Radiomics analysis of contrast-enhanced CT for staging liver fibrosis: an update for image biomarker

Imaging at the nexus: how state of the art imaging techniques can enhance our understanding of cancer and fibrosis

Both cancer and fibrosis are diseases involving dysregulation of cell signaling pathways resulting in an altered cellular microenvironment which ultimately leads to progression of the condition. The two disease entities share common molecular pathophysiology and recent research has illuminated the how each promotes the other. Multiple imaging techniques have been developed to aid in the early and accurate diagnosis of each disease, and given the commonalities between the pathophysiology of the conditions, advances in imaging one disease have opened new avenues to study the other. Here, we detail the most up-to-date advances in imaging techniques for each disease and how they have crossed over to improve detection and monitoring of the other. We explore techniques in positron emission tomography (PET), magnetic resonance imaging (MRI), second generation harmonic Imaging (SGHI), ultrasound (US), radiomics, and artificial intelligence (AI). A new diagnostic imaging tool in PET/computed tomography (CT) is the use of radiolabeled fibroblast activation protein inhibitor (FAPI). SGHI uses high-frequency sound waves to penetrate deeper into the tissue, providing a more detailed view of the tumor microenvironment. Artificial intelligence with the aid of advanced deep learning (DL) algorithms has been highly effective in training computer systems to diagnose and classify neoplastic lesions in multiple organs. Ultimately, advancing imaging techniques in cancer and fibrosis can lead to significantly more timely and accurate diagnoses of both diseases resulting in better patient outcomes.

Role of radiomics in staging liver fibrosis: a meta-analysis

BACKGROUND

Fibrosis has important pathoetiological and prognostic roles in chronic liver disease. This study evaluates the role of radiomics in staging liver fibrosis.

METHOD

After literature search in electronic databases (Embase, Ovid, Science Direct, Springer, and Web of Science), studies were selected by following precise eligibility criteria. The quality of included studies was assessed, and meta-analyses were performed to achieve pooled estimates of area under receiver-operator curve (AUROC), accuracy, sensitivity, and specificity of radiomics in staging liver fibrosis compared to histopathology.

RESULTS

Fifteen studies (3718 patients; age 47 years [95% confidence interval (CI): 42, 53]; 69% [95% CI: 65, 73] males) were included. AUROC values of radiomics for detecting significant fibrosis (F2-4), advanced fibrosis (F3-4), and cirrhosis (F4) were 0.91 [95%CI: 0.89, 0.94], 0.92 [95%CI: 0.90, 0.95], and 0.94 [95%CI: 0.93, 0.96] in training cohorts and 0.89 [95%CI: 0.83, 0.91], 0.89 [95%CI: 0.83, 0.94], and 0.93 [95%CI: 0.91, 0.95] in validation cohorts, respectively. For diagnosing significant fibrosis, advanced fibrosis, and cirrhosis the sensitivity of radiomics was 84.0% [95%CI: 76.1, 91.9], 86.9% [95%CI: 76.8, 97.0], and 92.7% [95%CI: 89.7, 95.7] in training cohorts, and 75.6% [95%CI: 67.7, 83.5], 80.0% [95%CI: 70.7, 89.3], and 92.0% [95%CI: 87.8, 96.1] in validation cohorts, respectively. Respective specificity was 88.6% [95% CI: 83.0, 94.2], 88.4% [95% CI: 81.9, 94.8], and 91.1% [95% CI: 86.8, 95.5] in training cohorts, and 86.8% [95% CI: 83.3, 90.3], 94.0% [95% CI: 89.5, 98.4], and 88.3% [95% CI: 84.4, 92.2] in validation cohorts. Limitations included use of several methods for feature selection and classification, less availability of studies evaluating a particular radiological modality, lack of a direct comparison between radiology and radiomics, and lack of external validation.

CONCLUSION

Although radiomics offers good diagnostic accuracy in detecting liver fibrosis, its role in clinical practice is not as clear at present due to comparability and validation constraints.

Machine Learning Radiomics Liver Function Model for Prognostic Prediction After Radical Resection of Advanced Gastric Cancer: A Retrospective Study

PURPOSE

We aimed to establish a machine learning radiomics liver function model to explore how liver function affects the prognosis of patients with gastric cancer (GC).

METHODS

Patients with advanced GC were retrospectively enrolled in this study. Eight machine learning radiomic models were constructed by extracting radiomic features from portal-vein-phase contrast-enhanced computed tomography (CE-CT) images. Clinicopathological features were determined using univariate and multifactorial Cox regression analyses. These features were used to construct a GC survival nomogram.

RESULTS

A total of 510 patients with GC were split into training and test cohorts in an 8:2 ratio. Kaplan-Meier analysis showed that patients with type I liver function had a better prognosis. Fifteen significant features were retained to establish the machine learning model. LightBGM showed the best predictive performance in the training (area under the receiver operating characteristic curve [AUC] 0.978) and test cohorts (AUC 0.714). Multivariate analysis revealed that gender, age, liver function, Nutritional Risk Screening 2002 (NRS-2002) score, tumor-lymph node-metastasis stage, tumor size, and tumor differentiation were independent risk factors for GC prognosis. The survival nomogram based on machine learning radiomics, instead of liver biochemical indicators, still had high accuracy (C-index of 0.771 vs. 0.773).

CONCLUSION

The machine learning radiomics liver function model has high diagnostic value in predicting the influence of liver function on prognosis in patients with GC.

Noninvasive diagnosis of liver cirrhosis: qualitative and quantitative imaging biomarkers

A diagnosis of cirrhosis initiates a shift in the management of chronic liver disease and affects the diagnostic workflow and treatment decision of primary liver cancer. Liver biopsy remains the gold standard for cirrhosis diagnosis, but it is invasive and susceptible to sampling bias and observer variability. Various qualitative and quantitative imaging biomarkers based on ultrasound, CT and MRI have been proposed for noninvasive diagnosis of cirrhosis. Qualitative imaging features are easy to apply but have moderate diagnostic sensitivity. Elastography techniques allow quantitative assessment of liver stiffness and are highly accurate for cirrhosis diagnosis. Ultrasound elastography are widely used in clinical practice, while MR elastography has narrower availability. Although not applicable in clinical practice yet, other quantitative imaging features, including liver surface nodularity, linear and volumetric measurement, extracellular volume fraction, liver enhancement on hepatobiliary phase, and parameters derived from diffusion-weighted imaging, can provide additional information of liver morphology, perfusion, and function, thus may increase diagnosis performance. The introduction of radiomics and deep learning has further improved diagnostic accuracy while reducing subjectivity. Several imaging features may also help to assess liver function and outcomes in patients with cirrhosis. In this review, we summarize the qualitative and quantitative imaging biomarkers for noninvasive cirrhosis diagnosis, and the assessment of liver function and outcomes, and discuss the challenges and future directions in this field.

Radiomics and liver: Where we are and where we are headed?

Hepatic diffuse conditions and focal liver lesions represent two of the most common scenarios to face in everyday radiological clinical practice. Thanks to the advances in technology, radiology has gained a central role in the management of patients with liver disease, especially due to its high sensitivity and specificity. Since the introduction of computed tomography (CT) and magnetic resonance imaging (MRI), radiology has been considered the non-invasive reference modality to assess and characterize liver pathologies. In recent years, clinical practice has moved forward to a quantitative approach to better evaluate and manage each patient with a more fitted approach. In this setting, radiomics has gained an important role in helping radiologists and clinicians characterize hepatic pathological entities, in managing patients, and in determining prognosis. Radiomics can extract a large amount of data from radiological images, which can be associated with different liver scenarios. Thanks to its wide applications in ultrasonography (US), CT, and MRI, different studies were focused on specific aspects related to liver diseases. Even if broadly applied, radiomics has some advantages and different pitfalls. This review aims to summarize the most important and robust studies published in the field of liver radiomics, underlying their main limitations and issues, and what they can add to the current and future clinical practice and literature.

An imaging-based machine learning model outperforms clinical risk scores for prognosis of cirrhotic variceal bleeding

OBJECTIVES

To develop and validate a machine learning model based on contrast-enhanced CT to predict the risk of occurrence of the composite clinical endpoint (hospital-based intervention or death) in cirrhotic patients with acute variceal bleeding (AVB).

METHODS

This retrospective study enrolled 330 cirrhotic patients with AVB between January 2017 and December 2020 from three clinical centers. Contrast-enhanced CT and clinical data were collected. Centers A and B were divided 7:3 into a training set and an internal test set, and center C served as a separate external test set. A well-trained deep learning model was applied to segment the liver and spleen. Then, we extracted 106 original features of the liver and spleen separately based on the Image Biomarker Standardization Initiative (IBSI). We constructed the Liver-Spleen (LS) model based on the selected radiomics features. The performance of LS model was evaluated by receiver operating characteristics and calibration curves. The clinical utility of models was analyzed using decision curve analyses (DCA).

RESULTS

The LS model demonstrated the best diagnostic performance in predicting the composite clinical endpoint of AVB in patients with cirrhosis, with an AUC of 0.782 (95% CI 0.650-0.882) and 0.789 (95% CI 0.674-0.878) in the internal test and external test groups, respectively. Calibration curves and DCA indicated the LS model had better performance than traditional clinical scores.

CONCLUSION

A novel machine learning model outperforms previously known clinical risk scores in assessing the prognosis of cirrhotic patients with AVB CLINICAL RELEVANCE STATEMENT: The Liver-Spleen model based on contrast-enhanced CT has proven to be a promising tool to predict the prognosis of cirrhotic patients with acute variceal bleeding, which can facilitate decision-making and personalized therapy in clinical practice.

KEY POINTS

• The Liver-Spleen machine learning model (LS model) showed good performance in assessing the clinical composite endpoint of cirrhotic patients with AVB (AUC ≥ 0.782, sensitivity ≥ 80%). • The LS model outperformed the clinical scores (AUC ≤ 0.730, sensitivity ≤ 70%) in both internal and external test cohorts.

CT-based methods for assessment of metabolic dysfunction associated with fatty liver disease

Metabolic dysfunction-associated fatty liver disease (MAFLD), previously called metabolic nonalcoholic fatty liver disease, is the most prevalent chronic liver disease worldwide. The multi-factorial nature of MAFLD severity is delineated through an intricate composite analysis of the grade of activity in concert with the stage of fibrosis. Despite the preeminence of liver biopsy as the diagnostic and staging reference standard, its invasive nature, pronounced interobserver variability, and potential for deleterious effects (encompassing pain, infection, and even fatality) underscore the need for viable alternatives. We reviewed computed tomography (CT)-based methods for hepatic steatosis quantification (liver-to-spleen ratio; single-energy "quantitative" CT; dual-energy CT; deep learning-based methods; photon-counting CT) and hepatic fibrosis staging (morphology-based CT methods; contrast-enhanced CT biomarkers; dedicated postprocessing methods including liver surface nodularity, liver segmental volume ratio, texture analysis, deep learning methods, and radiomics). For dual-energy and photon-counting CT, the role of virtual non-contrast images and material decomposition is illustrated. For contrast-enhanced CT, normalized iodine concentration and extracellular volume fraction are explained. The applicability and salience of these approaches for clinical diagnosis and quantification of MAFLD are discussed.Relevance statementCT offers a variety of methods for the assessment of metabolic dysfunction-associated fatty liver disease by quantifying steatosis and staging fibrosis.Key points• MAFLD is the most prevalent chronic liver disease worldwide and is rapidly increasing.• Both hardware and software CT advances with high potential for MAFLD assessment have been observed in the last two decades.• Effective estimate of liver steatosis and staging of liver fibrosis can be possible through CT.

Enhanced and unenhanced: Radiomics models for discriminating between benign and malignant cystic renal masses on CT images: A multi-center study

BACKGROUND

Machine learning algorithms used to classify cystic renal masses (CRMs) nave not been applied to unenhanced CT images, and their diagnostic accuracy had not been compared against radiologists.

METHOD

This retrospective study aimed to develop radiomics models that discriminate between benign and malignant CRMs in a triple phase computed tomography (CT) protocol and compare the diagnostic accuracy of the radiomics approach with experienced radiologists. Predictive models were established using a training set and validation set of unenhanced and enhanced (arterial phase [AP] and venous phase [VP]) CT images of benign and malignant CRMs. The diagnostic capabilities of the models and experienced radiologists were compared using Receiver Operating Characteristic (ROC) curves.

RESULTS

On unenhanced, AP and VP CT images in the validation set, the AUC, specificity, sensitivity and accuracy for discriminating between benign and malignant CRMs were 90.0 (95%CI: 81-98%), 90.0%, 90.5% and 90.2%; 93.0% (95%CI: 86-99%), 86.7%, 95.2% and 88.3%; and 95.0% (95%CI: 90%-100%), 93.3%, 90.5% and 92.1%, respectively, for the radiomics models. Diagnostic accuracy of the radiomics models differed significantly on unenhanced images in the training set vs. each radiologist (p = 0.001 and 0.003) but not in the validation set (p = 0.230 and 0.590); differed significantly on AP images in the validation set vs. each radiologist (p = 0.007 and 0.007) but not in the training set (p = 0.663 and 0.663); and there were no differences on VP images in the training or validation sets vs. each radiologist (training set: p = 0.453 and 0.051, validation set: p = 0.236 and 0.786).

CONCLUSIONS

Radiomics models may have clinical utility for discriminating between benign and malignant CRMs on unenhanced and enhanced CT images. The performance of the radiomics model on unenhanced CT images was similar to experienced radiologists, implying it has potential as a screening and diagnostic tool for CRMs.

A decision tree model to predict liver cirrhosis in hepatocellular carcinoma patients: a retrospective study

Background

The severity of liver cirrhosis in hepatocellular carcinoma (HCC) patients is essential for determining the scope of surgical resection. It also affects the long-term efficacy of systemic anti-tumor therapy and transcatheter arterial chemoembolization (TACE). Non-invasive tools, including aspartate aminotransferase to platelet ratio index (APRI), fibrosis-4 (FIB-4), and γ-glutamyl transferase to platelet ratio (GPR), are less accurate in predicting cirrhosis in HCC patients. We aimed to build a novel decision tree model to improve diagnostic accuracy of liver cirrhosis.

Patients and Methods

The Mann-Whitney U test, χ2 test, and multivariate logistic regression analysis were used to identify independent cirrhosis predictors. A decision tree model was developed using machine learning algorithms in a training cohort of 141 HCC patients. Internal validation was conducted in 99 HCC patients. The diagnostic accuracy and calibration of the established model were evaluated using receiver operating characteristic (ROC) and calibration curves, respectively.

Results

Sex and platelet count were identified as independent cirrhosis predictors. A decision tree model integrating imaging-reported cirrhosis, APRI, FIB-4, and GPR was established. The novel model had an excellent diagnostic performance in the training and validation cohorts, with area under the curve (AUC) values of 0.853 and 0.817, respectively. Calibration curves and the Hosmer-Lemeshow test showed good calibration of the novel model. The decision curve analysis (DCA) indicated that the decision tree model could provide a larger net benefit to predict liver cirrhosis.

Conclusion

Our developed decision tree model could successfully predict liver cirrhosis in HCC patients, which may be helpful in clinical decision-making.

T2-weighted imaging and dynamic contrast‑enhanced imaging in predicting the prognosis in patients with acute-on-chronic liver failure

BACKGROUND

Acute-on-chronic liver failure (ACLF) is a syndrome with high 28- and 90-day mortality rates. Magnetic resonance imaging (MRI) has been widely used to diagnose and evaluate liver disease. Our purpose is to determine the value of the imaging features derived from Gd-DTPA-enhanced MRI for predicting the poor outcome of patients with ACLF and develop a clinically practical radiological score.

METHODS

This retrospective study comprised 175 ACLF patients who underwent Gd-DTPA-enhanced abdominal MRI from January 2017 to December 2021. The primary end-point was 90-day mortality. Imaging parameters, such as diffuse hyperintense of the liver on T2WI, patchy enhancement of the liver at the arterial phase, uneven enhancement of the liver at the portal vein phase, gallbladder wall edema, periportal edema, ascites, esophageal and gastric varix, umbilical vein patefac, portal vein thrombosis, and splenomegaly were screened. Cox proportional hazard regression models were used to evaluate prognostic factors and develop a prediction model. The accuracy of the model was evaluated by receiver operating characteristic (ROC) curves.

RESULTS

During the follow-up period, 31 of the 175 ACLF patients died within 90 days. In the multivariate analysis, three imaging parameters were independently associated with survival: diffuse hyperintense on T2WI (p = 0.007; HR = 3.53 [1.40-8.89]), patchy enhancement at the arterial phase (p = 0.037; HR = 2.45 [1.06-5.69]), moderate ascites (vs. mild) (p = 0.006; HR = 4.12 [1.49-11.36]), and severe ascites (vs. mild) (p = 0.005; HR = 4.29 [1.57-11.71]). A practical radiological score was proposed, based on the presence of diffuse hyperintense (7 points), patchy enhancement (5 points), and ascites (6, 8, and 8 points for mild, moderate, and severe, respectively). Further analysis showed that a cut-off at 14 points was optimum to distinguish high-risk (score > 14) from the low-risk group (score ≤ 14) for 90-day survival and demonstrated a mean area under the ROC curve of 0.774 in ACLF patients.

CONCLUSIONS

Gd-DTPA-enhanced MR imaging features can predict poor outcomes in patients with ACLF, based on which we proposed a clinically practical radiological score allowing stratification of the 90-day survival.

An integrated radiomics nomogram based on conventional ultrasound improves discriminability between fibroadenoma and pure mucinous carcinoma in breast

Objective

To evaluate the ability of integrated radiomics nomogram based on ultrasound images to distinguish between breast fibroadenoma (FA) and pure mucinous carcinoma (P-MC).

Methods

One hundred seventy patients with FA or P-MC (120 in the training set and 50 in the test set) with definite pathological confirmation were retrospectively enrolled. Four hundred sixty-four radiomics features were extracted from conventional ultrasound (CUS) images, and radiomics score (Radscore) was constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Different models were developed by a support vector machine (SVM), and the diagnostic performance of the different models was assessed and validated. A comparison of the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) was performed to evaluate the incremental value of the different models.

Results

Finally, 11 radiomics features were selected, and then Radscore was developed based on them, which was higher in P-MC in both cohorts. In the test group, the clinic + CUS + radiomics (Clin + CUS + Radscore) model achieved a significantly higher area under the curve (AUC) value (AUC = 0.86, 95% CI, 0.733-0.942) when compared with the clinic + radiomics (Clin + Radscore) (AUC = 0.76, 95% CI, 0.618-0.869, P > 0.05), clinic + CUS (Clin + CUS) (AUC = 0.76, 95% CI, 0.618-0.869, P< 0.05), Clin (AUC = 0.74, 95% CI, 0.600-0.854, P< 0.05), and Radscore (AUC = 0.64, 95% CI, 0.492-0.771, P< 0.05) models, respectively. The calibration curve and DCA also suggested excellent clinical value of the combined nomogram.

Conclusion

The combined Clin + CUS + Radscore model may help improve the differentiation of FA from P-MC.

Development and Validation of a New Staging System for Esophageal Squamous Cell Carcinoma Patients Based on Combined Pathological TNM, Radiomics, and Proteomics

OBJECTIVE

This study aimed to construct a new staging system for patients with esophageal squamous cell carcinoma (ESCC) based on combined pathological TNM (pTNM) stage, radiomics, and proteomics.

METHODS

This study collected patients with radiomics and pTNM stage (Cohort 1, n = 786), among whom 103 patients also had proteomic data (Cohort 2, n = 103). The Cox regression model with the least absolute shrinkage and selection operator, and the Cox proportional hazards model were used to construct a nomogram and predictive models. Concordance index (C-index) and the integrated area under the time-dependent receiver operating characteristic (ROC) curve (IAUC) were used to evaluate the predictive models. The corresponding staging systems were further assessed using Kaplan-Meier survival curves.

RESULTS

For Cohort 1, the RadpTNM4c staging systems, constructed based on combined pTNM stage and radiomic features, outperformed the pTNM4c stage in both the training dataset 1 (Train1; IAUC 0.711 vs. 0.706, p < 0.001) and the validation dataset 1 (Valid1; IAUC 0.695 vs. 0.659, p < 0.001; C-index 0.703 vs. 0.674, p = 0.029). For Cohort 2, the ProtRadpTNM2c staging system, constructed based on combined pTNM stage, radiomics, and proteomics, outperformed the pTNM2c stage in both the Train2 (IAUC 0.777 vs. 0.610, p < 0.001; C-index 0.898 vs. 0.608, p < 0.001) and Valid2 (IAUC 0.746 vs. 0.608, p < 0.001; C-index 0.889 vs. 0.641, p = 0.009) datasets.

CONCLUSIONS

The ProtRadpTNM2c staging system, based on combined pTNM stage, radiomic, and proteomic features, improves the predictive performance of the classical pTNM staging system.

Clinical-radiomic analysis for non-invasive prediction of liver steatosis on non-contrast CT: A pilot study

Purpose: Our aim is to build and validate a clinical-radiomic model for non-invasive liver steatosis prediction based on non-contrast computed tomography (CT). Methods: We retrospectively reviewed 342 patients with suspected NAFLD diagnoses between January 2019 and July 2020 who underwent non-contrast CT and liver biopsy. Radiomics features from hepatic and splenic regions-of-interests (ROIs) were extracted based on abdominal non-contrast CT imaging. The radiomics signature was constructed based on reproducible features by adopting the least absolute shrinkage and selection operator (LASSO) regression. Then, multivariate logistic regression analysis was applied to develop a combined clinical-radiomic nomogram integrating radiomics signature with several independent clinical predictors in a training cohort of 124 patients between January 2019 and December 2019. The performance of models was determined by the area under the receiver operating characteristic curves and calibration curves. We conducted an internal validation during 103 consecutive patients between January 2020 and July 2020. Results: The radiomics signature was composed of four steatosis-related features and positively correlated with pathologic liver steatosis grade (p < 0.01). In both subgroups (Group One, none vs. steatosis; Group Two, none/mild vs. moderate/severe steatosis), the clinical-radiomic model performed best within the validation cohort with an AUC of 0.734 and 0.930, respectively. The calibration curve confirmed the concordance of excellent models. Conclusion: We developed a robust clinical-radiomic model for accurate liver steatosis stage prediction in a non-invasive way, which may improve the clinical decision-making ability.

Development of an MRI-Based Radiomics-Clinical Model to Diagnose Liver Fibrosis Secondary to Pancreaticobiliary Maljunction in Children

BACKGROUND

Preoperative diagnosis of liver fibrosis in children with pancreaticobiliary maljunction (PBM) is needed to guide clinical decision-making and improve patient prognosis.

PURPOSE

To develop and validate an MR-based radiomics-clinical nomogram for identifying liver fibrosis in children with PBM.

STUDY TYPE

Retrospective.

POPULATION

A total of 136 patients with PBM from two centers (center A: 111 patients; center B: 25 patients). Cases from center A were randomly divided into training (74 patients) and internal validation (37 patients) sets. Cases from center B were assigned to the external validation set. Liver fibrosis was determined by histopathological examination.

FIELD STRENGTH/SEQUENCE

A 3.0 T (two vendors)/T1-weighted imaging and T2-weighted imaging.

ASSESSMENT

Clinical factors associated with liver fibrosis were evaluated. A total of 3562 radiomics features were extracted from segmented liver parenchyma. Maximum relevance minimum redundancy and least absolute shrinkage and selection operator were recruited to screen radiomics features. Based on the selected variables, multivariate logistic regression was used to construct the clinical model, radiomics model, and combined model. The combined model was visualized as a nomogram to show the impact of the radiomics signature and key clinical factors on the individual risk of developing liver fibrosis.

STATISTICAL TESTS

Mann-Whitney U and chi-squared tests were used to compare clinical factors. P < 0.05 was considered statistically significant in the final models.

RESULTS

Two clinical factors and four radiomics features were selected as they were associated with liver fibrosis in the training (AUC, 0.723, 0.927), internal validation (AUC, 0.718, 0.885), and external validation (AUC, 0.737, 0.865) sets. The radiomics-clinical nomogram yielded the best performance in the training (AUC, 0.977), internal validation (AUC, 0.921), and external validation (AUC, 0.878) sets, with good calibration (P > 0.05).

DATA CONCLUSION

Our radiomic-based nomogram is a noninvasive, accurate, and preoperative diagnostic tool that is able to detect liver fibrosis in PBM children.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 2.

An overview: Management of patients with advanced hepatocellular carcinoma

Hepatocellular carcinoma (HCC) has constituted a significant health burden worldwide, and patients with advanced HCC, which is stage C as defined by the Barcelona Clinic Liver Cancer staging system, have a poor overall survival of 6-8 months. Studies have indicated the significant survival benefit of treatment based on sorafenib, lenvatinib, or atezolizumab-bevacizumab with reliable safety. In addition, the combination of two or more molecularly targeted therapies (first- plus second-line) has become a hot topic recently and is now being extensively investigated in patients with advanced HCC. In addition, a few biomarkers have been investigated and found to predict drug susceptibility and prognosis, which provides an opportunity to evaluate the clinical benefits of current therapies. In addition, many therapies other than tyrosine kinase inhibitors that might have additional survival benefits when combined with other therapeutic modalities, including immunotherapy, transarterial chemoembolization, radiofrequency ablation, hepatectomy, and chemotherapy, have also been examined. This review provides an overview on the current understanding of disease management and summarizes current challenges with and future perspectives on advanced HCC.

Establishment and Validation of a Machine Learning Prediction Model Based on Big Data for Predicting the Risk of Bone Metastasis in Renal Cell Carcinoma Patients

Purpose

Since the prognosis of renal cell carcinoma (RCC) patients with bone metastasis (BM) is poor, this study is aimed at using big data to build a machine learning (ML) model to predict the risk of BM in RCC patients.

Methods

A retrospective study was conducted on 40,355 RCC patients in the SEER database from 2010 to 2017. LASSO regression and multivariate logistic regression analysis was performed to determine independent risk factors of RCC-BM. Six ML algorithm models, including LR, GBM, XGB, RF, DT, and NBC, were used to establish risk models for predicting RCC-BM. The prediction performance of ML models was weighed by 10-fold cross-validation.

Results

The study investigated 40,355 patients diagnosed with RCC in the SEER database, where 1,811 (4.5%) were BM patients. Independent risk factors for BM were tumor grade, T stage, N stage, liver metastasis, lung metastasis, and brain metastasis. Among the RCC-BM risk prediction models established by six ML algorithms, the XGB model showed the best prediction performance (AUC = 0.891). Therefore, a network calculator based on the XGB model was established to individually assess the risk of BM in patients with RCC.

Conclusion

The XGB risk prediction model based on the ML algorithm performed a good prediction effect on BM in RCC patients.

The Application Value of MRI T 2 ∗ WI Radiomics Nomogram in Discriminating Hepatocellular Carcinoma from Intrahepatic Cholangiocarcinoma

Objective. To establish and validate an MRI T $2^{\ast }$ WI-based radiomics nomogram model and to discriminate hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (ICCA). Methods. 174 patients were retrospectively collected, who were diagnosed with primary hepatic carcinoma by surgery or puncture pathology and received preoperative MRI scans including T $2^{\ast }$ WI scans. There were 113 cases of HCC and 61 cases of mass-type ICCA. T $2^{\ast }$ WI was used for feature extraction, the extent of the lesions was manually outlined at the largest lesions layer of the T $2^{\ast }$ WI, and the feature dimension reduction was performed by the mRMR and LASSO to obtain the optimal feature set. The radiomics features and clinical risk factors were combined to establish the radiomics nomogram model. In both training and validation groups, calibration curves and ROC curves were applied to validate the efficacy of the established model. Finally, calibration curves were applied to assess the degree of fitting and DCA to assess the clinical utility of the established model. Results. The radiomics model had the AUC of 0.90 (95% CI, 0.85–0.96) and 0.91 (95% CI, 0.83–0.99) in the training and validation groups, respectively; the AUC of the radiomics nomogram was 0.97 (95% CI, 0.94–0.99) in the training group and 0.95 (95% CI, 0.95–0.99) in the validation group. DCA suggested the clinical application value of the nomogram model. Conclusion. Radiomics nomogram model based on MRI T $2^{\ast }$ WI scan without enhancement can be used to discriminate HCC from ICCA.

Radiomics based on enhanced CT for differentiating between pulmonary tuberculosis and pulmonary adenocarcinoma presenting as solid nodules or masses

PURPOSE

To investigate the incremental value of enhanced CT-based radiomics in discriminating between pulmonary tuberculosis (PTB) and pulmonary adenocarcinoma (PAC) presenting as solid nodules or masses and to develop an optimal radiomics model.

METHODS

A total of 128 lesions (from 123 patients) from three hospitals were retrospectively analyzed and were randomly divided into training and test datasets at a ratio of 7:3. Independent predictors in subjective image features were used to develop the subjective image model (SIM). The plain CT-based and enhanced CT-based radiomics features were screened by the correlation coefficient method, univariate analysis, and the least absolute shrinkage and selection operator, then used to build the plain CT radiomics model (PRM) and enhanced CT radiomics model (ERM), respectively. Finally, the combined model (CM) combining PRM and ERM was established. In addition, the performance of three radiologists and one respiratory physician was evaluated. The areas under the receiver operating characteristic curve (AUCs) were used to assess the performance of each model.

RESULTS

The differential diagnostic capability of the ERM (training: AUC = 0.933; test: AUC = 0.881) was better than that of the PRM (training: AUC = 0.861; test: AUC = 0.756) and the SIM (training: AUC = 0.760; test: AUC = 0.611). The CM was optimal (training: AUC = 0.948; test: AUC = 0.917) and outperformed the respiratory physician and most radiologists.

CONCLUSIONS

The ERM was more helpful than the PRM for identifying PTB and PAC that present as solid nodules or masses, and the CM was the best.