Radiomics and radiogenomics of primary liver cancers

A predictive radiotranscriptomics model based on DCE-MRI for tumor immune landscape and immunotherapy in cholangiocarcinoma

This study aims to determine the predictive role of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) derived radiomic model in tumor immune profiling and immunotherapy for cholangiocarcinoma. To perform radiomic analysis, immune related subgroup clustering was first performed by single sample gene set enrichment analysis (ssGSEA). Second, a total of 806 radiomic features for each phase of DCE-MRI were extracted by utilizing the Python package Pyradiomics. Then, a predictive radiomic signature model was constructed after a three-step features reduction and selection, and receiver operating characteristic (ROC) curve was employed to evaluate the performance of this model. In the end, an independent testing cohort involving cholangiocarcinoma patients with anti-PD-1 Sintilimab treatment after surgery was used to verify the potential application of the established radiomic model in immunotherapy for cholangiocarcinoma. Two distinct immune related subgroups were classified using ssGSEA based on transcriptome sequencing. For radiomic analysis, a total of 10 predictive radiomic features were finally identified to establish a radiomic signature model for immune landscape classification. Regarding to the predictive performance, the mean AUC of ROC curves was 0.80 in the training/validation cohort. For the independent testing cohort, the individual predictive probability by radiomic model and the corresponding immune score derived from ssGSEA was significantly correlated. In conclusion, radiomic signature model based on DCE-MRI was capable of predicting the immune landscape of chalangiocarcinoma. Consequently, a potentially clinical application of this developed radiomic model to guide immunotherapy for cholangiocarcinoma was suggested.

MR radiomics to predict microvascular invasion status and biological process in combined hepatocellular carcinoma-cholangiocarcinoma

OBJECTIVES

To establish an MRI-based radiomics model for predicting the microvascular invasion (MVI) status of cHCC-CCA and to investigate biological processes underlying the radiomics model.

METHODS

The study consisted of a retrospective dataset (82 in the training set, 36 in the validation set) and a prospective dataset (25 patients in the test set) from two hospitals. Based on the training set, logistic regression analyses were employed to develop the clinical-imaging model, while radiomic features were extracted to construct a radiomics model. The diagnosis performance was further validated in the validation and test sets. Prognostic aspects of the radiomics model were investigated using the Kaplan-Meier method and log-rank test. Differential gene expression analysis and gene ontology (GO) analysis were conducted to explore biological processes underlying the radiomics model based on RNA sequencing data.

RESULTS

One hundred forty-three patients (mean age, 56.4 ± 10.5; 114 men) were enrolled, in which 73 (51.0%) were confirmed as MVI-positive. The radiomics model exhibited good performance in predicting MVI status, with the area under the curve of 0.935, 0.873, and 0.779 in training, validation, and test sets, respectively. Overall survival (OS) was significantly different between the predicted MVI-negative and MVI-positive groups (median OS: 25 vs 18 months, p = 0.008). Radiogenomic analysis revealed associations between the radiomics model and biological processes involved in regulating the immune response.

CONCLUSION

A robust MRI-based radiomics model was established for predicting MVI status in cHCC-CCA, in which potential prognostic value and underlying biological processes that regulate immune response were demonstrated.

CRITICAL RELEVANCE STATEMENT

MVI is a significant manifestation of tumor invasiveness, and the MR-based radiomics model established in our study will facilitate risk stratification. Furthermore, underlying biological processes demonstrated in the radiomics model will offer valuable insights for guiding immunotherapy strategies.

KEY POINTS

MVI is of prognostic significance in cHCC-CCA, but lacks reliable preoperative assessment. The MRI-based radiomics model predicts MVI status effectively in cHCC-CCA. The MRI-based radiomics model demonstrated prognostic value and underlying biological processes. The radiomics model could guide immunotherapy and risk stratification in cHCC-CCA.

Radiogenomics of Intrahepatic Cholangiocarcinoma: Correlation of Imaging Features With BAP1 and FGFR Molecular Subtypes

PURPOSE

Clinical research has shown unique tumor behavioral characteristics of BRCA-associated protein-1- (BAP1-) and fibroblast growth factor receptor (FGFR)-mutated intrahepatic cholangiocarcinomas (CCAs), with BAP1-mutated tumors demonstrating more aggressive forms of disease and FGFR-altered CCAs showing more indolent behavior. We performed a retrospective case-control study to evaluate for unique imaging features associated with BAP1 and FGFR genomic markers in intrahepatic CCA (iCCA).

METHODS

Multiple imaging features of iCCA at first staging were analyzed by 2 abdominal radiologists blinded to genomic data. Growth and development of metastases at available follow-up imaging were also recorded, as were basic clinical cohort data. Types of iCCA analyzed included those with BAP1, FGFR, or both alterations, as well as cases with low mutational burden or mutations with low clinical impact, which served as a control or "wild-type" group. There were 18 cases in the FGFR group, 10 with BAP1 mutations, and 31 wild types (controls).

RESULTS

Cases with BAP1 mutations showed significantly larger growth at first year of follow-up (P = 0.03) and more frequent tumor-associated biliary ductal dilatation (P = 0.04) compared with controls. FGFR-altered cases showed more infiltrative margins compared with controls (P = 0.047) and demonstrated less enhancement between arterial to portal venous phases (P = 0.02). BAP1 and FGFR groups had more cases with stage IV disease at presentation than controls (P = 0.025, P = 0.006).

CONCLUSION

Compared with wild-type iCCAs, FGFR-mutated tumors often demonstrate infiltrative margins, and BAP1 tumors show increased biliary ductal dilatation at presentation. BAP1-mutated cases had significantly larger growth at first-year restaging.

A novel radiomics approach for predicting TACE outcomes in hepatocellular carcinoma patients using deep learning for multi-organ segmentation

Transarterial chemoembolization (TACE) represent the standard of therapy for non-operative hepatocellular carcinoma (HCC), while prediction of long term treatment outcomes is a complex and multifactorial task. In this study, we present a novel machine learning approach utilizing radiomics features from multiple organ volumes of interest (VOIs) to predict TACE outcomes for 252 HCC patients. Unlike conventional radiomics models requiring laborious manual segmentation limited to tumoral regions, our approach captures information comprehensively across various VOIs using a fully automated, pretrained deep learning model applied to pre-TACE CT images. Evaluation of radiomics random survival forest models against clinical ones using Cox proportional hazard demonstrated comparable performance in predicting overall survival. However, radiomics outperformed clinical models in predicting progression-free survival. Explainable analysis highlighted the significance of non-tumoral VOI features, with their cumulative importance superior to features from the largest liver tumor. The proposed approach overcomes the limitations of manual VOI segmentation, requires no radiologist input and highlight the clinical relevance of features beyond tumor regions. Our findings suggest the potential of this radiomics models in predicting TACE outcomes, with possible implications for other clinical scenarios.

Application of artificial intelligence radiomics in the diagnosis, treatment, and prognosis of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer, with an increasing incidence and poor prognosis. In the past decade, artificial intelligence (AI) technology has undergone rapid development in the field of clinical medicine, bringing the advantages of efficient data processing and accurate model construction. Promisingly, AI-based radiomics has played an increasingly important role in the clinical decision-making of HCC patients, providing new technical guarantees for prediction, diagnosis, and prognostication. In this review, we evaluated the current landscape of AI radiomics in the management of HCC, including its diagnosis, individual treatment, and survival prognosis. Furthermore, we discussed remaining challenges and future perspectives regarding the application of AI radiomics in HCC.

MRI-based radiomics signature: a potential imaging biomarker for prediction of microvascular invasion in combined hepatocellular-cholangiocarcinoma

PURPOSE

To investigate the potential of radiomics analysis of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in preoperatively predicting microvascular invasion (MVI) in patients with combined hepatocellular-cholangiocarcinoma (cHCC-CC) before surgery.

METHODS

A cohort of 91 patients with histologically confirmed cHCC-CC who underwent preoperative liver DCE-MRI were enrolled and divided into a training cohort (27 MVI-positive and 37 MVI-negative) and a validation cohort (11 MVI-positive and 16 MVI-negative). Clinical characteristics and MR features of the patients were evaluated. Radiomics features were extracted from DCE-MRI, and a radiomics signature was built using the least absolute shrinkage and selection operator (LASSO) algorithm in the training cohort. Prediction performance of the developed radiomics signature was evaluated by utilizing the receiver operating characteristic (ROC) analysis.

RESULTS

Larger tumor size and higher Radscore were associated with the presence of MVI in the training cohort (p = 0.026 and < 0.001, respectively), and theses findings were also confirmed in the validation cohort (p = 0.040 and 0.001, respectively). The developed radiomics signature, composed of 4 stable radiomics features, showed high prediction performance in both the training cohort (AUC = 0.866, 95% CI 0.757-0.938, p < 0.001) and validation cohort (AUC = 0.841, 95% CI 0.650-0.952, p < 0.001).

CONCLUSIONS

The radiomics signature developed from DCE-MRI can be a reliable imaging biomarker to preoperatively predict MVI in cHCC-CC.

Differentiation of Hepatocellular Carcinoma from Intrahepatic Cholangiocarcinoma through MRI Radiomics

The purpose of this study was to investigate the efficacy of magnetic resonance imaging (MRI) radiomics in differentiating hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (ICC). The clinical and MRI data of 129 pathologically confirmed HCC patients and 48 ICC patients treated at the Affiliated Hospital of North Sichuan Medical College between April 2016 and December 2021 were retrospectively analyzed. The patients were randomly divided at a ratio of 7:3 into a training group of 124 patients (90 with HCC and 34 with ICC) and a validation group of 53 patients (39 with HCC and 14 with ICC). Radiomic features were extracted from axial fat suppression T2-weighted imaging (FS-T2WI) and axial arterial-phase (AP) and portal-venous-phase (PVP) dynamic-contrast-enhanced MRI (DCE-MRI) sequences, and the corresponding datasets were generated. The least absolute shrinkage and selection operator (LASSO) method was used to select the best radiomic features. Logistic regression was used to establish radiomic models for each sequence (FS-T2WI, AP and PVP models), a clinical model for optimal clinical variables (C model) and a joint radiomics model (JR model) integrating the radiomics features of all the sequences as well as a radiomics-clinical model combining optimal radiomic features and clinical risk factors (RC model). The performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC). The AUCs of the FS-T2WI, AP, PVP, JR, C and RC models for distinguishing HCC from ICC were 0.693, 0.863, 0.818, 0.914, 0.936 and 0.977 in the training group and 0.690, 0.784, 0.727, 0.802, 0.860 and 0.877 in the validation group, respectively. The results of this study suggest that MRI-based radiomics may help noninvasively differentiate HCC from ICC. The model integrating the radiomics features and clinical risk factors showed a further improvement in performance.

Review of the Application of Dual Drug Delivery Nanotheranostic Agents in the Diagnosis and Treatment of Liver Cancer

Liver cancer has high incidence and mortality rates and its treatment generally requires the use of a combination treatment strategy. Therefore, the early detection and diagnosis of liver cancer is crucial to achieving the best treatment effect. In addition, it is imperative to explore multimodal combination therapy for liver cancer treatment and the synergistic effect of two liver cancer treatment drugs while preventing drug resistance and drug side effects to maximize the achievable therapeutic effect. Gold nanoparticles are used widely in applications related to optical imaging, CT imaging, MRI imaging, biomarkers, targeted drug therapy, etc., and serve as an advanced platform for integrated application in the nano-diagnosis and treatment of diseases. Dual-drug-delivery nano-diagnostic and therapeutic agents have drawn great interest in current times. Therefore, the present report aims to review the effectiveness of dual-drug-delivery nano-diagnostic and therapeutic agents in the field of anti-tumor therapy from the particular perspective of liver cancer diagnosis and treatment.

A novel collaborative self-supervised learning method for radiomic data

The computer-aided disease diagnosis from radiomic data is important in many medical applications. However, developing such a technique relies on labeling radiological images, which is a time-consuming, labor-intensive, and expensive process. In this work, we present the first novel collaborative self-supervised learning method to solve the challenge of insufficient labeled radiomic data, whose characteristics are different from text and image data. To achieve this, we present two collaborative pretext tasks that explore the latent pathological or biological relationships between regions of interest and the similarity and dissimilarity of information between subjects. Our method collaboratively learns the robust latent feature representations from radiomic data in a self-supervised manner to reduce human annotation efforts, which benefits the disease diagnosis. We compared our proposed method with other state-of-the-art self-supervised learning methods on a simulation study and two independent datasets. Extensive experimental results demonstrated that our method outperforms other self-supervised learning methods on both classification and regression tasks. With further refinement, our method will have the potential advantage in automatic disease diagnosis with large-scale unlabeled data available.

Machine learning radiomics to predict the early recurrence of intrahepatic cholangiocarcinoma after curative resection: A multicentre cohort study

PURPOSE

Postoperative early recurrence (ER) leads to a poor prognosis for intrahepatic cholangiocarcinoma (ICC). We aimed to develop machine learning (ML) radiomics models to predict ER in ICC after curative resection.

METHODS

Patients with ICC undergoing curative surgery from three institutions were retrospectively recruited and assigned to training and external validation cohorts. Preoperative arterial and venous phase contrast-enhanced computed tomography (CECT) images were acquired and segmented. Radiomics features were extracted and ranked through their importance. Univariate and multivariate logistic regression analysis was used to identify clinical characteristics. Various ML algorithms were used to construct radiomics-based models, and the predictive performance was evaluated by receiver operating characteristic curves, calibration curves, and decision curve analysis.

RESULTS

127 patients were included for analysis: 90 patients in the training set and 37 patients in the validation set. Ninety-two patients (72.4%) experienced recurrence, including 71 patients exhibiting ER. Male sex, microvascular invasion, TNM stage, and serum CA19-9 were identified as independent risk factors for ER, with the corresponding clinical model having a poor predictive performance (AUC of 0.685). Fifty-seven differential radiomics features were identified, and the 10 most important features were utilized for modelling. Seven ML radiomics models were developed with a mean AUC of 0.87 ± 0.02, higher than the clinical model. Furthermore, the clinical-radiomics models showed similar predictive performance to the radiomics models (AUC of 0.87 ± 0.03).

CONCLUSION

ML radiomics models based on CECT are valuable in predicting ER in ICC.

Hepatocellular carcinoma: State of the art diagnostic imaging

Primary liver cancer is the fourth most common malignancy worldwide, with hepatocellular carcinoma (HCC) comprising up to 90% of cases. Imaging is a staple for surveillance and diagnostic criteria for HCC in current guidelines. Because early diagnosis can impact treatment approaches, utilizing new imaging methods and protocols to aid in differentiation and tumor grading provides a unique opportunity to drastically impact patient prognosis. Within this review manuscript, we provide an overview of imaging modalities used to screen and evaluate HCC. We also briefly discuss emerging uses of new imaging techniques that offer the potential for improving current paradigms for HCC characterization, management, and treatment monitoring.

Radiomics-Based Prediction of Future Portal Vein Tumor Infiltration in Patients with HCC-A Proof-of-Concept Study

Portal vein infiltration (PVI) is a typical complication of HCC. Once diagnosed, it leads to classification as BCLC C with an enormous impact on patient management, as systemic therapies are henceforth recommended. Our aim was to investigate whether radiomics analysis using imaging at initial diagnosis can predict the occurrence of PVI in the course of disease. Between 2008 and 2018, we retrospectively identified 44 patients with HCC and an in-house, multiphase CT scan at initial diagnosis who presented without CT-detectable PVI but developed it in the course of disease. Accounting for size and number of lesions, growth type, arterial enhancement pattern, Child-Pugh stage, AFP levels, and subsequent therapy, we matched 44 patients with HCC who did not develop PVI to those developing PVI in the course of disease (follow-up ended December 2021). After segmentation of the tumor at initial diagnosis and texture analysis, we used LASSO regression to find radiomics features suitable for PVI detection in this matched set. Using an 80:20 split between training and holdout validation dataset, 17 radiomics features remained in the fitted model. Applying the model to the holdout validation dataset, sensitivity to detect occurrence of PVI was 0.78 and specificity was 0.78. Radiomics feature extraction had the ability to detect aggressive HCC morphology likely to result in future PVI. An additional radiomics evaluation at initial diagnosis might be a useful tool to identify patients with HCC at risk for PVI during follow-up benefiting from a closer surveillance.

Radiomics nomogram based on multi-parametric magnetic resonance imaging for predicting early recurrence in small hepatocellular carcinoma after radiofrequency ablation

BACKGROUND

There are few studies on the application of radiomics in the risk prediction of early recurrence (ER) after radiofrequency ablation (RFA). This study evaluated the value of a multi-parametric magnetic resonance imaging (MRI, mpMRI)-based radiomics nomogram in predicting ER of small hepatocellular carcinoma (HCC) after RFA.

MATERIALS AND METHODS

A retrospective analysis was performed on 90 patients with small HCC who were treated with RFA. Patients were divided into two groups according to recurrence within 2 years: the ER group (n=38) and the non-ER group (n=52). Preoperative T1WI, T2WI, and contrast-enhanced MRI (CE-MRI) were used for radiomic analysis. Tumor segmentation was performed on the images and applied to extract 1316 radiomics features. The most predictive features were selected using analysis of variance + Mann-Whitney, Spearman's rank correlation test, random forest (importance), and least absolute shrinkage and selection operator analysis. Radiomics models based on each sequence or combined sequences were established using logistic regression analysis. A predictive nomogram was constructed based on the radiomics score (rad-score) and clinical predictors. The predictive efficiency of the nomogram was evaluated using the area under the receiver operating characteristic curve (AUC). Decision curve analysis (DCA) was used to evaluate the clinical efficacy of the nomogram.

RESULTS

The radiomics model mpMRI, which is based on T1WI, T2WI, and CE-MRI sequences, showed the best predictive performance, with an AUC of 0.812 for the validation cohort. Combined with the clinical risk factors of albumin level, number of tumors, and rad-score of mpMRI, the AUC of the preoperative predictive nomogram in the training and validation cohorts were 0.869 and 0.812, respectively. DCA demonstrated that the combined nomogram is clinically useful.

CONCLUSIONS

The multi-parametric MRI-based radiomics nomogram has a high predictive value for ER of small HCC after RFA, which could be helpful for personalized risk stratification and further treatment decision-making for patients with small HCC.

Radiomics: a primer on high-throughput image phenotyping

Radiomics is a high-throughput approach to image phenotyping. It uses computer algorithms to extract and analyze a large number of quantitative features from radiological images. These radiomic features collectively describe unique patterns that can serve as digital fingerprints of disease. They may also capture imaging characteristics that are difficult or impossible to characterize by the human eye. The rapid development of this field is motivated by systems biology, facilitated by data analytics, and powered by artificial intelligence. Here, as part of Abdominal Radiology's special issue on Quantitative Imaging, we provide an introduction to the field of radiomics. The technique is formally introduced as an advanced application of data analytics, with illustrating examples in abdominal radiology. Artificial intelligence is then presented as the main driving force of radiomics, and common techniques are defined and briefly compared. The complete step-by-step process of radiomic phenotyping is then broken down into five key phases. Potential pitfalls of each phase are highlighted, and recommendations are provided to reduce sources of variation, non-reproducibility, and error associated with radiomics.

Clinical relevance of biomarkers in cholangiocarcinoma: critical revision and future directions

Cholangiocarcinoma (CCA) is a malignant tumour arising from the biliary system. In Europe, this tumour frequently presents as a sporadic cancer in patients without defined risk factors and is usually diagnosed at advanced stages with a consequent poor prognosis. Therefore, the identification of biomarkers represents an utmost need for patients with CCA. Numerous studies proposed a wide spectrum of biomarkers at tissue and molecular levels. With the present paper, a multidisciplinary group of experts within the European Network for the Study of Cholangiocarcinoma discusses the clinical role of tissue biomarkers and provides a selection based on their current relevance and potential applications in the framework of CCA. Recent advances are proposed by dividing biomarkers based on their potential role in diagnosis, prognosis and therapy response. Limitations of current biomarkers are also identified, together with specific promising areas (ie, artificial intelligence, patient-derived organoids, targeted therapy) where research should be focused to develop future biomarkers.

Diagnostic Value of Multislice Spiral Computed Tomography Combined with Serum AFP, TSGF, and GP73 Assay in the Diagnosis of Primary Liver Cancer

Objective

To explore the diagnostic value of multislice spiral computed tomography (MSCT) scan combined with serum alpha-fetoprotein (AFP), tumor-specific growth factor (TSGF), and Golgi protein73 (GP73) assays in the diagnosis of primary liver cancer (PLC).

Methods

Totally, 60 patients with PLC admitted to The Second Hospital of Dalian Medical University from January 2019 to January 2020 were included in group A, 60 patients with liver cirrhosis were included in group B, and 60 healthy subjects were included in group C. The serum AFP, TSGF, and GP73 levels were determined, and all participants received MSCT scanning. The diagnostic efficacy of MSCT, assays of serum AFP, TSGF, and GP73, and their combined detection was analyzed.

Results

Group A had the highest levels of AFP, TSGF, and GP73, followed by group B, and then group C. The sensitivity, specificity, positive predictive value, and negative predictive value of MSCT for PLC were 80.0%,91.7%, 82.8%, and 90.2%, respectively, while those of combined detection of MSCT plus serum AFP, TSGF, and GP73 for PLC were 100.0%, 93.3%, 88.2%, and 100.0%. The combined detection was associated with significantly a higher detection rate of PLC versus stand-alone detection.

Conclusion

MSCT plus serum AFP, TSGF, and GP73 has a higher detection rate versus stand-alone detection, which shows great potential in the diagnosis of PLC.

PET-Based Radiogenomics Supports mTOR Pathway Targeting for Hepatocellular Carcinoma

PURPOSE

This work aimed to explore in depth the genomic and molecular underpinnings of hepatocellular carcinoma (HCC) with increased 2[18F]fluoro-2-deoxy-d-glucose (FDG) uptake in PET and to identify therapeutic targets based on this imaging-genomic surrogate.

EXPERIMENTAL DESIGN

We used RNA sequencing and whole-exome sequencing data obtained from 117 patients with HCC who underwent hepatic resection with preoperative FDG-PET/CT imaging as a discovery cohort. The primary radiogenomic results were validated with transcriptomes from a second cohort of 81 patients with more advanced tumors. All patients were allocated to an FDG-avid or FDG-non-avid group according to the PET findings. We also screened potential drug candidates targeting FDG-avid HCCs in vitro and in vivo.

RESULTS

High FDG avidity conferred worse recurrence-free survival after HCC resection. Whole transcriptome analysis revealed upregulation of mTOR pathway signals in the FDG-avid tumors, together with higher abundance of associated mutations. These clinical and genomic findings were replicated in the validation set. A molecular signature of FDG-avid HCCs identified in the discovery set consistently predicted poor prognoses in the public-access datasets of two cohorts. Treatment with an mTOR inhibitor resulted in decreased FDG uptake followed by effective tumor control in both the hyperglycolytic HCC cell lines and xenograft mouse models.

CONCLUSIONS

Our PET-based radiogenomic analysis indicates that mTOR pathway genes are markedly activated and altered in HCCs with high FDG retention. This nuclear imaging biomarker may stimulate umbrella trials and tailored treatments in precision care of patients with HCC.

Deep Neural Networks and Machine Learning Radiomics Modelling for Prediction of Relapse in Mantle Cell Lymphoma

Simple Summary

Mantle cell lymphoma (MCL) is an aggressive lymphoid tumour with a poor prognosis. There exist no routine biomarkers for the early prediction of relapse. Our study compared the potential of radiomics-based machine learning and 3D deep learning models as non-invasive biomarkers to risk-stratify MCL patients, thus promoting precision imaging in clinical oncology.

Abstract

Mantle cell lymphoma (MCL) is a rare lymphoid malignancy with a poor prognosis characterised by frequent relapse and short durations of treatment response. Most patients present with aggressive disease, but there exist indolent subtypes without the need for immediate intervention. The very heterogeneous behaviour of MCL is genetically characterised by the translocation t(11;14)(q13;q32), leading to Cyclin D1 overexpression with distinct clinical and biological characteristics and outcomes. There is still an unfulfilled need for precise MCL prognostication in real-time. Machine learning and deep learning neural networks are rapidly advancing technologies with promising results in numerous fields of application. This study develops and compares the performance of deep learning (DL) algorithms and radiomics-based machine learning (ML) models to predict MCL relapse on baseline CT scans. Five classification algorithms were used, including three deep learning models (3D SEResNet50, 3D DenseNet, and an optimised 3D CNN) and two machine learning models based on K-nearest Neighbor (KNN) and Random Forest (RF). The best performing method, our optimised 3D CNN, predicted MCL relapse with a 70% accuracy, better than the 3D SEResNet50 (62%) and the 3D DenseNet (59%). The second-best performing method was the KNN-based machine learning model (64%) after principal component analysis for improved accuracy. Our optimised CNN developed by ourselves correctly predicted MCL relapse in 70% of the patients on baseline CT imaging. Once prospectively tested in clinical trials with a larger sample size, our proposed 3D deep learning model could facilitate clinical management by precision imaging in MCL.

Comparing Radiomics features of tumour and healthy liver tissue in a limited CT dataset: A machine learning study

INTRODUCTION

Liver cancer lesions on Computed Tomography (CT) withholds a great amount of data, which is not visible to the radiologists and radiographer. Radiomics features can be extracted from the lesions and used to train Machine Learning (ML) algorithms to predict between tumour and liver tissue. The purpose of this study was to investigate and classify Radiomics features extracted from liver tumours and normal liver tissue in a limited CT dataset.

METHODS

The Liver Tumour Segmentation Benchmark (LiTS) dataset consisting of 131 CT scans of the liver with segmentations of tumour tissue and healthy liver was used to extract Radiomic features. Extracted Radiomic features included size, shape, and location extracted with morphological and statistical techniques according to the International Symposium on Biomedical Imaging manual. Relevant features was selected with chi2 correlation and principal component analysis (PCA) with tumour and healthy liver tissue as outcome according to a consensus between three experienced radiologists. Logistic regression, random forest and support vector machine was used to train and validate the dataset with a 10-fold cross-validation method and the Grid Search as hyper-parameter tuning. Performance was evaluated with sensitivity, specificity and accuracy.

RESULTS

The performance of the ML algorithms achieved sensitivities, specificities and accuracy ranging from 96.30% (95% CI: 81.03%-99.91%) to 100.00% (95% CI: 86.77%-100.00%), 91.30% (95% CI: 71.96%-98.93%) to 100.00% (95% CI: 83.89%-100.00%)and 94.00% (95% CI: 83.45%-98.75%) to 100.00% (95% CI: 92.45%-100.00%), respectively.

CONCLUSION

ML algorithms classifies Radiomics features extracted from healthy liver and tumour tissue with perfect accuracy. The Radiomics signature allows for a prognostic biomarker for hepatic tumour screening on liver CT.

IMPLICATIONS FOR PRACTICE

Differentiation between tumour and liver tissue with Radiomics ML algorithms have the potential to increase the diagnostic accuracy, assist in the decision-making of supplementary multiphasic enhanced medical imaging, as well as for developing novel prognostic biomarkers for liver cancer patients.

MRE-based NASH score for diagnosis of nonalcoholic steatohepatitis in patients with nonalcoholic fatty liver disease

BACKGROUND AND AIMS

As the prevalence of nonalcoholic fatty liver disease (NAFLD) is approximately 30% in the general population, it is important to develop a non-invasive biomarker for the diagnosis of nonalcoholic steatohepatitis (NASH). This prospective cross-sectional study aimed to develop a scoring system for NASH diagnosis through multiparametric magnetic resonance (MR) and clinical indicators.

METHODS

Medical history, laboratory tests, and MR parameters of patients with NAFLD were assessed. A scoring system was developed using a logistic regression model. In total, 127 patients (58 with nonalcoholic fatty liver [NAFL] and 69 with NASH) were enrolled. After evaluating 23 clinical characteristics of the patients (4 categorical and 19 numeric variables) for the NASH diagnostic model, an equation for MR elastography (MRE)-based NASH score was obtained using 3 demographic factors, 2 laboratory variables, and MRE.

RESULTS

The MRE-based NASH score showed a satisfactory accuracy for NASH diagnosis (c-statistics, 0.841; 95% CI 0.772-0.910). At a cut-off MRE-based NASH score of 0.68 for NASH diagnosis, its sensitivity was 0.68 and specificity was 0.91. When an MRE-based NASH score of 0.37 was used as a cut-off for NASH exclusion, the sensitivity was 0.91 and specificity was 0.55. Overall, 35% (44/127) of patients were in the gray zone (between 0.37 and 0.68). Internal validation via bootstrapping also indicated the satisfactory accuracy of NASH diagnosis (optimism-corrected statistics, 0.811).

CONCLUSION

MRE-based NASH score is a useful and accurate non-invasive biomarker for diagnosis of NASH in patients with NAFLD.

Associating Preoperative MRI Features and Gene Expression Signatures of Early-stage Hepatocellular Carcinoma Patients using Machine Learning

BACKGROUND AND AIMS

The relationship between quantitative magnetic resonance imaging (MRI) imaging features and gene-expression signatures associated with the recurrence of hepatocellular carcinoma (HCC) is not well studied.

METHODS

In this study, we generated multivariable regression models to explore the correlation between the preoperative MRI features and Golgi membrane protein 1 (GOLM1), SET domain containing 7 (SETD7), and Rho family GTPase 1 (RND1) gene expression levels in a cohort study including 92 early-stage HCC patients. A total of 307 imaging features of tumor texture and shape were computed from T2-weighted MRI. The key MRI features were identified by performing a multi-step feature selection procedure including the correlation analysis and the application of RELIEFF algorithm. Afterward, regression models were generated using kernel-based support vector machines with 5-fold cross-validation.

RESULTS

The features computed from higher specificity MRI better described GOLM1 and RND1 gene-expression levels, while imaging features computed from lower specificity MRI data were more descriptive for the SETD7 gene. The GOLM1 regression model generated with three features demonstrated a moderate positive correlation (p<0.001), and the RND1 model developed with five variables was positively associated (p<0.001) with gene expression levels. Moreover, RND1 regression model integrating four features was moderately correlated with expressed RND1 levels (p<0.001).

CONCLUSIONS

The results demonstrated that MRI radiomics features could help quantify GOLM1, SETD7, and RND1 expression levels noninvasively and predict the recurrence risk for early-stage HCC patients.

Longitudinal CT Imaging to Explore the Predictive Power of 3D Radiomic Tumour Heterogeneity in Precise Imaging of Mantle Cell Lymphoma (MCL)

The study's primary aim is to evaluate the predictive performance of CT-derived 3D radiomics for MCL risk stratification. The secondary objective is to search for radiomic features associated with sustained remission. Included were 70 patients: 31 MCL patients and 39 control subjects with normal axillary lymph nodes followed over five years. Radiomic analysis of all targets (n = 745) was performed and features selected using the Mann Whitney U test; the discriminative power of identifying "high-risk MCL" was evaluated by receiver operating characteristics (ROC). The four radiomic features, "Uniformity", "Entropy", "Skewness" and "Difference Entropy" showed predictive significance for relapse (p < 0.05)-in contrast to the routine size measurements, which showed no relevant difference. The best prognostication for relapse achieved the feature "Uniformity" (AUC-ROC-curve 0.87; optimal cut-off ≤0.0159 to predict relapse with 87% sensitivity, 65% specificity, 69% accuracy). Several radiomic features, including the parameter "Short Axis," were associated with sustained remission. CT-derived 3D radiomics improves the predictive estimation of MCL patients; in combination with the ability to identify potential radiomic features that are characteristic for sustained remission, it may assist physicians in the clinical management of MCL.

Pharmacological Inhibition of Sonic Hedgehog Signaling Suppresses Tumor Development in a Murine Model of Intrahepatic Cholangiocarcinoma

Cholangiocarcinoma (CCC) is the second most primary liver cancer with an aggressive biological behavior, and its incidence increases steadily. An aberrant up-regulation of the sonic hedgehog signaling pathway has been reported in a variety of hepatic diseases including hepatic inflammation, fibrosis, as well as cancer. In this study, we determined the effect of a sonic hedgehog inhibitor, vismodegib, on the development of CCC. Through database analyses, we found sonic hedgehog signaling was up-regulated in human CCC, based on overexpression of its target genes, GLI1 and GLI2. Further, human CCC cells were highly sensitive to the treatment with vismodegib in vitro. Based on the data, we investigated the in vivo anti-cancer efficacy of vismodegib in CCC employing a murine model of CCC developed by hydrodynamic tail vein injection method. In the murine model, CCC induced by constitutively active forms of TAZ and PI3K exhibited up-regulated sonic hedgehog signaling. Treatment of vismodegib significantly suppressed tumor development in the murine CCC model, based on comparison of gross morphologies and liver weight/body weight. It is expected that pharmacological inhibition of sonic hedgehog signaling would be an effective molecular target therapy for CCC.

A novel prognostic nomogram for hepatocellular carcinoma after thermal ablation

It remains impossible to accurately assess the prognosis after thermal ablation in patients with hepatocellular carcinoma (HCC). Our aim was to build a nomogram to predict the survival rate of HCC patients after thermal ablation. We developed and validated a nomogram using data of 959 HCC patients after thermal ablation from two centers. Harrell's concordance index (C-index), calibration plot and Decision curve analysis (DCA) were used to measure the performance of the nomogram, and we compared it with the Barcelona Clinic Liver Cancer (BCLC) staging system and a previous nomogram. Six variables including age, serum albumin, operation method, risk area, tumor number and early recurrence were selected to construct the nomogram. In the training cohort, internal validation cohort, and external validation cohort, the nomogram all had a higher C-index to predict survival rate than both the BCLC staging system and the previous nomogram (0.736, 0.558 and 0.698, respectively; 0.763, 0.621 and 0.740, respectively; and 0.825, 0.551 and 0.737, respectively). Calibration plots showed a high degree of consistency between prediction and actual observation. Decision curve analysis (DCA) presented that compared with BCLC system and the previous nomogram, our nomogram had the highest net benefit. In all three cohorts, the nomogram could accurately divide patients into three subgroups according to predicted survival risk. A nomogram was developed and validated to predict survival of HCC patients who underwent thermal ablation, which is helpful for prognostic prediction and individual surveillance in clinical practice.

A Clinical-Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Gallbladder Cancer

Objectives

The aim of the current study was to develop and validate a nomogram based on CT radiomics features and clinical variables for predicting lymph node metastasis (LNM) in gallbladder cancer (GBC).

Methods

A total of 353 GBC patients from two hospitals were enrolled in this study. A Radscore was developed using least absolute shrinkage and selection operator (LASSO) logistic model based on the radiomics features extracted from the portal venous-phase computed tomography (CT). Four prediction models were constructed based on the training cohort and were validated using internal and external validation cohorts. The most effective model was then selected to build a nomogram.

Results

The clinical-radiomics nomogram, which comprised Radscore and three clinical variables, showed the best diagnostic efficiency in the training cohort (AUC = 0.851), internal validation cohort (AUC = 0.819), and external validation cohort (AUC = 0.824). Calibration curves showed good discrimination ability of the nomogram using the validation cohorts. Decision curve analysis (DCA) showed that the nomogram had a high clinical utility.

Conclusion

The findings showed that the clinical-radiomics nomogram based on radiomics features and clinical parameters is a promising tool for preoperative prediction of LN status in patients with GBC.

Evaluation of Angiogenesis and Pathological Classification of Extrahepatic Cholangiocarcinoma by Dynamic MR Imaging for E-Healthcare

For staging cholangiocarcinoma and determining respectability, MR is an accurate noninvasive method which provides size of tumor and vascular patency information. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a noninvasive inspection method for evaluating the vascular structure and functional characteristics of tumor tissue. However, some limitations should be noted about the technology. At present, the technology cannot be used alone, which is just an assisted method during the conventional MRI examination. 50 ECC patients, admitted to Indira Gandhi Medical College and Hospital between 2016 and 2019, were selected as research subjects. They were classified pathologically according to the Steiner classification system. After image processing, regions of interest (ROIs) were selected from the image to measure the rate constant (Kep), extravascular space volume fraction (Ve), and tissue volume transfer constant (Ktrans). There were 15 cases with highly differentiated carcinoma, 23 cases with moderately differentiated carcinoma, and 12 cases with lowly differentiated carcinoma. Non-VEGF expression was noted in 21 cases, with low expression noted in 15 cases, moderate expression noted in 14 cases, and no high expression case noted. The relevant parameters in the dynamic MRI image can quantitatively reflect the angiogenesis and pathological classification of ECC, which is suggested in the clinical treatment of ECC. The Ktrans, Kep, and Ve values of the ECC patients were all not associated with the pathological classification, with no significant difference (P < 0.05). Besides, due to the fact that the patient cannot completely hold his breath, the air leak reduces the image quality.

Decoding Genes: Current Update on Radiogenomics of Select Abdominal Malignancies

Technologic advances in chromosomal analysis and DNA sequencing have enabled genome-wide analysis of cancer cells, yielding considerable data on the genetic basis of malignancies. Evolving knowledge of tumor genetics and oncologic pathways has led to a better understanding of histopathologic features, tumor classification, tumor biologic characteristics, and imaging findings and discovery of targeted therapeutic agents. Radiogenomics is a rapidly evolving field of imaging research aimed at correlating imaging features with gene mutations and gene expression patterns, and it may provide surrogate imaging biomarkers that may supplant genetic tests and be used to predict treatment response and prognosis and guide personalized treatment options. Multidetector CT, multiparametric MRI, and PET with use of multiple radiotracers are some of the imaging techniques commonly used to assess radiogenomic associations. Select abdominal malignancies demonstrate characteristic imaging features that correspond to gene mutations. Recent advances have enabled us to understand the genetics of steatotic and nonsteatotic hepatocellular adenomas, a plethora of morphologic-molecular subtypes of hepatic malignancies, a variety of clear cell and non-clear cell renal cell carcinomas, a myriad of hereditary and sporadic exocrine and neuroendocrine tumors of the pancreas, and the development of targeted therapeutic agents for gastrointestinal stromal tumors based on characteristic KIT gene mutations. Mutations associated with aggressive phenotypes of these malignancies can sometimes be predicted on the basis of their imaging characteristics. Radiologists should be familiar with the genetics and pathogenesis of common cancers that have associated imaging biomarkers, which can help them be integral members of the cancer management team and guide clinicians and pathologists. Online supplemental material is available for this article. ^©RSNA, 2020 See discussion on this article by Luna (pp 1627-1630).

CT-Based Radiomics Nomogram: A Potential Tool for Differentiating Hepatocellular Adenoma From Hepatocellular Carcinoma in the Noncirrhotic Liver

RATIONALE AND OBJECTIVES

To evaluate the value of a radiomics nomogram for preoperative differentiating hepatocellular adenoma (HCA) from hepatocellular carcinoma (HCC) in the noncirrhotic liver.

MATERIALS AND METHODS

One hundred and thirty-one patients with HCA (n = 46) and HCC (n = 85) were divided into a training set (n = 93) and a test set (n = 38). Clinical data and CT findings were analyzed. Radiomics features were extracted from the triphasic contrast CT images. A radiomics signature was constructed with the least absolute shrinkage and selection operator algorithm and a radiomics score was calculated. Combined with the radiomics score and independent clinical factors, a radiomics nomogram was developed by multivariate logistic regression analysis. The performance of the radiomics nomogram was assessed by calibration, discrimination and clinical usefulness.

RESULTS

Gender, age, and enhancement pattern were the independent clinical factors. Three thousand seven hundred and sixty-eight features were extracted and reduced to 7 features as the optimal discriminators to build the radiomics signature. The radiomics nomogram (area under the curve [AUC], 0.96; 95% confidence interval [CI], 0.93-0.99) and the clinical factors model (AUC, 0.93; 95%CI, 0.88-0.99) showed better discrimination capability (p = 0.001 and 0.047) than the radiomics signature (AUC, 0.83; 95%CI, 0.74-0.92) in the training set. In the test set, the radiomics nomogram (AUC, 0.94; 95%CI, 0.87-1.00) performed better (p = 0.013) than the radiomics signature (AUC, 0.75; 95%CI, 0.59-0.91). Decision curve analysis showed the radiomics nomogram outperformed the clinical factors model and the radiomics signature in terms of clinical usefulness.

CONCLUSION

The CT-based radiomics nomogram has the potential to accurately differentiate HCA from HCC in the noncirrhotic liver.

Challenges and opportunities for artificial intelligence in oncological imaging

Imaging plays a key role in oncology, including the diagnosis and detection of cancer, determining clinical management, assessing treatment response, and complications of treatment or disease. The current use of clinical oncology is predominantly qualitative in nature with some relatively crude size-based measurements of tumours for assessment of disease progression or treatment response; however, it is increasingly understood that there may be significantly more information about oncological disease that can be obtained from imaging that is not currently utilized. Artificial intelligence (AI) has the potential to harness quantitative techniques to improve oncological imaging. These may include improving the efficiency or accuracy of traditional roles of imaging such as diagnosis or detection. These may also include new roles for imaging such as risk-stratifying patients for different types of therapy or determining biological tumour subtypes. This review article outlines several major areas in oncological imaging where there may be opportunities for AI technology. These include (1) screening and detection of cancer, (2) diagnosis and risk stratification, (3) tumour segmentation, (4) precision oncology, and (5) predicting prognosis and assessing treatment response. This review will also address some of the potential barriers to AI research in oncological imaging.

An imageomics and multi-network based deep learning model for risk assessment of liver transplantation for hepatocellular cancer

INTRODUCTION

Liver transplantation (LT) is an effective treatment for hepatocellular carcinoma (HCC), the most common type of primary liver cancer. Patients with small HCC (<5 cm) are given priority over others for transplantation due to clinical allocation policies based on tumor size. Attempting to shift from the prevalent paradigm that successful transplantation and longer disease-free survival can only be achieved in patients with small HCC to expanding the transplantation option to patients with HCC of the highest tumor burden (>5 cm), we developed a convergent artificial intelligence (AI) model that combines transient clinical data with quantitative histologic and radiomic features for more objective risk assessment of liver transplantation for HCC patients.

METHODS

Patients who received a LT for HCC between 2008-2019 were eligible for inclusion in the analysis. All patients with post-LT recurrence were included, and those without recurrence were randomly selected for inclusion in the deep learning model. Pre- and post-transplant magnetic resonance imaging (MRI) scans and reports were compressed using CapsNet networks and natural language processing, respectively, as input for a multiple feature radial basis function network. We applied a histological image analysis algorithm to detect pathologic areas of interest from explant tissue of patients who recurred. The multilayer perceptron was designed as a feed-forward, supervised neural network topology, with the final assessment of recurrence risk. We used area under the curve (AUC) and F-1 score to assess the predictability of different network combinations.

RESULTS

A total of 109 patients were included (87 in the training group, 22 in the testing group), of which 20 were positive for cancer recurrence. Seven models (AUC; F-1 score) were generated, including clinical features only (0.55; 0.52), magnetic resonance imaging (MRI) only (0.64; 0.61), pathological images only (0.64; 0.61), MRI plus pathology (0.68; 0.65), MRI plus clinical (0.78, 0.75), pathology plus clinical (0.77; 0.73), and a combination of clinical, MRI, and pathology features (0.87; 0.84). The final combined model showed 80 % recall and 89 % precision. The total accuracy of the implemented model was 82 %.

CONCLUSION

We validated that the deep learning model combining clinical features and multi-scale histopathologic and radiomic image features can be used to discover risk factors for recurrence beyond tumor size and biomarker analysis. Such a predictive, convergent AI model has the potential to alter the LT allocation system for HCC patients and expand the transplantation treatment option to patients with HCC of the highest tumor burden.

Role of artificial intelligence in hepatobiliary and pancreatic surgery

Over the past decade, enhanced preoperative imaging and visualization, improved delineation of the complex anatomical structures of the liver and pancreas, and intra-operative technological advances have helped deliver the liver and pancreatic surgery with increased safety and better postoperative outcomes. Artificial intelligence (AI) has a major role to play in 3D visualization, virtual simulation, augmented reality that helps in the training of surgeons and the future delivery of conventional, laparoscopic, and robotic hepatobiliary and pancreatic (HPB) surgery; artificial neural networks and machine learning has the potential to revolutionize individualized patient care during the preoperative imaging, and postoperative surveillance. In this paper, we reviewed the existing evidence and outlined the potential for applying AI in the perioperative care of patients undergoing HPB surgery.

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.

Current status and quality of radiomics studies in lymphoma: a systematic review

OBJECTIVES

To perform a systematic review regarding the developments in the field of radiomics in lymphoma. To evaluate the quality of included articles by the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), the phases classification criteria for image mining studies, and the radiomics quality scoring (RQS) tool.

METHODS

We searched for eligible articles in the MEDLINE/PubMed and EMBASE databases using the terms "radiomics", "texture" and "lymphoma". The included studies were divided into two categories: diagnosis-, therapy response- and outcome-related studies. The diagnosis-related studies were evaluated using the QUADAS-2; all studies were evaluated using the phases classification criteria for image mining studies and the RQS tool by two reviewers.

RESULTS

Forty-five studies were included; thirteen papers (28.9%) focused on the differential diagnosis of primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM). Thirty-two (71.1%) studies were classified as discovery science according to the phase classification criteria for image mining studies. The mean RQS score of all studies was 14.2% (ranging from 0.0 to 40.3%), and 23 studies (51.1%) were given a score of < 10%.

CONCLUSION

The radiomics features could serve as diagnostic and prognostic indicators in lymphoma. However, the current conclusions should be interpreted with caution due to the suboptimal quality of the studies. In order to introduce radiomics into lymphoma clinical settings, the lesion segmentation and selection, the influence of the pathological pattern and the extraction of multiple modalities and multiple time points features need to be further studied.

KEY POINTS

• The radiomics approach may provide useful information for diagnosis, prediction of the therapy response, and outcome of lymphoma. • The quality of published radiomics studies in lymphoma has been suboptimal to date. • More studies are needed to examine lesion selection and segmentation, the influence of pathological patterns, and the extraction of multiple modalities and multiple time point features.

Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma: Initial Application of a Radiomic Algorithm Based on Grayscale Ultrasound Images

Objectives: To establish a radiomic algorithm based on grayscale ultrasound images and to make preoperative predictions of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. Methods: In this retrospective study, 322 cases of histopathologically confirmed HCC lesions were included. The classifications based on preoperative grayscale ultrasound images were performed in two stages: (1) classifier #1, MVI-negative and MVI-positive cases; (2) classifier #2, MVI-positive cases were further classified as M1 or M2 cases. The gross-tumoral region (GTR) and peri-tumoral region (PTR) signatures were combined to generate gross- and peri-tumoral region (GPTR) radiomic signatures. The optimal radiomic signatures were further incorporated with vital clinical information. Multivariable logistic regression was used to build radiomic models. Results: Finally, 1,595 radiomic features were extracted from each HCC lesion. At the classifier #1 stage, the radiomic signatures based on features of GTR, PTR, and GPTR showed area under the curve (AUC) values of 0.708 (95% CI, 0.603-0.812), 0.710 (95% CI, 0.609-0.811), and 0.726 (95% CI, 0.625-0.827), respectively. Upon incorporation of vital clinical information, the AUC of the GPTR radiomic algorithm was 0.744 (95% CI, 0.646-0.841). At the classifier #2 stage, the AUC of the GTR radiomic signature was 0.806 (95% CI, 0.667-0.944). Conclusions: Our radiomic algorithm based on grayscale ultrasound images has potential value to facilitate preoperative prediction of MVI in HCC patients. The GTR radiomic signature may be helpful for further discriminating between M1 and M2 levels among MVI-positive patients.

A CT-based radiomics nomogram for differentiation of focal nodular hyperplasia from hepatocellular carcinoma in the non-cirrhotic liver

Background

The purpose of this study was to develop and validate a radiomics nomogram for preoperative differentiating focal nodular hyperplasia (FNH) from hepatocellular carcinoma (HCC) in the non-cirrhotic liver.

Methods

A total of 156 patients with FNH (n = 55) and HCC (n = 101) were divided into a training set (n = 119) and a validation set (n = 37). Radiomics features were extracted from triphasic contrast CT images. A radiomics signature was constructed with the least absolute shrinkage and selection operator algorithm, and a radiomics score (Rad-score) was calculated. Clinical data and CT findings were assessed to build a clinical factors model. Combined with the Rad-score and independent clinical factors, a radiomics nomogram was constructed by multivariate logistic regression analysis. Nomogram performance was assessed with respect to discrimination and clinical usefulness.

Results

Four thousand two hundred twenty-seven features were extracted and reduced to 10 features as the most important discriminators to build the radiomics signature. The radiomics signature showed good discrimination in the training set (AUC [area under the curve], 0.964; 95% confidence interval [CI], 0.934–0.995) and the validation set (AUC, 0.865; 95% CI, 0.725–1.000). Age, Hepatitis B virus infection, and enhancement pattern were the independent clinical factors. The radiomics nomogram, which incorporated the Rad-score and clinical factors, showed good discrimination in the training set (AUC, 0.979; 95% CI, 0.959–0.998) and the validation set (AUC, 0.917; 95% CI, 0.800–1.000), and showed better discrimination capability (P < 0.001) compared with the clinical factors model (AUC, 0.799; 95% CI, 0.719–0.879) in the training set. Decision curve analysis showed the nomogram outperformed the clinical factors model in terms of clinical usefulness.

Conclusions

The CT-based radiomics nomogram, a noninvasive preoperative prediction tool that incorporates the Rad-score and clinical factors, shows favorable predictive efficacy for differentiating FNH from HCC in the non-cirrhotic liver, which might facilitate clinical decision-making process.

Determination of optimized set of b-values for Apparent Diffusion Coefficient mapping in liver Diffusion-Weighted MRI

In this manuscript we derive the Cramér-Rao Lower Bound (CRLB) of the monoexponential diffusion-weighted signal model under a realistic noise assumption, and propose a formulation to obtain optimized sets of b-values that maximize the noise performance of the Apparent Diffusion Coefficient (ADC) maps given a target ADC and a signal-to-noise ratio. Therefore, for various sets of parameters (S₀ and ADC), signal-to-noise ratios (SNR) and noise distribution, we computed optimized sets of b-values using CRLB-based analysis in two different ways: (i) through a greedy algorithm where b-values from a pool of candidates were added iteratively to the set, and (ii) through a two b-value search algorithm were all two b-value combinations of the pool of candidates were tested. Further, optimized sets of b-values were computed from synthetic data, phantoms, and in-vivo liver diffusion-weighted imaging (DWI) experiments to validate the CRLB-based analysis. The optimized sets of b-values obtained through the proposed CRLB-based analysis showed good agreement with the optimized sets obtained experimentally from synthetic, phantoms, and in-vivo liver data. The variance of the ADC maps decreased when employing the optimized set of b-values compared to various sets of b-values proposed in the literature for in-vivo liver DWI, although differences of notable magnitude between noise models and optimization strategies were not found. In addition, the higher b-values decreased for lower SNR under the Rician noise distribution. Optimization of the set b-values is critical to maximize the noise performance (i.e., maximize the precision and minimize the variance) of the estimated ADC maps in diffusion-weighted MRI. Hence, the proposed approach may help to optimize and standardize liver diffusion-weighted MRI acquisitions by computing optimized set of b-values for a given set of parameters.

Precise hepatectomy in the intelligent digital era

In the past 20 years, the concept of surgery has undergone profound changes. Surgical practice has shifted from emphasizing the complete elimination of lesions to achieving optimal rehabilitation in patients. Collaborative optimization of surgery consists of three core elements, removal of lesions, organ protection and injury close monitoring, and controlled surgical intervention. As a result, the traditional surgical paradigm has quietly transformed into a modern precision surgical paradigm. In this review, we summarized the latest breakthroughs and applications of precision medicine in liver surgery. In addition, we also outlined the progresses that have been made in precision liver surgery, the opportunities and challenges that may encountered in the future.

A Comparison of the Efficiency of Using a Deep CNN Approach with Other Common Regression Methods for the Prediction of EGFR Expression in Glioblastoma Patients

To estimate epithermal growth factor receptor (EGFR) expression level in glioblastoma (GBM) patients using radiogenomic analysis of magnetic resonance images (MRI). A comparative study using a deep convolutional neural network (CNN)-based regression, deep neural network, least absolute shrinkage and selection operator (LASSO) regression, elastic net regression, and linear regression with no regularization was carried out to estimate EGFR expression of 166 GBM patients. Except for the deep CNN case, overfitting was prevented by using feature selection, and loss values for each method were compared. The loss values in the training phase for deep CNN, deep neural network, Elastic net, LASSO, and the linear regression with no regularization were 2.90, 8.69, 7.13, 14.63, and 21.76, respectively, while in the test phase, the loss values were 5.94, 10.28, 13.61, 17.32, and 24.19 respectively. These results illustrate that the efficiency of the deep CNN approach is better than that of the other methods, including Lasso regression, which is a regression method known for its advantage in high-dimension cases. A comparison between deep CNN, deep neural network, and three other common regression methods was carried out, and the efficiency of the CNN deep learning approach, in comparison with other regression models, was demonstrated.

The Many Facets of Tumor Heterogeneity: Is Metabolism Lagging Behind?

Tumor functional heterogeneity has been recognized for decades, and technological advancements are fueling renewed interest in uncovering the cell-intrinsic and extrinsic factors that influence tumor development and therapeutic response. Intratumoral heterogeneity is now arguably one of the most-studied topics in tumor biology, leading to the discovery of new paradigms and reinterpretation of old ones, as we aim to understand the profound implications that genomic, epigenomic, and functional heterogeneity hold with regard to clinical outcomes. In spite of our improved understanding of the biological complexity of cancer, characterization of tumor metabolic heterogeneity has lagged behind, lost in a century-old controversy debating whether glycolysis or mitochondrial respiration is more influential. But is tumor metabolism really so simple? Here, we review historical and current views of intratumoral heterogeneity, with an emphasis on summarizing the emerging data that begin to illuminate just how vast the spectrum of metabolic strategies a tumor can employ may be, and what this means for how we might interpret other tumor characteristics, such as mutational landscape, contribution of microenvironmental influences, and treatment resistance.

Radiomics in hepatocellular carcinoma: a quantitative review

Radiomics is an emerging field which extracts quantitative radiology data from medical images and explores their correlation with clinical outcomes in a non-invasive manner. This review aims to assess whether radiomics is a useful and reproducible method for clinical management of hepatocellular carcinoma (HCC) by reviewing the strengths and weaknesses of current radiomics literature pertaining specifically to HCC. From an initial set of 48 articles recovered through database searches, 23 articles were retained to be included in this review after full screening. Among these 23 studies, 7 used a radiomics approach in magnetic resonance imaging (MRI). Only two studies applied radiomics to positron emission tomography-computed tomography (PET-CT). In the remaining 14 articles, a radiomics analysis was performed on computed tomography (CT). Eight studies dealt with the relationship between biological signatures and imaging findings, and can be classified as radiogenomic studies. For each study included in our review, we computed a Radiomics Quality Score (RQS) as proposed by Lambin et al. We found that the RQS (mean ± standard deviation) was 8.35 ± 5.38 (out of a possible maximum value of 36). Although these scores are fairly low, and radiomics has not yet reached clinical utility in HCC, it is important to underscore the fact that these early studies pave the way for the radiomics field with a focus on HCC. Radiomics is still a very young field, and is far from being mature, but it remains a very promising technology for the future for developing adequate personalized treatment as a non-invasive approach, for complementing or replacing tumor biopsies, as well as for developing novel prognostic biomarkers in HCC patients.

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

Objectives

To explore the feasibility of diagnosing microvascular invasion (MVI) with radiomics, to compare the diagnostic performance of different models established by each method, and to determine the best diagnostic model based on radiomics.

Methods

A retrospective analysis was conducted with 206 cases of hepatocellular carcinoma (HCC) confirmed through surgery and pathology in our hospital from June 2015 to September 2018. Among the samples, 88 were MVI-positive, and 118 were MVI-negative. The radiomics analysis process included tumor segmentation, feature extraction, data preprocessing, dimensionality reduction, modeling and model evaluation.

Results

A total of 1044 sets of texture feature parameters were extracted, and 21 methods were used for the radiomics analysis. All research methods could be used to diagnose MVI. Of all the methods, the LASSO+GBDT method had the highest accuracy, the LASSO+RF method had the highest sensitivity, the LASSO+BPNet method had the highest specificity, and the LASSO+GBDT method had the highest AUC. Through Z-tests of the AUCs, LASSO+GBDT, LASSO+K-NN, LASSO+RF, PCA + DT, and PCA + RF had Z-values greater than 1.96 (p<0.05). The DCA results showed that the LASSO + GBDT method was better than the other methods when the threshold probability was greater than 0.22.

Conclusions

Radiomics can be used for the preoperative, noninvasive diagnosis of MVI, but different dimensionality reduction and modeling methods will affect the diagnostic performance of the final model. The model established with the LASSO+GBDT method had the optimal diagnostic performance and the greatest diagnostic value for MVI.

Development and validation of a prognostic model for patients with hepatocellular carcinoma undergoing radiofrequency ablation

Background

There are large variations in prognosis among hepatocellular carcinoma (HCC) patients undergoing radiofrequency ablation (RFA). However, current staging or scoring systems hardly discriminate the outcome of HCC patients treated with RFA.

Methods

A total of 757 treatment‐naïve HCC patients undergoing RFA (derivation cohort) were analyzed to establish a nomogram for disease‐free survival (DFS) based on Cox proportional hazard regression model. Accuracy of the nomogram was assessed and compared with conventional staging or scoring systems. Furthermore, external validation was performed in an independent cohort including 208 patients (validation cohort).

Results

Tumor size, tumor number, alpha‐fetoprotein, prothrombin induced by vitamin K absence‐II, lymphocyte count, albumin, and presence of ascites were adopted to construct the prognostic nomogram from the derivation cohort. Calibration curves to predict probability of DFS at 3 and 5 years after RFA showed good agreements between the nomogram and actual observations. The concordance index of the present nomogram was 0.759 (95% confidence interval 0.728‐0.790), which was superior to those of conventional staging or scoring systems (range 0.505‐0.683, all P < .001). These results were also reproduced in the validation cohort.

Conclusion

Our simple‐to‐use nomogram optimized for treatment‐naïve HCC patients undergoing RFA provided better prognostic performance than conventional staging or scoring systems.

Liver tissue segmentation in multiphase CT scans using cascaded convolutional neural networks

PURPOSE

We address the automatic segmentation of healthy and cancerous liver tissues (parenchyma, active and necrotic parts of hepatocellular carcinoma (HCC) tumor) on multiphase CT images using a deep learning approach.

METHODS

We devise a cascaded convolutional neural network based on the U-Net architecture. Two strategies for dealing with multiphase information are compared: Single-phase images are concatenated in a multi-dimensional features map on the input layer, or output maps are computed independently for each phase before being merged to produce the final segmentation. Each network of the cascade is specialized in the segmentation of a specific tissue. The performances of these networks taken separately and of the cascaded architecture are assessed on both single-phase and on multiphase images.

RESULTS

In terms of Dice coefficients, the proposed method is on par with a state-of-the-art method designed for automatic MR image segmentation and outperforms previously used technique for interactive CT image segmentation. We validate the hypothesis that several cascaded specialized networks have a higher prediction accuracy than a single network addressing all tasks simultaneously. Although the portal venous phase alone seems to provide sufficient contrast for discriminating tumors from healthy parenchyma, the multiphase information brings significant improvement for the segmentation of cancerous tissues (active versus necrotic part).

CONCLUSION

The proposed cascaded multiphase architecture showed promising performances for the automatic segmentation of liver tissues, allowing to reliably estimate the necrosis rate, a valuable imaging biomarker of the clinical outcome.

Reliability of Radiomic Features Across Multiple Abdominal CT Image Acquisition Settings: A Pilot Study Using ACR CT Phantom

We studied the reliability of radiomic features on abdominal computed tomography (CT) images reconstructed with multiple CT image acquisition settings using the ACR (American College of Radiology) CT Phantom. Twenty-four sets of CT images of the ACR CT phantom were attained from a GE Discovery 750HD scanner using 24 different image acquisition settings, combinations of 4 tube currents (25, 50, 100, 200 Effective mAs), 3 slice thicknesses (1.25, 2.5, 5 mm), and 2 convolution kernels (STANDARD and SOFT). Polyethylene (-95 HU) and acrylic (120 HU) of the phantom model were selected for calculating real feature value; a noise-free, computer-generated phantom image series that reproduced the 2 objects and the background was used for calculating reference feature value. Feature reliability was defined as the degree of predicting reference feature value from real feature value. Radiomic features mean, std, skewness, kurtosis, gray-level co-occurrence matrix (GLCM)-energy, GLCM-contrast, GLCM-correlation, GLCM-homogeneity were investigated. The value of R2 ≥ 0.85 was considered to be of high reliability. The reliability of mean and std were high across all image acquisition settings. At 200 Effective mAs, all features except GLCM-homogeneity showed high reliability, whereas at 25 Effective mAs, most features (except mean and std) showed low reliability. From high to low, reliability was ranked in the following order: mean, std, skewness, kurtosis, GLCM-energy, correlation, contrast and homogeneity. CT image acquisition settings affected the reliability of radiomic features. High reliable features were attained from images reconstructed at high tube current and thick slice thickness.