantization algorithm, feature selection method, and classifiers on the performance of radiomics biomarkers in the prediction of HCC MVI. We trained and tested these models using leave-one-out cross-validation (LOOCV).

Results

The radiomics model based on the images of the hepatobiliary phase (HBP) had better predictive performance than those based on the arterial phase (AP), portal venous phase (PVP), and pre-enhanced T1-weighted images [area under the receiver operating characteristic (ROC) curve (AUC) =0.792 vs. 0.641/0.634/0.620, P=0.041/0.021/0.010, respectively]. Compared with the equal-probability and Lloyd-Max algorithms, the radiomics features obtained using the Uniform quantization algorithm had a better performance (AUC =0.643/0.666 vs. 0.792, P=0.002/0.003, respectively). Among the values of 8, 16, 32, 64, and 128, the best predictive performance was achieved when the Ng was 64 (AUC =0.792 vs. 0.584/0.697/0.677/0.734, P<0.001/P=0.039/0.001/0.137, respectively). We used a two-stage feature selection method which combined the least absolute shrinkage and selection operator (LASSO) and recursive feature elimination (RFE) gradient boosting decision tree (GBDT), which achieved better stability than and outperformed LASSO, minimum redundancy maximum relevance (mRMR), and support vector machine (SVM)-RFE (stability =0.967 vs. 0.837/0.623/0.390, respectively; AUC =0.850 vs. 0.792/0.713/0.699, P=0.142/0.007/0.003, respectively). The model based on the radiomics features of HBP images using the GBDT classifier showed a better performance for the preoperative prediction of MVI compared with logistic regression (LR), SVM, and random forest (RF) classifiers (AUC =0.895 vs. 0.850/0.834/0.884, P=0.558/0.229/0.058, respectively). With the optimal combination of these factors, we established the best model, which had an AUC of 0.895, accuracy of 87.0%, specificity of 82.5%, and sensitivity of 93.1%.

Conclusions

Imaging sequences, feature extraction and selection methods, and classifiers can have a considerable effect on the predictive performance of radiomics models for HCC MVI.

Radiomics, Radiogenomics, and Next-Generation Molecular Imaging to Augment Diagnosis of Hepatocellular Carcinoma

Ultrasound, computed tomography, magnetic resonance imaging, and [F]F-fluorodeoxyglucose positron emission tomography are invaluable in the clinical evaluation of human cancers. Radiomics and radiogenomics tools may allow clinicians to standardize interpretation of these conventional imaging modalities, while better linking radiographic hallmarks to disease biology and prognosis. These advances, coupled with next-generation positron emission tomography imaging tracers capable of providing biologically relevant tumor information, may further expand the tools available in our armamentarium against human cancers. We present current imaging methods and explore emerging research that may improve diagnosis and monitoring of local, oligometastatic, and disseminated cancers exhibiting heterogeneous uptake of [F]F-fluorodeoxyglucose, using hepatocellular carcinoma as an example.

Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma

Objective

In order to enhance the detection rate of multiple myeloma and execute an early and more precise disease management, an artificial intelligence assistant diagnosis system is developed.

Methods

4,187 routine blood and biochemical examination records were collected from Shengjing Hospital affiliated to China Medical University from January 2010 to January 2020, which include 1,741 records of multiple myeloma (MM) and 2,446 records of non-myeloma (infectious diseases, rheumatic immune system diseases, hepatic diseases and renal diseases). The data set was split into training and test subsets with the ratio of 4:1 while connecting hemoglobin, serum creatinine, serum calcium, immunoglobulin (A, G and M), albumin, total protein, and the ratio of albumin to globulin data. An early assistant diagnostic model of MM was established by Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Deep Neural Networks (DNN), and Random Forest (RF). Out team calculated the precision and recall of the system. The performance of the diagnostic model was evaluated by using the receiver operating characteristic (ROC) curve.

Results

By designing the features properly, the typical machine learning algorithms SVM, DNN, RF and GBDT all performed well. GBDT had the highest precision (92.9%), recall (90.0%) and F1 score (0.915) for the myeloma group. The maximized area under the ROC (AUROC) was calculated, and the results of GBDT (AUC: 0.975; 95% confidence interval (CI): 0.963–0.986) outperformed that of SVM, DNN and RF.

Conclusion

The model established by artificial intelligence derived from routine laboratory results can accurately diagnose MM, which can boost the rate of early diagnosis.

Deep Learning With 3D Convolutional Neural Network for Noninvasive Prediction of Microvascular Invasion in Hepatocellular Carcinoma

BACKGROUND

Microvascular invasion (MVI) is a critical prognostic factor of hepatocellular carcinoma (HCC). However, it could only be obtained by postoperative histological examination.

PURPOSE

To develop an end-to-end deep-learning models based on MRI images for preoperative prediction of MVI in HCC patients who underwent surgical resection.

STUDY TYPE

Retrospective.

POPULATION

Two hundred and thirty-seven patients with histologically confirmed HCC.

FIELD STRENGTH

1.5 T and 3.0 T.

SEQUENCE

Axial T₂ -weighted (T₂ -w) with turbo spin echo sequence, T₂ -Spectral Presaturation with Inversion Recovery (T₂ -SPIR), and dynamic contrast-enhanced (DCE) imaging with fat suppressed enhanced T₁ high-resolution isotropic volume examination.

ASSESSMENT

The patients were randomly divided into training (N = 158) and validation (N = 79) sets. Data augmentation by random rotation was performed on the training set and the sample size increased to 1940 for each MR sequence. A three-dimensional convolutional neural network (3D CNN) was used to develop four deep-learning models, including three single-layer models based on single-sequence, and fusion model combining three sequences. MVI status was obtained from the postoperative pathology reports.

STATISTICAL TESTS

The dice similarity coefficient (DSC) and Hausdorff distance (HD) were applied to assess the similarity and reproducibility between the manual segmentations of tumor from two radiologists. Receiver operating characteristic curve analysis was used to evaluate model performance. MVI was identified in 92 (38.8%) patients. Good reproducibility with interobserver DSCs of 0.90, 0.89, and 0.89 and HDs of 4.09, 3.67, and 3.60 was observed for PVP, T₂ WI, and T₂ -SPIR, respectively. The fusion model achieved an area under the curve (AUC) of 0.81, sensitivity of 69%, and specificity of 79% in the training set and 0.72, sensitivity of 55%, and specificity of 81% in the validation set.

DATA CONCLUSION

3D CNN model may serve as a noninvasive tool to predict MVI in HCC, whereas its accuracy needs to be enhanced with larger cohort.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

The importance of a nonsmooth tumor margin and incomplete tumor capsule in predicting HCC microvascular invasion on preoperative imaging examination: a systematic review and meta-analysis

OBJECTIVES

Microvascular invasion (MVI) is a key factor affecting the prognosis of hepatocellular carcinoma (HCC). Preoperative imaging plays an important role in the diagnosis of HCC, treatment planning and treatment evaluation, but it is still difficult to detect MVI directly. Whether the appearance of the tumor margin and the capsule on radiological images can predict MVI is still controversial. The aim of this study is to explore the correlation of the presence of MVI with the smoothness of the tumor margin and the integrity of the capsule in HCC.

MATERIALS AND METHODS

The PubMed, Embase, Medline, SCI and Cochrane Library databases up to January 2020. Heterogeneity among studies was assessed by sensitivity analysis, subgroup analysis and meta-regression, and the influence of threshold effects was also analyzed.

RESULTS

Eleven studies with 1618 patients were included. The results of the meta-analysis indicated that there was a significant relationship between MVI and nonsmooth tumor margin (DOR = 4.62 [2.73, 7.81]) and between MVI and incomplete tumor capsule (DOR = 2.25 [1.22, 4.15]); the sensitivity and specificity of these two parameters were 0.757 [0.602, 0.865], 0.597 [0.450, 0.728] and 0.646 [0.455, 0.800], 0.552 [0.419, 0.678], respectively. We drew the receiver operating characteristic (ROC) curves, and the area under curve (AUC) of the nonsmooth tumor margin variable for predicting MVI was 0.72 [0.69, 0.77], and the AUC of the incomplete tumor capsule variable for predicting MVI was 0.62 [0.58, 0.66].

CONCLUSION

Nonsmooth tumor margins and incomplete tumor capsules observed by imaging are important for the preoperative prediction of MVI in HCC.

Risk Factors for Hepatocellular Carcinoma Recurrence and Survival after Liver Transplantation in Patients with HCV-Related Cirrhosis

Purpose

We aimed to identify prognostic factors for survival and recurrence of hepatocellular carcinoma (HCC) after liver transplantation (LT) for patients with HCC and hepatitis C virus-related cirrhosis (HCV-cirrhosis).

Methods

This retrospective cohort study followed all adult patients with HCV-cirrhosis who underwent LT because of HCC or had incidental HCC identified through pathologic examination of the explanted liver at a university hospital in Rio de Janeiro, Brazil, over 11 years (1998-2008). We used Cox regression models to assess the following risk factors regarding HCC recurrence or death after LT: age, Model for End-stage Liver Disease score, Child-Pugh classification, alpha-fetoprotein (AFP), whether patients had undergone locoregional treatment before transplantation, the number of packed red blood cell units (PRBCU) transfused during surgery, the number and size of HCC lesions in the explanted liver, and the presence of microvascular invasion and necrotic areas within HCC lesions.

Results

Seventy-six patients were followed up for a median (interquartile range (IQR)) of 4.4 (0.7-6.6) years. Thirteen (17%) patients had HCC recurrence during the follow-up period, and 26 (34%) died. The median survival time was 6.6 years (95% CI: 2.4-12.0), and the 5-year survival was 52.5% (95% CI: 42.3-65.0%). The final regression model for overall survival included four variables: age (hazard ratio (HR): 1.02, 95% CI: 0.96-1.08, P = 0.603), transplantation waiting time (HR: 1.00, 95% CI: 1.00-1.00, P = 0.190), preoperative AFP serum levels (HR: 1.01, 95% CI: 1.00-1.02, P = 0.006), and whether >4 PRBCU were transfused during surgery (HR: 1.15, 95% CI: 1.05-1.25, P = 0.001). The final cause-specific Cox regression model for HCC recurrence included only microvascular invasion (HR: 14.86, 95% CI: 4.47-49.39, P < 0.001).

Conclusion

In this study of LT for HCV-cirrhosis, preoperative AFP levels and the number of PRBCU transfused during surgery were associated with overall survival, whereas microvascular invasion with HCC recurrence.

The application of texture quantification in hepatocellular carcinoma using CT and MRI: a review of perspectives and challenges

Recently, radiomic texture quantification of tumors has received much attention from radiologists, scientists, and stakeholders because several results have shown the feasibility of using the technique to diagnose and manage oncological conditions. In patients with hepatocellular carcinoma, radiomics has been applied in all stages of tumor evaluation, including diagnosis and characterization of the genotypic behavior of the tumor, monitoring of treatment responses and prediction of various clinical endpoints. It is also useful in selecting suitable candidates for specific treatment strategies. However, the clinical validation of hepatocellular carcinoma radiomics is limited by challenges in imaging protocol and data acquisition parameters, challenges in segmentation techniques, dimensionality reduction, and modeling methods. Identification of the best segmentation and optimal modeling methods, as well as texture features most stable to imaging protocol variability would go a long way in harmonizing HCC radiomics for personalized patient care. This article reviews the process of HCC radiomics, its clinical applications, associated challenges, and current optimization strategies.

Study Processes and Applications of Ultrasomics in Precision Medicine

Ultrasomics is the science of transforming digitally encrypted medical ultrasound images that hold information related to tumor pathophysiology into mineable high-dimensional data. Ultrasomics data have the potential to uncover disease characteristics that are not found with the naked eye. The task of ultrasomics is to quantify the state of diseases using distinctive imaging algorithms and thereby provide valuable information for personalized medicine. Ultrasomics is a powerful tool in oncology but can also be applied to other medical problems for which a disease is imaged. To date there is no comprehensive review focusing on ultrasomics. Here, we describe how ultrasomics works and its capability in diagnosing disease in different organs, including breast, liver, and thyroid. Its pitfalls, challenges and opportunities are also discussed.

Radiomics in liver diseases: Current progress and future opportunities

Liver diseases, a wide spectrum of pathologies from inflammation to neoplasm, have become an increasingly significant health problem worldwide. Noninvasive imaging plays a critical role in the clinical workflow of liver diseases, but conventional imaging assessment may provide limited information. Accurate detection, characterization and monitoring remain challenging. With progress in quantitative imaging analysis techniques, radiomics emerged as an efficient tool that shows promise to aid in personalized diagnosis and treatment decision-making. Radiomics could reflect the heterogeneity of liver lesions via extracting high-throughput and high-dimensional features from multi-modality imaging. Machine learning algorithms are then used to construct clinical target-oriented imaging biomarkers to assist disease management. Here, we review the methodological process in liver disease radiomics studies in a stepwise fashion from data acquisition and curation, region of interest segmentation, liver-specific feature extraction, to task-oriented modelling. Furthermore, the applications of radiomics in liver diseases are outlined in aspects of diagnosis and staging, evaluation of liver tumour biological behaviours, and prognosis according to different disease type. Finally, we discuss the current limitations of radiomics in liver disease studies and explore its future opportunities.

Preoperative Prediction Power of Imaging Methods for Microvascular Invasion in Hepatocellular Carcinoma: A Systemic Review and Meta-Analysis

Background: To compare the predictive power between radiomics and non-radiomics (conventional imaging and functional imaging methods) for preoperative evaluation of microvascular invasion (MVI) in hepatocellular carcinoma (HCC).

Methods: Comprehensive publications were screened in PubMed, Embase, and Cochrane Library. Studies focusing on the discrimination values of imaging methods, including radiomics and non-radiomics methods, for MVI evaluation were included in our meta-analysis.

Results: Thirty-three imaging studies with 5,462 cases, focusing on preoperative evaluation of MVI status in HCC, were included. The sensitivity and specificity of MVI prediction in HCC were 0.78 [95% confidence interval (CI): 0.75–0.80; I² = 70.7%] and 0.78 (95% CI: 0.76–0.81; I² = 0.0%) for radiomics, respectively, and were 0.73 (95% CI: 0.71–0.75; I² = 83.7%) and 0.82 (95% CI: 0.80–0.83; I² = 86.5%) for non-radiomics, respectively. The areas under the receiver operation curves for radiomics and non-radiomics to predict MVI status in HCC were 0.8550 and 0.8601, respectively, showing no significant difference.

Conclusion: The imaging method is feasible to predict the MVI state of HCC. Radiomics method based on medical image data is a promising application in clinical practice and can provide quantifiable image features. With the help of these features, highly consistent prediction performance will be achieved in anticipation.

Contrast-enhanced CT radiomics for preoperative evaluation of microvascular invasion in hepatocellular carcinoma: A two-center study

Background

The present study constructed and validated the use of contrast‐enhanced computed tomography (CT)‐based radiomics to preoperatively predict microvascular invasion (MVI) status (positive vs negative) and risk (low vs high) in patients with hepatocellular carcinoma (HCC).

Methods

We enrolled 637 patients from two independent institutions. Patients from Institution I were randomly divided into a training cohort of 451 patients and a test cohort of 111 patients. Patients from Institution II served as an independent validation set. The LASSO algorithm was used for the selection of 798 radiomics features. Two classifiers for predicting MVI status and MVI risk were developed using multivariable logistic regression. We also performed a survival analysis to investigate the potentially prognostic value of the proposed MVI classifiers.

Results

The developed radiomics signature predicted MVI status with an area under the receiver operating characteristic curve (AUC) of .780, .776, and .743 in the training, test, and independent validation cohorts, respectively. The final MVI status classifier that integrated two clinical factors (age and α‐fetoprotein level) achieved AUC of .806, .803, and .796 in the training, test, and independent validation cohorts, respectively. For MVI risk stratification, the AUCs of the radiomics signature were .746, .664, and .700 in the training, test, and independent validation cohorts, respectively, and the AUCs of the final MVI risk classifier‐integrated clinical stage were .783, .778, and .740, respectively. Survival analysis showed that our MVI status classifier significantly stratified patients for short overall survival or early tumor recurrence.

Conclusions

Our CT radiomics‐based models were able to predict MVI status and MVI risk of HCC and might serve as a reliable preoperative evaluation tool.

The Value of TTPVI in Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Purpose

The objective of our study was to evaluate the value of two-trait predictor of venous invasion (TTPVI) in the prediction of pathological microvascular invasion (pMVI) in patients with hepatocellular carcinoma (HCC) from preoperative computed tomography (CT) and magnetic resonance (MR).

Methods

A total of 128 preoperative patients with findings of HCC were enrolled. Tumor size, tumor margins, tumor capsule, peritumoral enhancement, and TTPVI was assessed on preoperative CT and MRI images. Histopathological features were reviewed: pathological tumor size, tumor differentiation, pMVI along with alpha-fetoprotein level (AFP). Significant imaging findings and histopathological features were determined with univariate and multivariate logistic regression analysis.

Results

Univariate analysis revealed that tumor size (p<0.01), AFP level (p=0.043), tumor differentiation (p<0.01), peritumoral enhancement (p=0.003), pathological tumor size (p<0.01), tumor margins (p<0.01) on CT and MRI, and TTPVI (p<0.01) showed statistically significant associations with pMVI. In multivariate logistic regression analysis, tumor size (odds ratio [OR] = 1.294; 95% confidence interval [CI]: 1.155, 1.451; p < 0.001), tumor differentiation (odds ratio [OR] =1.384; 95% confidence interval [CI]: 1.224, 1.564; p < 0.001), and TTPVI (odds ratio [OR] = 4.802; 95% confidence interval [CI]: 1.037, 22.233; p=0.045) were significant independent predictors of pMVI. Using 5.8 as the threshold for size, one could obtain an area-under-curve (AUC) of 0.793, 95% confidence interval [CI]: 0.715 to 0.857.

Conclusion

Tumor size, tumor differentiation, and TTPVI depicted in preoperative CT and MRI had a statistically significant correlation with pMVI. Hence, TTPVI detected on CT and MRI may be predictive of pMVI in HCC cases.

Development and validation of a prediction model for microvascular invasion in hepatocellular carcinoma

BACKGROUND

Microvascular invasion (MVI) is an important prognostic factor affecting early recurrence and overall survival in hepatocellular carcinoma (HCC) patients after hepatectomy and liver transplantation, but it can be determined only in surgical specimens. Accurate preoperative prediction of MVI is conducive to clinical decisions.

AIM

To develop and validate a preoperative prediction model for MVI in patients with HCC.

METHODS

Data from 454 patients with HCC who underwent hepatectomy at the First Affiliated Hospital of Nanjing Medical University between May 2016 and October 2019 were retrospectively collected. Then, the patients were nonrandomly split into a training cohort and a validation cohort. Logistic regression analysis was used to identify variables significantly associated with MVI that were then included in the nomogram. We evaluated the discrimination and calibration ability of the nomogram by using R software.

RESULTS

MVI was confirmed in 209 (46.0%) patients by a pathological examination. Multivariate logistic regression analysis identified four risk factors independently associated with MVI: Tumor size [odds ratio (OR) = 1.195; 95% confidence interval (CI): 1.107–1.290; P < 0.001], number of tumors (OR = 4.441; 95%CI: 2.112–9.341; P < 0.001), neutrophils (OR = 1.714; 95%CI: 1.036–2.836; P = 0.036), and serum α-fetoprotein (20–400 ng/mL, OR = 1.955; 95%CI: 1.055–3.624; P = 0.033; >400 ng/mL, OR = 3.476; 95%CI: 1.950–6.195; P < 0.001). The concordance index was 0.79 (95%CI: 0.74–0.84) and 0.81 (95%CI: 0.74–0.89) in the training and validation cohorts, respectively. The calibration curves showed good agreement between the predicted risk by the nomogram and real outcomes.

CONCLUSION

We have developed and validated a preoperative prediction model for MVI in patients with HCC. The model could aid physicians in clinical treatment decision making.

Predicting survival after transarterial chemoembolization for hepatocellular carcinoma using a neural network: A Pilot Study

BACKGROUND AND AIMS

Deciding when to repeat and when to stop transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) can be difficult even for experienced investigators. Our aim was to develop a survival prediction model for such patients undergoing TACE using novel machine learning algorithms and to compare it to conventional prediction scores, ART, ABCR and SNACOR.

METHODS

For this retrospective analysis, 282 patients who underwent TACE for HCC at our tertiary referral centre between January 2005 and December 2017 were included in the final analysis. We built an artificial neural network (ANN) including all parameters used by the aforementioned risk scores and other clinically meaningful parameters. Following an 80:20 split, the first 225 patients were used for training; the more recently treated 20% were used for validation.

RESULTS

The ANN had a promising performance at predicting 1-year survival, with an area under the ROC curve (AUC) of 0.77 ± 0.13. Internal validation yielded an AUC of 0.83 ± 0.06, a positive predictive value of 87.5% and a negative predictive value of 68.0%. The sensitivity was 77.8% and specificity 81.0%. In a head-to-head comparison, the ANN outperformed the aforementioned scoring systems, which yielded lower AUCs (SNACOR 0.73 ± 0.07, ABCR 0.70 ± 0.07 and ART 0.54 ± 0.08). This difference reached significance for ART (P < .001); for ABCR and SNACOR significance was not reached (P = .143 and P = .201).

CONCLUSIONS

Artificial neural networks could be better at predicting patient survival after TACE for HCC than traditional scoring systems. Once established, such prediction models could easily be deployed in clinical routine and help determine optimal patient care.