A radiomics-based biomarker for cytokeratin 19 status of hepatocellular carcinoma with gadoxetic acid-enhanced MRI

Deep Reinforcement Learning for CT-Based Non-Invasive Prediction of SOX9 Expression in Hepatocellular Carcinoma

Background: The transcription factor SOX9 plays a critical role in various diseases, including hepatocellular carcinoma (HCC), and has been implicated in resistance to sorafenib treatment. Accurate assessment of SOX9 expression is important for guiding personalized therapy in HCC patients; however, a reliable non-invasive method for evaluating SOX9 status remains lacking. This study aims to develop a deep learning (DL) model capable of preoperatively and non-invasively predicting SOX9 expression from CT images in HCC patients. Methods: We retrospectively analyzed a dataset comprising 4011 CT images from 101 HCC patients who underwent surgical resection followed by sorafenib therapy at West China Hospital, Sichuan University. A deep reinforcement learning (DRL) approach was proposed to enhance prediction accuracy by identifying and focusing on image regions highly correlated with SOX9 expression, thereby reducing the impact of background noise. Results: Our DRL-based model achieved an area under the curve (AUC) of 91.00% (95% confidence interval: 88.64-93.15%), outperforming conventional DL methods by over 10%. Furthermore, survival analysis revealed that patients with SOX9-positive tumors had significantly shorter recurrence-free survival (RFS) and overall survival (OS) compared to SOX9-negative patients, highlighting the prognostic value of SOX9 status. Conclusions: This study demonstrates that a DRL-enhanced DL model can accurately and non-invasively predict SOX9 expression in HCC patients using preoperative CT images. These findings support the clinical utility of imaging-based SOX9 assessment in informing treatment strategies and prognostic evaluation for patients with advanced HCC.

A magnetic resonance image-based deep learning radiomics nomogram for hepatocyte cytokeratin 7 expression: application to predict cholestasis progression in children with pancreaticobiliary maljunction

BACKGROUND

Hepatocyte cytokeratin 7 (CK7) is a reliable marker for evaluating the severity of cholestasis in chronic cholestatic cholangiopathies. However, there is currently no noninvasive test available to assess the status of hepatocyte CK7 in pancreaticobiliary maljunction patients.

OBJECTIVE

We aimed to develop a deep learning radiomics nomogram using magnetic resonance images (MRIs) to preoperatively identify the hepatocyte CK7 status and assess cholestasis progression in patients with pancreaticobiliary maljunction.

MATERIALS AND METHODS

In total, 180 pancreaticobiliary maljunction patients were retrospectively enrolled and were randomly divided into a training cohort (n = 144) and a validation cohort (n = 36). CK7 status was determined through immunohistochemical analysis. Pyradiomics and pretrained ResNet50 were used to extract radiomics and deep learning features, respectively. To construct the radiomics and deep learning signature, feature selection methods including the minimum redundancy-maximum relevance and least absolute shrinkage and selection operator were employed. The integrated deep learning radiomics nomogram model was constructed by combining the imaging signatures and valuable clinical feature.

RESULTS

The deep learning signature exhibited superior predictive performance compared with the radiomics signature, as evidenced by the higher area under the curve (AUC) values in validation cohort (0.92 vs. 0.81). Further, the deep learning radiomics nomogram, which incorporated the radiomics signature, deep learning signature, and Komi classification, demonstrated excellent predictive ability for CK7 expression, with AUC value of 0.95 in the validation cohort.

CONCLUSION

The proposed deep learning radiomics nomogram exhibits promising performance in accurately identifying hepatic CK7 expression, thus facilitating prediction of cholestasis progression and perhaps earlier initiation of treatment in pancreaticobiliary maljunction children.

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

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

Gadoxetic acid-enhanced MRI for identifying cholangiocyte phenotype hepatocellular carcinoma by interpretable machine learning: individual application of SHAP

PURPOSE

Cholangiocyte phenotype hepatocellular carcinoma (HCC) is highly invasive. This study aims to develop and validate an optimal machine learning model to predict cholangiocyte phenotype HCC based on T1 mapping gadoxetic acid-enhanced MRI and to implement individual applications via the Shapley Additive explanation (SHAP).

METHODS

We included 180 patients with histologically confirmed HCC from two institutions. Clinical and MRI imaging features were screened for predicting cholangiocyte phenotype hepatocellular carcinoma using Least Absolute Shrinkage and Selection Operator (LASSO) and the logistic regression analysis. Five machine learning models were constructed based on these features. A Kaplan-Meier survival analysis aims to compare prognostic differences between cholangiocyte phenotype-positive HCC groups and classical (cholangiocyte phenotype-negative) HCC groups, and was conducted to explore the prognostic information of the optimal model.

RESULTS

The most significant clinicoradiological features, including the platelet-to-lymphocyte ratio (PLR), tumor capsule, target sign on hepatobiliary phase (HBP), and T1 relaxation time of 20 min (T1rt-20 min), were selected to construct the prediction model. Finally, we selected the eXtreme Gradient Boosting (XGBoost) model as the optimal predictive model, which achieved AUCs of 0.835, 0.830, 0.816 and 0.776 in training, internal validation, external validation, and prospective validation cohorts, respectively, for visual analysis via SHAP, in which T1rt-20 min made a significant contribution. Survival analysis showed a statistically significant difference in relapse-free survival (RFS) between cholangiocyte phenotype-positive HCC groups and classical HCC groups from institution I (hazard ratio [HR] 1.994; 95% CI, 1.059-3.758; P = 0.027), and the construction XGBoost model can be used to stratify RFS according to prognosis (HR, 1.986; 95% CI, 1.061-3.717; P = 0.029).

CONCLUSION

The machine learning model utilizing T1 mapping gadoxetic acid-enhanced MRI demonstrates significant potential in identifying cholangiocyte phenotype HCC. Furthermore, personalized prediction is enhanced through the application of SHAP, providing valuable insights to support clinical decision-making processes.

Radiomics-based biomarker for PD-1 status and prognosis analysis in patients with HCC

Purpose

To investigate the impact of preoperative contrast-enhanced CT-based radiomics model on PD-1 prediction in hepatocellular carcinoma (HCC) patients.

Methods

The study included 105 HCC patients (training cohort: 72; validation cohort: 33) who underwent preoperative contrast-enhanced CT and received systemic sorafenib treatment after surgery. Radiomics score was built for each patient and was integrated with independent clinic radiologic predictors into the radiomics model using multivariable logistic regression analysis.

Results

Seventeen radiomics features were finally selected to construct the radiomics score. In multivariate analysis, serum creatine and peritumoral enhancement were significant independent factors for PD-1 prediction. The radiomics model integrated radiomics signature with serum creatine and peritumoral enhancement showed good discriminative performance (AUC of 0.897 and 0.794 in the training and validation cohort). Overall survival (OS) was significantly different between the radiomics-predicted PD-1-positive and PD-1-negative groups (OS: 29.66 months, CI:16.03-44.40 vs. 31.04 months, CI: 17.10-44.07, P<0.001). Radiomics-predicted PD-1 was an independent predictor of OS of patients treated with sorafenib after surgery. (Hazard ratio [HR]: 1.61 [1.23-2.1], P<0.001).

Conclusion

The proposed model based on radiomic signature helps to evaluate PD-1 status of HCC patients and may be used for evaluating patients most likely to benefit from sorafenib as a potentially combination therapy regimen with immune checkpoint therapies.

Gadoxetic Acid-Enhanced MRI-Based Radiomic Models for Preoperative Risk Prediction and Prognostic Assessment of Proliferative Hepatocellular Carcinoma

RATIONALE AND OBJECTIVES

Proliferative hepatocellular carcinoma (HCC) is associated with high invasiveness and poor prognosis. This study aimed to investigate the preoperative risk prediction and prognostic value of different radiomics models and a nomogram for proliferative HCC.

MATERIALS AND METHODS

Patients were randomly divided into a training cohort (n = 156) and a validation cohort (n = 66) in a 7:3 ratio. Original and delta (the different value between imaging features extracted from two different phases) radiomics features were extracted from T1-weighted imaging (T1WI), arterial, and hepatobiliary phases to construct models using different machine learning algorithms. Logistic regression was used to select clinical independent risk factors. A nomogram was constructed by integrating the optimal radiomics model score with independent risk factors. The diagnostic efficacy and clinical utility of the models were assessed. Subsequently, patients were stratified into high-risk and low-risk subgroups based on radiomics model scores and nomogram scores, and both recurrence-free survival (RFS) and overall survival (OS) were evaluated.

RESULTS

Multivariate logistic regression analysis showed that BCLC stage and combined radscore were independent predictors of proliferative HCC. The area under the curve (AUC) of the nomogram incorporating these factors was 0.838 and 0.801 in the training and validation cohorts, respectively, with good predictive performance. Multivariate Cox regression analysis shows that the delta radiomics model (DR)-predicted proliferative HCC can independently predict RFS and OS, with scores from the delta radiomics model performing best in prognostic risk stratification.

CONCLUSION

The nomogram can effectively predict proliferative HCC, while different radiomics models and the nomogram can offer varying prognostic stratification values.

Radiomics predicting immunohistochemical markers in primary hepatic carcinoma: Current status and challenges

Primary hepatic carcinoma, comprising hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and combined hepatocellular cholangiocarcinoma (cHCC-CCA), ranks among the most common malignancies worldwide. The heterogeneity of tumors is a primary factor impeding the efficacy of treatments for primary hepatic carcinoma. Immunohistochemical markers may play a potential role in characterizing this heterogeneity, providing significant guidance for prognostic analysis and the development of personalized treatment plans for the patients with primary hepatic carcinoma. Currently, primary hepatic carcinoma immunohistochemical analysis primarily relies on invasive techniques such as surgical pathology and tissue biopsy. Consequently, the non-invasive preoperative acquisition of primary hepatic carcinoma immunohistochemistry has emerged as a focal point of research. As an emerging non-invasive diagnostic technique, radiomics possesses the potential to extensively characterize tumor heterogeneity. It can predict immunohistochemical markers associated with hepatocellular carcinoma preoperatively, demonstrating significant auxiliary utility in clinical guidance. This article summarizes the progress in using radiomics to predict immunohistochemical markers in primary hepatic carcinoma, addresses the challenges faced in this field of study, and anticipates its future application prospects.

Bridging the Gap Between Imaging and Molecular Characterization: Current Understanding of Radiomics and Radiogenomics in Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is the sixth most common malignancy worldwide and the third leading cause of cancer-related deaths. Imaging plays a crucial role in the screening, diagnosis, and monitoring of HCC; however, the potential mechanism regarding phenotypes or molecular subtyping remains underexplored. Radiomics significantly expands the selection of features available by extracting quantitative features from imaging data. Radiogenomics bridges the gap between imaging and genetic/transcriptomic information by associating imaging features with critical genes and pathways, thereby providing biological annotations to these features. Despite challenges in interpreting these connections, assessing their universality, and considering the diversity in HCC etiology and genetic information across different populations, radiomics and radiogenomics offer new perspectives for precision treatment in HCC. This article provides an up-to-date summary of the advancements in radiomics and radiogenomics throughout the HCC care continuum, focusing on the clinical applications, advantages, and limitations of current techniques and offering prospects. Future research should aim to overcome these challenges to improve the prognosis of HCC patients and leverage imaging information for patient benefit.

Noninvasive identification of SOX9 status using radiomics signatures may help construct personalized treatment strategy in hepatocellular carcinoma

OBJECTIVES

To develop and validate a radiomics-based model for predicting SOX9-positive hepatocellular carcinoma (HCC) using preoperative contrast-enhanced computed tomography (CT) images.

METHODS

From January 2013 to April 2017, patients with histologically proven HCC who received systemic sorafenib treatment after curative resection were retrospectively enrolled. Radiomic features were extracted from portal venous phase CT images and selected to build a radiomics score using logistic regression analysis. The factors associated with SOX9 expression were selected and combined by univariate and multivariate analyses to establish clinico-liver imaging (CL) model and clinico-liver imaging-radiomics (CLR) model. Diagnostic performance was measured by area under curve (AUC). Overall survival (OS) and recurrence-free survival (RFS) rates were compared using Kaplan-Meier method.

RESULTS

A total of 108 patients (training cohort: n = 80; validation cohort: n = 28) were enrolled. Multivariate analyses revealed that the albumin-bilirubin grade and tumor size were significant independent factors for predicting SOX9-positive HCCs and were included in the CL model. The CLR model integrating the radiomics score with albumin-bilirubin grade and tumor size showed better discriminative performance than the CL model with AUCs of 0.912 and 0.790 in the training and validation cohorts. Survival curves for RFS and OS showed that SOX9 expression was closely related to the prognosis of HCC patients. RFS and OS rates were significantly lower in patients with SOX9-positive than SOX9-negative (51.02% vs. 75.00% at 1-year RFS rates; 76.92% vs. 94.94% at 2-year OS rates).

CONCLUSION

Radiomics signatures may serve as noninvasive predictors for SOX9 status evaluation in patients with HCC and may aid in constructing individualized treatment strategies.

Prognostication of Hepatocellular Carcinoma Using Artificial Intelligence

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

Leveraging radiomics and AI for precision diagnosis and prognostication of liver malignancies

Liver tumors, whether primary or metastatic, have emerged as a growing concern with substantial global health implications. Timely identification and characterization of liver tumors are pivotal factors in order to provide optimum treatment. Imaging is a crucial part of the detection of liver tumors; however, conventional imaging has shortcomings in the proper characterization of these tumors which leads to the need for tissue biopsy. Artificial intelligence (AI) and radiomics have recently emerged as investigational opportunities with the potential to enhance the detection and characterization of liver lesions. These advancements offer opportunities for better diagnostic accuracy, prognostication, and thereby improving patient care. In particular, these techniques have the potential to predict the histopathology, genotype, and immunophenotype of tumors based on imaging data, hence providing guidance for personalized treatment of such tumors. In this review, we outline the progression and potential of AI in the field of liver oncology imaging, specifically emphasizing manual radiomic techniques and deep learning-based representations. We discuss how these tools can aid in clinical decision-making challenges. These challenges encompass a broad range of tasks, from prognosticating patient outcomes, differentiating benign treatment-related factors and actual disease progression, recognizing uncommon response patterns, and even predicting the genetic and molecular characteristics of the tumors. Lastly, we discuss the pitfalls, technical limitations and future direction of these AI-based techniques.

Deep learning-based multi-model prediction for disease-free survival status of patients with clear cell renal cell carcinoma after surgery: a multicenter cohort study

BACKGROUND

Although separate analysis of individual factor can somewhat improve the prognostic performance, integration of multimodal information into a single signature is necessary to stratify patients with clear cell renal cell carcinoma (ccRCC) for adjuvant therapy after surgery.

METHODS

A total of 414 patients with whole slide images, computed tomography images, and clinical data from three patient cohorts were retrospectively analyzed. The authors performed deep learning and machine learning algorithm to construct three single-modality prediction models for disease-free survival of ccRCC based on whole slide images, cell segmentation, and computed tomography images, respectively. A multimodel prediction signature (MMPS) for disease-free survival were further developed by combining three single-modality prediction models and tumor stage/grade system. Prognostic performance of the prognostic model was also verified in two independent validation cohorts.

RESULTS

Single-modality prediction models performed well in predicting the disease-free survival status of ccRCC. The MMPS achieved higher area under the curve value of 0.742, 0.917, and 0.900 in three independent patient cohorts, respectively. MMPS could distinguish patients with worse disease-free survival, with HR of 12.90 (95% CI: 2.443-68.120, P <0.0001), 11.10 (95% CI: 5.467-22.520, P <0.0001), and 8.27 (95% CI: 1.482-46.130, P <0.0001) in three different patient cohorts. In addition, MMPS outperformed single-modality prediction models and current clinical prognostic factors, which could also provide complements to current risk stratification for adjuvant therapy of ccRCC.

CONCLUSION

Our novel multimodel prediction analysis for disease-free survival exhibited significant improvements in prognostic prediction for patients with ccRCC. After further validation in multiple centers and regions, the multimodal system could be a potential practical tool for clinicians in the treatment for ccRCC patients.

MRI-Based Radiomics and Deep Learning in Biological Characteristics and Prognosis of Hepatocellular Carcinoma: Opportunities and Challenges

Hepatocellular carcinoma (HCC) is the fifth most common malignancy and the third leading cause of cancer-related death worldwide. HCC exhibits strong inter-tumor heterogeneity, with different biological characteristics closely associated with prognosis. In addition, patients with HCC often distribute at different stages and require diverse treatment options at each stage. Due to the variability in tumor sensitivity to different therapies, determining the optimal treatment approach can be challenging for clinicians prior to treatment. Artificial intelligence (AI) technology, including radiomics and deep learning approaches, has emerged as a unique opportunity to improve the spectrum of HCC clinical care by predicting biological characteristics and prognosis in the medical imaging field. The radiomics approach utilizes handcrafted features derived from specific mathematical formulas to construct various machine-learning models for medical applications. In terms of the deep learning approach, convolutional neural network models are developed to achieve high classification performance based on automatic feature extraction from images. Magnetic resonance imaging offers the advantage of superior tissue resolution and functional information. This comprehensive evaluation plays a vital role in the accurate assessment and effective treatment planning for HCC patients. Recent studies have applied radiomics and deep learning approaches to develop AI-enabled models to improve accuracy in predicting biological characteristics and prognosis, such as microvascular invasion and tumor recurrence. Although AI-enabled models have demonstrated promising potential in HCC with biological characteristics and prognosis prediction with high performance, one of the biggest challenges, interpretability, has hindered their implementation in clinical practice. In the future, continued research is needed to improve the interpretability of AI-enabled models, including aspects such as domain knowledge, novel algorithms, and multi-dimension data sources. Overcoming these challenges would allow AI-enabled models to significantly impact the care provided to HCC patients, ultimately leading to their deployment for clinical use. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

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

BACKGROUND

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

AIM

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

METHODS

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

RESULTS

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

CONCLUSION

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

Dual-phenotype hepatocellular carcinoma: correlation of MRI features with other primary hepatocellular carcinoma and differential diagnosis

Objectives

Dual-phenotype hepatocellular carcinoma (DPHCC) is a rare subtype of hepatocellular carcinoma characterized by high invasiveness and a poor prognosis. The study aimed to compare clinical and magnetic resonance imaging (MRI) features of DPHCC with that of non-DPHCC and intrahepatic cholangiocarcinoma (ICC), exploring the most valuable features for diagnosing DPHCC.

Methods

A total of 208 cases of primary liver cancer, comprising 27 DPHCC, 113 non-DPHCC, and 68 ICC, who undergone gadoxetic acid-enhanced MRI, were enrolled in this study. The clinicopathologic and MRI features of all cases were summarized and analyzed. Univariate and multivariate logistic regression analyses were conducted to identify the predictors. Kaplan-Meier survival analysis was used to evaluate the 1-year and 2-year disease-free survival (DFS) and overall survival (OS) rates in the cohorts.

Results

In the multivariate analysis, the absence of tumor capsule (P = 0.046; OR = 9.777), persistent enhancement (P = 0.006; OR = 46.941), arterial rim enhancement (P = 0.011; OR = 38.211), and target sign on DWI image (P = 0.021; OR = 30.566) were identified as independently significant factors for distinguishing DPHCC from non-DPHCC. Serum alpha-fetoprotein (AFP) >20 μg/L (P = 0.036; OR = 67.097) and hepatitis B virus (HBV) positive (P = 0.020; OR = 153.633) were independent significant factors for predicting DPHCC compared to ICC. The 1-year and 2-year DFS rates for patients in the DPHCC group were 65% and 50%, respectively, whereas those for the non-DPHCC group were 80% and 60% and for the ICC group were 50% and 29%, respectively. The 1-year and 2-year OS rates for patients in the DPHCC group were 74% and 60%, respectively, whereas those for the non-DPHCC group were 87% and 70% and for the ICC group were 55% and 37%, respectively. Kaplan-Meier survival analysis revealed significant differences in the 1-year and 2-year OS rates between the DPHCC and non-DPHCC groups (P = 0.030 and 0.027) as well as between the DPHCC and ICC groups (P = 0.029 and 0.016).

Conclusion

In multi-parameter MRI, combining the assessment of the absence of tumor capsule, persistent enhancement, arterial rim enhancement, and target sign on DWI image with clinical data such as AFP >20 μg/L and HBV status may support in the diagnosis of DPHCC and differentiation from non-DPHCC and ICC. Accurate preoperative diagnosis facilitates the selection of personalized treatment options.

Diagnostic value of radiomics in predicting Ki-67 and cytokeratin 19 expression in hepatocellular carcinoma: a systematic review and meta-analysis

Background

Radiomics have been increasingly used in the clinical management of hepatocellular carcinoma (HCC), such as markers prediction. Ki-67 and cytokeratin 19 (CK-19) are important prognostic markers of HCC. Radiomics has been introduced by many researchers in the prediction of these markers expression, but its diagnostic value remains controversial. Therefore, this review aims to assess the diagnostic value of radiomics in predicting Ki-67 and CK-19 expression in HCC.

Methods

Original studies were systematically searched in PubMed, EMBASE, Cochrane Library, and Web of Science from inception to May 2023. All included studies were evaluated by the radiomics quality score. The C-index was used as the effect size of the performance of radiomics in predicting Ki-67and CK-19 expression, and the positive cutoff values of Ki-67 label index (LI) were determined by subgroup analysis and meta-regression.

Results

We identified 34 eligible studies for Ki-67 (18 studies) and CK-19 (16 studies). The most common radiomics source was magnetic resonance imaging (MRI; 25/34). The pooled C-index of MRI-based models in predicting Ki-67 was 0.89 (95% CI:0.86-0.92) in the training set, and 0.87 (95% CI: 0.82-0.92) in the validation set. The pooled C-index of MRI-based models in predicting CK-19 was 0.86 (95% CI:0.81-0.90) in the training set, and 0.79 (95% CI: 0.73-0.84) in the validation set. Subgroup analysis suggested Ki-67 LI cutoff was a significant source of heterogeneity (I 2 = 0.0% P>0.05), and meta-regression showed that the C-index increased as Ki-67 LI increased.

Conclusion

Radiomics shows promising diagnostic value in predicting positive Ki-67 or CK-19 expression. But lacks standardized guidelines, which makes the model and variables selection dependent on researcher experience, leading to study heterogeneity. Therefore, standardized guidelines are warranted for future research.

Systematic Review Registration

https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42023427953.

The value of MRI in predicting hepatocellular carcinoma with cytokeratin 19 expression: a systematic review and meta-analysis

AIM

To evaluate the overall diagnostic performance of magnetic resonance imaging (MRI), different image features, and different image analysis methods in predicting hepatocellular carcinoma (HCC) with cytokeratin 19 (CK19) expression.

MATERIALS AND METHODS

A systematic literature search was performed to identify studies using MRI to predict HCC with CK19 expression between 2012 and 2023. Data were extracted to calculate the pooled sensitivity and specificity. Overall diagnostic performance was assessed using areas under the summary receiver operating characteristic curve (AUC). Subgroup analyses were conducted for specific image features and according to image analysis methods (traditional image feature, radiomics, and combined methods). Z-test statistics was used to analyse the differences in diagnostic performance between combined and individual methods.

RESULTS

Eleven studies with 14 datasets (1,278 lesions from 1,264 patients) were included. The overall pooled sensitivity, specificity, and AUC with corresponding 95% confidence intervals were estimated to be 0.72 (0.55, 0.85), 0.88 (0.80, 0.93), and 0.89 (0.86, 0.91) for MRI in predicting HCC with CK19 expression. Combined methods had higher sensitivity than image feature methods (0.86 versus 0.54, p=0.001), with no difference in specificity (0.85 versus 0.87, p=0.641). There were no significant differences between radiomics and combined methods regarding sensitivity (p=0.796) and specificity (p=0.535), respectively.

CONCLUSION

MRI shows moderate sensitivity and high specificity in identifying HCC with CK19 expression. The application of radiomics can improve the sensitivity of MRI in identifying HCC with CK19 expression.

A Noninvasive Approach to Evaluate Tumor Immune Microenvironment and Predict Outcomes in Hepatocellular Carcinoma

It is widely recognized that tumor immune microenvironment (TIME) plays a crucial role in tumor progression, metastasis, and therapeutic response. Despite several noninvasive strategies have emerged for cancer diagnosis and prognosis, there are still lack of effective radiomic-based model to evaluate TIME status, let alone predict clinical outcome and immune checkpoint inhibitor (ICIs) response for hepatocellular carcinoma (HCC). In this study, we developed a radiomic model to evaluate TIME status within the tumor and predict prognosis and immunotherapy response. A total of 301 patients who underwent magnetic resonance imaging (MRI) examinations were enrolled in our study. The intra-tumoral expression of 17 immune-related molecules were evaluated using co-detection by indexing (CODEX) technology, and we construct Immunoscore (IS) with the least absolute shrinkage and selection operator (LASSO) algorithm and Cox regression method to evaluate TIME. Of 6115 features extracted from MRI, five core features were filtered out, and the Radiomic Immunoscore (RIS) showed high accuracy in predicting TIME status in testing cohort (area under the curve = 0.753). More importantly, RIS model showed the capability of predicting therapeutic response to anti-programmed cell death 1 (PD-1) immunotherapy in an independent cohort with advanced HCC patients (area under the curve = 0.731). In comparison with previously radiomic-based models, our integrated RIS model exhibits not only higher accuracy in predicting prognosis but also the potential guiding significance to HCC immunotherapy.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43657-023-00136-8.

Consensus report from the 10th Global Forum for Liver Magnetic Resonance Imaging: developments in HCC management

The 10th Global Forum for Liver Magnetic Resonance Imaging (MRI) was held as a virtual 2-day meeting in October 2021, attended by delegates from North and South America, Asia, Australia, and Europe. Most delegates were radiologists with experience in liver MRI, with representation also from specialists in liver surgery, oncology, and hepatology. Presentations, discussions, and working groups at the Forum focused on the following themes: • Gadoxetic acid in clinical practice: Eastern and Western perspectives on current uses and challenges in hepatocellular carcinoma (HCC) screening/surveillance, diagnosis, and management • Economics and outcomes of HCC imaging • Radiomics, artificial intelligence (AI) and deep learning (DL) applications of MRI in HCC. These themes are the subject of the current manuscript. A second manuscript discusses multidisciplinary tumor board perspectives: how to approach early-, mid-, and late-stage HCC management from the perspectives of a liver surgeon, interventional radiologist, and oncologist (Taouli et al, 2023). Delegates voted on consensus statements that were developed by working groups on these meeting themes. A consensus was considered to be reached if at least 80% of the voting delegates agreed on the statements. CLINICAL RELEVANCE STATEMENT: This review highlights the clinical applications of gadoxetic acid-enhanced MRI for liver cancer screening and diagnosis, as well as its cost-effectiveness and the applications of radiomics and AI in patients with liver cancer. KEY POINTS: • Interpretation of gadoxetic acid-enhanced MRI differs slightly between Eastern and Western guidelines, reflecting different regional requirements for sensitivity vs specificity. • Emerging data are encouraging for the cost-effectiveness of gadoxetic acid-enhanced MRI in HCC screening and diagnosis, but more studies are required. • Radiomics and artificial intelligence are likely, in the future, to contribute to the detection, staging, assessment of treatment response and prediction of prognosis of HCC-reducing the burden on radiologists and other specialists and supporting timely and targeted treatment for patients.

Preoperative prediction of cholangiocyte phenotype hepatocellular carcinoma on contrast-enhanced MRI and the prognostic implication after hepatectomy

BACKGROUND

Hepatocellular carcinoma (HCC) expressing cytokeratin (CK) 7 or CK19 has a cholangiocyte phenotype that stimulates HCC proliferation, metastasis, and sorafenib therapy resistance This study aims to noninvasively predict cholangiocyte phenotype-positive HCC and assess its prognosis after hepatectomy.

METHODS

Between January 2010 and May 2022, preoperative contrast-enhanced MRI was performed on consecutive patients who underwent hepatectomy and had pathologically confirmed solitary HCC. Two abdominal radiologists separately assessed the MRI features. A predictive model for cholangiocyte phenotype HCC was created using logistic regression analysis and five-fold cross-validation. A receiver operating characteristic curve was used to calculate the model performance. Kaplan-Meier and log-rank methods were used to evaluate survival outcomes.

RESULTS

In total, 334 patients were included in this retrospective study. Four contrast-enhanced MRI features, including "rim arterial phase hyperenhancement" (OR = 5.9, 95% confidence interval [CI]: 2.9-12.0, 10 points), "nodule in nodule architecture" (OR = 3.5, 95% CI: 2.1-5.9, 7 points), "non-smooth tumor margin" (OR = 1.6, 95% CI: 0.8-2.9, 3 points), and "non-peripheral washout" (OR = 0.6, 95% CI: 0.3-1.0, - 3 points), were assigned to the cholangiocyte phenotype HCC prediction model. The area under the curves for the training and independent validation set were 0.76 and 0.73, respectively. Patients with model-predicted cholangiocyte phenotype HCC demonstrated lower rates of recurrence-free survival (RFS) and overall survival (OS) after hepatectomy, with an estimated median RFS and OS of 926 vs. 1565 days (p < 0.001) and 1504 vs. 2960 days (p < 0.001), respectively.

CONCLUSIONS

Contrast-enhanced MRI features can be used to predict cholangiocyte phenotype-positive HCC. Patients with pathologically confirmed or MRI model-predicted cholangiocyte phenotype HCC have a worse prognosis after hepatectomy.

CRITICAL RELEVANCE STATEMENT

Four contrast-enhanced MRI features were significantly associated with cholangiocyte phenotype HCC and a worse prognosis following hepatectomy; these features may assist in predicting prognosis after surgery and improve personalized treatment decision-making.

KEY POINTS

• Four contrast-enhanced MRI features were significantly associated with cholangiocyte phenotype HCC. • A noninvasive cholangiocyte phenotype HCC predictive model was established based on MRI features. • Patients with cholangiocyte phenotype HCC demonstrated a worse prognosis following hepatic resection.

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.

Artificial intelligence-based non-invasive tumor segmentation, grade stratification and prognosis prediction for clear-cell renal-cell carcinoma

Due to the complicated histopathological characteristics of clear-cell renal-cell carcinoma (ccRCC), non-invasive prognosis before operative treatment is crucial in selecting the appropriate treatment. A total of 126 345 computerized tomography (CT) images from four independent patient cohorts were included for analysis in this study. We propose a V Bottleneck multi-resolution and focus-organ network (VB-MrFo-Net) using a cascade framework for deep learning analysis. The VB-MrFo-Net achieved better performance than VB-Net in tumor segmentation, with a Dice score of 0.87. The nuclear-grade prediction model performed best in the logistic regression classifier, with area under curve values from 0.782 to 0.746. Survival analysis revealed that our prediction model could significantly distinguish patients with high survival risk, with a hazard ratio (HR) of 2.49 [95% confidence interval (CI): 1.13-5.45, P = 0.023] in the General cohort. Excellent performance had also been verified in the Cancer Genome Atlas cohort, the Clinical Proteomic Tumor Analysis Consortium cohort, and the Kidney Tumor Segmentation Challenge cohort, with HRs of 2.77 (95%CI: 1.58-4.84, P = 0.0019), 3.83 (95%CI: 1.22-11.96, P = 0.029), and 2.80 (95%CI: 1.05-7.47, P = 0.025), respectively. In conclusion, we propose a novel VB-MrFo-Net for the renal tumor segmentation and automatic diagnosis of ccRCC. The risk stratification model could accurately distinguish patients with high tumor grade and high survival risk based on non-invasive CT images before surgical treatments, which could provide practical advice for deciding treatment options.

Delta-radiomics models based on multi-phase contrast-enhanced magnetic resonance imaging can preoperatively predict glypican-3-positive hepatocellular carcinoma

Objectives: The aim of this study is to investigate the value of multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) based on the delta radiomics model for identifying glypican-3 (GPC3)-positive hepatocellular carcinoma (HCC). Methods: One hundred and twenty-six patients with pathologically confirmed HCC (training cohort: n = 88 and validation cohort: n = 38) were retrospectively recruited. Basic information was obtained from medical records. Preoperative multi-phase CE-MRI images were reviewed, and the 3D volumes of interest (VOIs) of the whole tumor were delineated on non-contrast T1-weighted imaging (T1), arterial phase (AP), portal venous phase (PVP), delayed phase (DP), and hepatobiliary phase (HBP). One hundred and seven original radiomics features were extracted from each phase, and delta-radiomics features were calculated. After a two-step feature selection strategy, radiomics models were built using two classification algorithms. A nomogram was constructed by combining the best radiomics model and clinical risk factors. Results: Serum alpha-fetoprotein (AFP) (p = 0.013) was significantly related to GPC3-positive HCC. The optimal radiomics model is composed of eight delta-radiomics features with the AUC of 0.805 and 0.857 in the training and validation cohorts, respectively. The nomogram integrated the radiomics score, and AFP performed excellently (training cohort: AUC = 0.844 and validation cohort: AUC = 0.862). The calibration curve showed good agreement between the nomogram-predicted probabilities and GPC3 actual expression in both training and validation cohorts. Decision curve analysis further demonstrates the clinical practicality of the nomogram. Conclusion: Multi-phase CE-MRI based on the delta-radiomics model can non-invasively predict GPC3-positive HCC and can be a useful method for individualized diagnosis and treatment.

Radiomics in the diagnosis and treatment of hepatocellular carcinoma

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

The added value of 18F-FDG PET/MRI multimodal imaging in hepatocellular carcinoma for identifying cytokeratin 19 status

PURPOSE

In hepatocellular carcinoma (HCC), cytokeratin 19(CK19) has been proven to be associated with clinical aggressiveness. Therefore, this study aimed to explore the added value of 18F-FDG PET/MRI in predicting CK19 status in HCC.

METHODS

Sixty-six patients who underwent whole-body or abdominal 18F-FDG PET/MRI after conventional PET/CT for HCC were retrospectively enrolled. The maximal standard uptake value (T-SUVmax) and the mean apparent diffusion coefficient (T-ADCmean) of the tumor (T), as well as those of the normal liver tissues (L) were derived, followed by calculations of the T-SUVmax/L-SUVmax (SUVmax-T/L) and the T-ADCmean/L-ADCmean (ADCmean-T/L) ratios. Combined with the postoperative pathological results, the performance in predicting the CK19 status in HCC was evaluated using receiver operating characteristic analysis (ROC).

RESULTS

The areas under the ROC curve (AUCs) for T-SUVmax, SUVmax-T/L, T-ADCmean, and ADCmean-T/L in predicting the CK19-positive HCC were 0.700, 0.717, 0.717, and 0.735, respectively. In the logistic regression analysis, the T-SUVmax was an independent and significant factor to predict CK19-positive HCC, with an odds ratio of 1.27. In addition, no significant differences were found in the pathological grading, microvascular invasion, liver capsular invasion, Hepatitis B virus (HBV) infection, alpha fetoprotein (AFP) level, and tumor diameter between the CK19-positive and CK19-negative groups, except the recurrent rate.

CONCLUSIONS

The radiomic features derived from 18F-FDG PET/MRI can be used to predict the CK19 status of HCC. T-SUVmax and T-ADCmean were significant indicators, whereas T-SUVmax was an independent predictor.

Three-dimensional multifrequency magnetic resonance elastography improves preoperative assessment of proliferative hepatocellular carcinoma

BACKGROUND

To investigate the viscoelastic signatures of proliferative hepatocellular carcinoma (HCC) using three-dimensional (3D) magnetic resonance elastography (MRE).

METHODS

This prospective study included 121 patients with 124 HCCs as training cohort, and validation cohort included 33 HCCs. They all underwent preoperative conventional magnetic resonance imaging (MRI) and tomoelastography based on 3D multifrequency MRE. Viscoelastic parameters of the tumor and liver were quantified as shear wave speed (c, m/s) and loss angle (φ, rad), representing stiffness and fluidity, respectively. Five MRI features were evaluated. Multivariate logistic regression analyses were used to determine predictors of proliferative HCC to construct corresponding nomograms.

RESULTS

In training cohort, model 1 (Combining cirrhosis, hepatitis virus, rim APHE, peritumoral enhancement, and tumor margin) yielded an area under the curve (AUC), sensitivity, specificity, accuracy of 0.72, 58.73%,78.69%, 67.74%, respectively. When adding MRE properties (tumor c and tumor φ), established model 2, the AUC increased to 0.81 (95% CI 0.72-0.87), with sensitivity, specificity, accuracy of 71.43%, 81.97%, 75%, respectively. The C-index of nomogram of model 2 was 0.81, showing good performance for proliferative HCC. Therefore, integrating tumor c and tumor φ can significantly improve the performance of preoperative diagnosis of proliferative HCC (AUC increased from 0.72 to 0.81, p = 0.012). The same finding was observed in the validation cohort, with AUC increasing from 0.62 to 0.77 (p = 0.021).

CONCLUSIONS

Proliferative HCC exhibits low stiffness and high fluidity. Adding MRE properties (tumor c and tumor φ) can improve performance of conventional MRI for preoperative diagnosis of proliferative HCC.

CRITICAL RELEVANCE STATEMENT

We investigated the viscoelastic signatures of proliferative hepatocellular carcinoma (HCC) using three-dimensional (3D) magnetic resonance elastography (MRE), and find that adding MRE properties (tumor c and tumor φ) can improve performance of conventional MRI for preoperative diagnosis of proliferative HCC.

Radiomics models based on multisequence MRI for predicting PD-1/PD-L1 expression in hepatocellular carcinoma

The purpose of this study was to explore the effectiveness of radiomics based on multisequence MRI in predicting the expression of PD-1/PD-L1 in hepatocellular carcinoma (HCC). One hundred and eight patients with HCC who underwent contrast-enhanced MRI 2 weeks before surgical resection were enrolled in this retrospective study. Corresponding paraffin sections were collected for immunohistochemistry to detect the expression of PD-1 and PD-L1. All patients were randomly divided into a training cohort and a validation cohort at a ratio of 7:3. Univariate and multivariate analyses were used to select potential clinical characteristics related to PD-1 and PD-L1 expression. Radiomics features were extracted from the axial fat-suppression T2-weighted imaging (FS-T2WI) images and the arterial phase and portal venous phase images from the axial dynamic contrast-enhanced MRI, and the corresponding feature sets were generated. The least absolute shrinkage and selection operator (LASSO) was used to select the optimal radiomics features for analysis. Logistic regression analysis was performed to construct single-sequence and multisequence radiomics and radiomic-clinical models. The predictive performance was judged by the area under the receiver operating characteristic curve (AUC) in the training and validation cohorts. In the whole cohort, PD-1 expression was positive in 43 patients, and PD-L1 expression was positive in 34 patients. The presence of satellite nodules served as an independent predictor of PD-L1 expression. The AUC values of the FS-T2WI, arterial phase, portal venous phase and multisequence models in predicting the expression of PD-1 were 0.696, 0.843, 0.863, and 0.946 in the training group and 0.669, 0.792, 0.800 and 0.815 in the validation group, respectively. The AUC values of the FS-T2WI, arterial phase, portal venous phase, multisequence and radiomic-clinical models in predicting PD-L1 expression were 0.731, 0.800, 0.800, 0.831 and 0.898 in the training group and 0.621, 0.743, 0.771, 0.810 and 0.779 in the validation group, respectively. The combined models showed better predictive performance. The results of this study suggest that a radiomics model based on multisequence MRI has the potential to predict the preoperative expression of PD-1 and PD-L1 in HCC, which could become an imaging biomarker for immune checkpoint inhibitor (ICI)-based treatment.

Gadoxetic Acid-Enhanced MRI-Based Radiomics Signature: A Potential Imaging Biomarker for Identifying Cytokeratin 19-Positive Hepatocellular Carcinoma

Purpose

One subtype of hepatocellular carcinoma (HCC), with cytokeratin 19 expression (CK19+), has shown to be more aggressive and has a poor prognosis. However, CK19+ is determined by immunohistochemical examination using a surgically resected specimen. This study is aimed at establishing a radiomics signature based on preoperative gadoxetic acid-enhanced MRI for predicting CK19 status in HCC. Patients and Methods. Clinicopathological and imaging data were retrospectively collected from patients who underwent hepatectomy between February 2015 and December 2020. Patients who underwent gadoxetic acid-enhanced MRI and had CK19 results of histopathological examination were included. Radiomics features of the manually segmented lesion during the arterial, portal venous, and hepatobiliary phases were extracted. The 10 most reproducible and robust features at each phase were selected for construction of radiomics signatures, and their performance was evaluated by analyzing the area under the curve (AUC). The goodness of fit of the model was assessed by the Hosmer-Lemeshow test.

Results

A total of 110 patients were included. The incidence of CK19(+) HCC was 17% (19/110). Alpha fetoprotein was the only significant clinicopathological variable different between CK19(-) and CK19(+) groups. A majority of the selected radiomics features were wavelet filter-derived features. The AUCs of the three radiomics signatures based on arterial, portal venous, and hepatobiliary phases were 0.70 (95% CI: 0.56-0.83), 0.83 (95% CI: 0.73-0.92), and 0.89 (95% CI: 0.82-0.96), respectively. The three radiomics signatures were integrated, and the fusion signature yielded an AUC of 0.92 (95% CI: 0.86-0.98) and was used as the final model for CK19(+) prediction. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the fusion signature was 0.84, 0.89, 0.88, 0.62, and 0.96, respectively. The Hosmer-Lemeshow test showed a good fit of the fusion signature (p > 0.05).

Conclusion

The established radiomics signature based on preoperative gadoxetic acid-enhanced MRI could be an accurate and potential imaging biomarker for HCC CK19(+) prediction.

A nomogram based on LI-RADS features, clinical indicators and quantitative contrast-enhanced MRI parameters for predicting glypican-3 expression in hepatocellular carcinoma

Purpose

Noninvasively assessing the tumor biology and microenvironment before treatment is greatly important, and glypican-3 (GPC-3) is a new-generation immunotherapy target for hepatocellular carcinoma (HCC). This study investigated the application value of a nomogram based on LI-RADS features, quantitative contrast-enhanced MRI parameters and clinical indicators in the noninvasive preoperative prediction of GPC-3 expression in HCC.

Methods and materials

We retrospectively reviewed 127 patients with pathologically confirmed solitary HCC who underwent Gd-EOB-DTPA MRI examinations and related laboratory tests. Quantitative contrast-enhanced MRI parameters and clinical indicators were collected by an abdominal radiologist, and LI-RADS features were independently assessed and recorded by three trained intermediate- and senior-level radiologists. The pathological and immunohistochemical results of HCC were determined by two senior pathologists. All patients were divided into a training cohort (88 cases) and validation cohort (39 cases). Univariate analysis and multivariate logistic regression were performed to identify independent predictors of GPC-3 expression in HCC, and a nomogram model was established in the training cohort. The performance of the nomogram was assessed by the area under the receiver operating characteristic curve (AUC) and the calibration curve in the training cohort and validation cohort, respectively.

Results

Blood products in mass, nodule-in-nodule architecture, mosaic architecture, contrast enhancement ratio (CER), transition phase lesion-liver parenchyma signal ratio (TP-LNR), and serum ferritin (Fer) were independent predictors of GPC-3 expression, with odds ratios (ORs) of 5.437, 10.682, 5.477, 11.788, 0.028, and 1.005, respectively. Nomogram based on LI-RADS features (blood products in mass, nodule-in-nodule architecture and mosaic architecture), quantitative contrast-enhanced MRI parameters (CER and TP-LNR) and clinical indicators (Fer) for predicting GPC-3 expression in HCC was established successfully. The nomogram showed good discrimination (AUC of 0.925 in the training cohort and 0.908 in the validation cohort) and favorable calibration. The diagnostic sensitivity and specificity were 76.9% and 92.3% in the training cohort, 76.8% and 93.8% in the validation cohort respectively.

Conclusion

The nomogram constructed from LI-RADS features, quantitative contrast-enhanced MRI parameters and clinical indicators has high application value, can accurately predict GPC-3 expression in HCC and may help noninvasively identify potential patients for GPC-3 immunotherapy.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review

Importance

Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.

Highlights

We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma.

Conclusion

AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

Preoperative identification of cytokeratin 19 status of hepatocellular carcinoma based on diffusion kurtosis imaging

PURPOSE

To explore the potential value of diffusion kurtosis imaging (DKI) for identification of cytokeratin 19 (CK19) status of HCCs.

METHODS

This study was approved by the local institute review board and written informed consent was obtained. 73 patients with pathologically confirmed HCCs were included in this prospective study. All the diffusion-weighted (DW) images were acquired using a 3.0-T MR scanner with 4 b-values (0, 800, 1500 and 2000 s/mm²). The mean diffusion value (MD) and mean kurtosis coefficient (MK) from DKI, apparent diffusion coefficient (ADC) from DW imaging (b = 0, 500 s/mm²), and tumor-to-liver signal intensity ratios on ADC map (SIR_ADC) and DW images with b-value of 500 s/mm² (SIR_b500) were calculated and compared between CK19-positive (n = 23) and CK19-negative (n = 50) HCC groups. Univariate and multivariate logistic regression analyses were used to identify risk factors for the positive expression of CK19.

RESULTS

Increased a-fetoprotein level (p = 0.021) and SIR_b500 (p = 0.006) and decreased ADC (p = 0.021) and MD (p < 0.001) were significantly correlated with CK19-positive HCCs at univariate analysis. Decreased MD value (odds ratio: 0.042, p = 0.002) and a-fetoprotein level (odds ratio: 5.139, p = 0.015) were the independent risk factors for CK19-positive HCCs at multivariate analysis. The area under the curve of MD value by receiver operating characteristic analysis was 0.823 with a sensitivity of 86.96% and a specificity of 76% for the prediction of CK19-positive HCCs.

CONCLUSION

The decreased MD value derived from DKI is potential quantitative biomarker for predicting CK19-positive HCCs.

Novel Computed-Tomography-Based Transformer Models for the Noninvasive Prediction of PD-1 in Pre-Operative Settings

The expression status of programmed cell death protein 1 (PD-1) in patients with hepatocellular carcinoma (HCC) is associated with the checkpoint blockade treatment responses of PD-1/PD-L1. Thus, accurately and preoperatively identifying the status of PD-1 has great clinical implications for constructing personalized treatment strategies. To investigate the preoperative predictive value of the transformer-based model for identifying the status of PD-1 expression, 93 HCC patients with 75 training cohorts (2859 images) and 18 testing cohorts (670 images) were included. We propose a transformer-based network architecture, ResTransNet, that efficiently employs convolutional neural networks (CNNs) and self-attention mechanisms to automatically acquire a persuasive feature to obtain a prediction score using a nonlinear classifier. The area under the curve, receiver operating characteristic curve, and decision curves were applied to evaluate the prediction model's performance. Then, Kaplan-Meier survival analyses were applied to evaluate the overall survival (OS) and recurrence-free survival (RFS) in PD-1-positive and PD-1-negative patients. The proposed transformer-based model obtained an accuracy of 88.2% with a sensitivity of 88.5%, a specificity of 88.9%, and an area under the curve of 91.1% in the testing cohort.

Preoperative prediction of cytokeratin-19 expression for hepatocellular carcinoma using T1 mapping on gadoxetic acid-enhanced MRI combined with diffusion-weighted imaging and clinical indicators

Objectives

To explore the value of T1 mapping on gadoxetic acid-enhanced magnetic resonance imaging (MRI) in preoperative predicting cytokeratin 19 (CK19) expression for hepatocellular carcinoma (HCC).

Methods

This retrospective study included 158 patients from two institutions with surgically resected treatment-native solitary HCC who underwent preoperative T1 mapping on gadoxetic acid-enhanced MRI. Patients from institution I (n = 102) and institution II (n = 56) were assigned to training and test sets, respectively. univariable and multivariable logistic regression analyses were performed to investigate the association of clinicoradiological variables with CK19. The receiver operating characteristic (ROC) curve and precision-recall (PR) curve were used to evaluate the performance for CK19 prediction. Then, a prediction nomogram was developed for CK19 expression. The performance of the prediction nomogram was evaluated by its discrimination, calibration, and clinical utility.

Results

Multivariable logistic regression analysis showed that AFP>400ng/ml (OR=4.607, 95%CI: 1.098-19.326; p=0.037), relative apparent diffusion coefficient (rADC)≤0.71 (OR=3.450, 95%CI: 1.126-10.567; p=0.030), T1 relaxation time in the 20-minute hepatobiliary phase (T1rt-HBP)>797msec (OR=4.509, 95%CI: 1.301-15.626; p=0.018) were significant independent predictors of CK19 expression. The clinical-quantitative model (CQ-Model) constructed based on these significant variables had the best predictive performance with an area under the ROC curve of 0.844, an area under the PR curve of 0.785 and an F1 score of 0.778. The nomogram constructed based on CQ-Model demonstrated satisfactory performance with C index of 0.844 (95%CI: 0.759-0.908) and 0.818 (95%CI: 0.693-0.902) in the training and test sets, respectively.

Conclusions

T1 mapping on gadoxetic acid-enhanced MRI has good predictive efficacy for preoperative prediction of CK19 expression in HCC, which can promote the individualized risk stratification and further treatment decision of HCC patients.

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

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

CT-based radiomics nomogram for differentiation of adrenal hyperplasia from lipid-poor adenoma: an exploratory study

BACKGROUND

To establish and verify a radiomics nomogram for differentiating isolated micronodular adrenal hyperplasia (iMAD) from lipid-poor adenoma (LPA) based on computed tomography (CT)-extracted radiomic features.

METHODS

A total of 148 patients with iMAD or LPA were divided into three cohorts: a training cohort (n = 72; 37 iMAD and 35 LPA), a validation cohort (n = 36; 22 iMAD and 14 LPA), and an external validation cohort (n = 40; 20 iMAD and 20 LPA). Radiomics features were extracted from contrast-enhanced and non-contrast CT images. The least absolute shrinkage and selection operator (LASSO) method was applied to develop a triphasic radiomics model and unenhanced radiomics model using reproducible radiomics features. A clinical model was constructed using certain laboratory variables and CT findings. Radiomics nomogram was established by selected radiomics signature and clinical factors. Nomogram performance was assessed by calibration curve, the areas under receiver operating characteristic curves (AUC), and decision curve analysis (DCA).

RESULTS

Eleven and eight extracted features were finally selected to construct an unenhanced radiomics model and a triphasic radiomics model, respectively. There was no significant difference in AUC between the two models in the external validation cohort (0.838 vs. 0.843, p = 0.949). The radiomics nomogram inclusive of the unenhanced model, maximum diameter, and aldosterone showed the AUC of 0.951, 0.938, and 0.893 for the training, validation, and external validation cohorts, respectively. The nomogram showed good calibration, and the DCA demonstrated the superiority of the nomogram compared with the clinical factors model alone in terms of clinical usefulness.

CONCLUSIONS

A radiomics nomogram based on unenhanced CT images and clinical variables showed favorable performance for distinguishing iMAD from LPA. In addition, an efficient unenhanced model can help avoid extra contrast-enhanced scanning and radiation risk.

A radiomics nomogram for predicting cytokeratin 19-positive hepatocellular carcinoma: a two-center study

Objectives

We aimed to construct and validate a radiomics-based nomogram model derived from gadoxetic acid-enhanced magnetic resonance (MR) images to predict cytokeratin (CK) 19-positive (+) hepatocellular carcinoma (HCC) and patients' prognosis.

Methods

A two-center and time-independent cohort of 311 patients were retrospectively enrolled (training cohort, n = 168; internal validation cohort, n = 72; external validation cohort, n = 71). A total of 2286 radiomic features were extracted from multisequence MR images with the uAI Research Portal (uRP), and a radiomic feature model was established. A combined model was established by incorporating the clinic-radiological features and the fusion radiomics signature using logistic regression analysis. Receiver operating characteristic curve (ROC) was used to evaluate the predictive efficacy of these models. Kaplan-Meier survival analysis was used to assess 1-year and 2-year progression-free survival (PFS) and overall survival (OS) in the cohort.

Results

By combining radiomic features extracted in DWI phase, arterial phase, venous and delay phase, the fusion radiomics signature achieved AUCs of 0.865, 0.824, and 0.781 in the training, internal, and external validation cohorts. The final combined clinic-radiological model showed higher AUC values in the three datasets compared with the fusion radiomics model. The nomogram based on the combined model showed satisfactory prediction performance in the training (C-index, 0.914), internal (C-index, 0.855), and external validation (C-index, 0.795) cohort. The 1-year and 2-year PFS and OS of the patients in the CK19+ group were 76% and 73%, and 78% and 68%, respectively. The 1-year and 2-year PFS and OS of the patients in the CK19-negative (-) group were 81% and 77%, and 80% and 74%, respectively. Kaplan-Meier survival analysis showed no significant differences in 1-year PFS and OS between the groups (P = 0.273 and 0.290), but it did show differences in 2-year PFS and OS between the groups (P = 0.032 and 0.040). Both PFS and OS were lower in CK19+ patients.

Conclusion

The combined model based on clinic-radiological radiomics features can be used for predicting CK19+ HCC noninvasively to assist in the development of personalized treatment.

Prediction for Aggressiveness and Postoperative Recurrence of Hepatocellular Carcinoma Using Gadoxetic Acid-Enhanced Magnetic Resonance Imaging

RATIONALE AND OBJECTIVES

To investigate the predictive value of gadoxetic acid-enhanced magnetic resonance imaging (MRI) features on the pathologic grade, microvascular invasion (MVI), and cytokeratin-19 (CK19) expression in hepatocellular carcinomas (HCC), and to evaluate their association with postoperative recurrence of HCC.

MATERIALS AND METHODS

This retrospective study included 147 patients with surgically confirmed HCCs who underwent gadoxetic-enhanced MRI. The lesions were evaluated quantitatively in terms of the relative enhancement ratio (RER), and qualitatively based on imaging features and clinical parameters. Logistic regression analyses were performed to investigate the value of these parameters in predicting the pathologic grade, MVI, and CK19 in HCC. Predictive factors for postoperative recurrence were determined using a Cox proportional hazards model.

RESULTS

Peritumoral enhancement (odds ratio [OR], 3.396; p = 0.025) was an independent predictor of high pathologic grades. Serum protein induced by vitamin K absence or antagonist (PIVKA) level > 40 mAU/mL (OR, 3.763; p = 0.018) and peritumoral hypointensity (OR, 4.343; p = 0.003) were independent predictors of MVI. Predictors of CK19 included serum alpha-fetoprotein (AFP) level > 400 ng/mL (OR, 4.576; p = 0.005), rim enhancement (OR, 5.493; p = 0.024), and lower RER (OR, 0.013; p = 0.011). Peritumoral hypointensity (hazard ratio [HR], 1.957; p = 0.027) and poor pathologic grades (HR, 2.339; p = 0.043) were independent predictors of recurrence.

CONCLUSION

We demonstrated the value of preoperative gadoxetic-enhanced MRI in predicting aggressive pathological features of HCC. Poor pathologic grades and peritumoral hypointensity may independently predict the recurrence of HCC.

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

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

Accurate prediction of microvascular invasion occurrence and effective prognostic estimation for patients with hepatocellular carcinoma after radical surgical treatment

Background

Hepatocellular carcinoma (HCC) is the third most common cause of cancer death worldwide, with an overall 5-year survival rate of less than 18%, which may be related to tumor microvascular invasion (MVI). This study aimed to compare the clinical prognosis of HCC patients with or without MVI after radical surgical treatment, and further analyze the preoperative risk factors related to MVI to promote the development of a new treatment strategy for HCC.

Methods

According to the postoperative pathological diagnosis of MVI, 160 study patients undergoing radical hepatectomy were divided into an MVI-negative group (n = 68) and an MVI-positive group (n = 92). The clinical outcomes and prognosis were compared between the two groups, and then the parameters were analyzed by multivariate logistic regression to construct an MVI prediction model. Then, the practicability and validity of the model were evaluated, and the clinical prognosis of different MVI risk groups was subsequently compared.

Result

There were no significant differences between the MVI-negative and MVI-positive groups in clinical baseline, hematological, or imaging data. Additionally, the clinical outcome comparison between the two groups presented no significant differences except for the pathological grading (P = 0.002) and survival and recurrence rates after surgery (P < 0.001). The MVI prediction model, based on preoperative AFP, tumor diameter, and TNM stage, presented superior predictive efficacy (AUC = 0.7997) and good practicability (high H-L goodness of fit, P = 0.231). Compared with the MVI high-risk group, the patients in the MVI low-risk group had a higher survival rate (P = 0.002) and a lower recurrence rate (P = 0.004).

Conclusion

MVI is an independent risk factor for a poor prognosis after radical resection of HCC. The MVI prediction model, consisting of AFP, tumor diameter, and TNM stage, exhibits superior predictive efficacy and strong clinical practicability for MVI prediction and prognostication, which provides a new therapeutic strategy for the standardized treatment of HCC patients.

Preoperative radiomics model using gadobenate dimeglumine-enhanced magnetic resonance imaging for predicting β-catenin mutation in patients with hepatocellular carcinoma: A retrospective study

Objective

To compare and evaluate radiomics models to preoperatively predict β-catenin mutation in patients with hepatocellular carcinoma (HCC).

Methods

Ninety-eight patients who underwent preoperative gadobenate dimeglumine (Gd-BOPTA)-enhanced MRI were retrospectively included. Volumes of interest were manually delineated on arterial phase, portal venous phase, delay phase, and hepatobiliary phase (HBP) images. Radiomics features extracted from different combinations of imaging phases were analyzed and validated. A linear support vector classifier was applied to develop different models.

Results

Among all 15 types of radiomics models, the model with the best performance was seen in the R^HBP radiomics model. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity of the R^HBP radiomics model in the training and validation cohorts were 0.86 (95% confidence interval [CI], 0.75–0.93), 0.75, 1.0, and 0.65 and 0.82 (95% CI, 0.63–0.93), 0.73, 0.67, and 0.76, respectively. The combined model integrated radiomics features in the R^HBP radiomics model, and signatures in the clinical model did not improve further compared to the single HBP radiomics model with AUCs of 0.86 and 0.76. Good calibration for the best R^HBP radiomics model was displayed in both cohorts; the decision curve showed that the net benefit could achieve 0.15. The most important radiomics features were low and high gray-level zone emphases based on gray-level size zone matrix with the same Shapley additive explanation values of 0.424.

Conclusion

The R^HBP radiomics model may be used as an effective model indicative of HCCs with β-catenin mutation preoperatively and thus could guide personalized medicine.

Ultrasomics prediction for cytokeratin 19 expression in hepatocellular carcinoma: A multicenter study

Objective

The purpose of this study was to investigate the preoperative prediction of Cytokeratin (CK) 19 expression in patients with hepatocellular carcinoma (HCC) by machine learning-based ultrasomics.

Methods

We retrospectively analyzed 214 patients with pathologically confirmed HCC who received CK19 immunohistochemical staining. Through random stratified sampling (ratio, 8:2), patients from institutions I and II were divided into training dataset (n = 143) and test dataset (n = 36), and patients from institution III served as external validation dataset (n = 35). All gray-scale ultrasound images were preprocessed, and then the regions of interest were then manually segmented by two sonographers. A total of 1409 ultrasomics features were extracted from the original and derived images. Next, the intraclass correlation coefficient, variance threshold, mutual information, and embedded method were applied to feature dimension reduction. Finally, the clinical model, ultrasonics model, and combined model were constructed by eXtreme Gradient Boosting algorithm. Model performance was assessed by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.

Results

A total of 12 ultrasomics signatures were used to construct the ultrasomics models. In addition, 21 clinical features were used to construct the clinical model, including gender, age, Child-Pugh classification, hepatitis B surface antigen/hepatitis C virus antibody (positive/negative), cirrhosis (yes/no), splenomegaly (yes/no), tumor location, tumor maximum diameter, tumor number, alpha-fetoprotein, alanine aminotransferase, aspartate aminotransferase, alkaline phosphatase, glutamyl-transpeptidase, albumin, total bilirubin, conjugated bilirubin, creatinine, prothrombin time, fibrinogen, and international normalized ratio. The AUC of the ultrasomics model was 0.789 (0.621 – 0.907) and 0.787 (0.616 – 0.907) in the test and validation datasets, respectively. However, the performance of the combined model covering clinical features and ultrasomics signatures improved significantly. Additionally, the AUC (95% CI), sensitivity, specificity, and accuracy were 0.867 (0.712 – 0.957), 0.750, 0.875, 0.861, and 0.862 (0.703 – 0.955), 0.833, 0.862, and 0.857 in the test dataset and external validation dataset, respectively.

Conclusion

Ultrasomics signatures could be used to predict the expression of CK19 in HCC patients. The combination of clinical features and ultrasomics signatures showed excellent effects, which significantly improved prediction accuracy and robustness.

Individual and joint influence of cytokeratin 19 and microvascular invasion on the prognosis of patients with hepatocellular carcinoma after hepatectomy

BACKGROUND AND OBJECTIVES

To evaluate the individual and combined associations of cytokeratin 19 (CK19) and microvascular invasion (MVI) with prognosis of patients with hepatocellular carcinoma (HCC).

METHODS

Clinicopathological data on 352 patients with HCC who underwent radical resection at our hospital between January 2013 and December 2015 were retrospectively analyzed. Patients were divided into four groups: CK19(-)/MVI(-), CK19(-)/MVI(+), CK19(+)/MVI(-), and CK19(+)/MVI(+).

RESULTS

Of the 352 HCC patients, 154 (43.8%) were CK19(-)/MVI(-); 116 (33.0%), CK19(-)/MVI(+); 31 (8.8%), CK19(+)/MVI(-); and 51 (14.5%), CK19(+)/MVI(+). The disease-free survival of CK19(-)/MVI(-) patients was significantly higher than that of CK19(-)/MVI(+) patients and CK19(+)/MVI(+) patients. Similar results were observed for overall survival. CK19(+)/MVI(+) patients showed significantly lower overall survival than the other three groups.

CONCLUSIONS

CK19 expression and MVI predict poor prognosis after radical resection of HCC, and the two markers jointly contribute to poor OS. Combining CK19 and MVI may predict post-resection prognosis better than using either factor on its own.

A Potential Prognostic Marker for Recognizing VEGF-Positive Hepatocellular Carcinoma Based on Magnetic Resonance Radiomics Signature

Objectives

The objective of our project is to explore a noninvasive radiomics model based on magnetic resonance imaging (MRI) that could recognize the expression of vascular endothelial growth factor (VEGF) in hepatocellular carcinoma before operation.

Methods

202 patients with proven single HCC were enlisted and stochastically distributed into a training set (n = 142) and a test set (n = 60). Arterial phase, portal venous phase, balanced phase, delayed phase, and hepatobiliary phase images were used to radiomics features extraction. We retrieved 1906 radiomic features from each phase of every participant’s MRI images. The F-test was applied to choose the crucial features. A logistic regression model was adopted to generate a radiomics signature. By combining independent risk indicators from the fusion radiomics signature and clinico-radiological features, we developed a multivariable logistic regression model that could predict the VEGF status preoperatively through calculating the area under the curve (AUC).

Results

The entire group comprised 108 VEGF-positive individuals and 94 VEGF-negative patients. AUCs of 0.892 (95% confidence interval [CI]: 0.839 - 0.945) in the training dataset and 0.800 (95% CI: 0.682 - 0.918) in the test dataset were achieved by utilizing radiomics features from two phase images (8 features from the portal venous phase and 5 features from the hepatobiliary phase). Furthermore, the nomogram relying on a combined model that included the clinical factors α-fetoprotein (AFP), irregular tumor margin, and the fusion radiomics signature performed well in both the training (AUC = 0.936, 95% CI: 0.898-0.974) and test (AUC = 0.836, 95% CI: 0.728-0.944) datasets.

Conclusions

The combined model acquired from two phase (portal venous and hepatobiliary phase) pictures of gadolinium-ethoxybenzyl-diethylenetriamine-pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI could be considered as a credible prognostic marker for the level of VEGF in HCC.

Radiomics signature: A potential biomarker for β-arrestin1 phosphorylation prediction in hepatocellular carcinoma

BACKGROUND

The phosphorylation status of β-arrestin1 influences its function as a signal strongly related to sorafenib resistance. This retrospective study aimed to develop and validate radiomics-based models for predicting β-arrestin1 phosphorylation in hepatocellular carcinoma (HCC) using whole-lesion radiomics and visual imaging features on preoperative contrast-enhanced computed tomography (CT) images.

AIM

To develop and validate radiomics-based models for predicting β-arrestin1 phosphorylation in HCC using radiomics with contrast-enhanced CT.

METHODS

Ninety-nine HCC patients (training cohort: n = 69; validation cohort: n = 30) receiving systemic sorafenib treatment after surgery were enrolled in this retrospective study. Three-dimensional whole-lesion regions of interest were manually delineated along the tumor margins on portal venous CT images. Radiomics features were generated and selected to build a radiomics score using logistic regression analysis. Imaging features were evaluated by two radiologists independently. All these features were combined to establish clinico-radiological (CR) and clinico-radiological-radiomics (CRR) models by using multivariable logistic regression analysis. The diagnostic performance and clinical usefulness of the models were measured by receiver operating characteristic and decision curves, and the area under the curve (AUC) was determined. Their association with prognosis was evaluated using the Kaplan-Meier method.

RESULTS

Four radiomics features were selected to construct the radiomics score. In the multivariate analysis, alanine aminotransferase level, tumor size and tumor margin on portal venous phase images were found to be significant independent factors for predicting β-arrestin1 phosphorylation-positive HCC and were included in the CR model. The CRR model integrating the radiomics score with clinico-radiological risk factors showed better discriminative performance (AUC = 0.898, 95%CI, 0.820 to 0.977) than the CR model (AUC = 0.794, 95%CI, 0.686 to 0.901; P = 0.011), with increased clinical usefulness confirmed in both the training and validation cohorts using decision curve analysis. The risk of β-arrestin1 phosphorylation predicted by the CRR model was significantly associated with overall survival in the training and validation cohorts (log-rank test, P < 0.05).

CONCLUSION

The radiomics signature is a reliable tool for evaluating β-arrestin1 phosphorylation which has prognostic significance for HCC patients, providing the potential to better identify patients who would benefit from sorafenib treatment.

Multi-phase contrast-enhanced magnetic resonance image-based radiomics-combined machine learning reveals microscopic ultra-early hepatocellular carcinoma lesions

Purpose

This study aimed to investigate whether models built from radiomics features based on multiphase contrast-enhanced MRI can identify microscopic pre-hepatocellular carcinoma lesions.

Methods

We retrospectively studied 54 small hepatocellular carcinoma (SHCC, diameter < 2 cm) patients and 70 patients with hepatocellular cysts or haemangiomas from September 2018 to June 2021. For the former, two MRI scans were collected within 12 months of each other; the 2^nd scan was used to confirm the diagnosis. The volumes of interest (VOIs), including SHCCs and normal liver tissues, were delineated on the 2^nd scans, mapped to the 1^st scans via image registration, and enrolled into the SHCC and internal-control cohorts, respectively, while those of normal liver tissues from patients with hepatocellular cysts or haemangioma were enrolled in the external-control cohort. We extracted 1132 radiomics features from each VOI and analysed their discriminability between the SHCC and internal-control cohorts for intra-group classification and the SHCC and external-control cohorts for inter-group classification. Five radial basis-function, kernel-based support vector machine (SVM) models (four corresponding single-phase models and one integrated from the four-phase MR images) were established.

Results

Among the 124 subjects, the multiphase models yielded better performance on the testing set for intra-group and inter-group classification, with areas under the receiver operating characteristic curves of 0.93 (95% CI, 0.85–1.00) and 0.97 (95% CI, 0.92–1.00), accuracies of 86.67% and 94.12%, sensitivities of 87.50% and 94.12%, and specificities of 85.71% and 94.12%, respectively.

Conclusion

The combined multiphase MRI-based radiomics feature model revealed microscopic pre-hepatocellular carcinoma lesions.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-022-05742-8.

Positron Emission Tomography/Magnetic Resonance Imaging Radiomics in Predicting Lung Adenocarcinoma and Squamous Cell Carcinoma

Objective

To investigate the diagnostic value of positron emission tomography (PET)/magnetic resonance imaging (MRI) radiomics in predicting the histological classification of lung adenocarcinoma and lung squamous cell carcinoma.

Methods

PET/MRI radiomics and clinical data were retrospectively collected from 61 patients with lung cancer. According to the pathological results of surgery or fiberscope, patients were divided into two groups, lung adenocarcinoma and squamous cell carcinoma group, which were set as positive for adenocarcinoma (40 cases) and negative for squamous cell carcinoma (21 cases). The radiomics characteristics most related to lung cancer classification were calculated and selected using radiomics software, and the two lung cancer groups were randomly assigned into a training set (70%) and a test set (30%). Maximum relevance and minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) methods in the uAI Research Portal software (United Imaging Intelligence, China) were used to select the desired characteristics from 2600 features extracted from MRI and PET. Eight optimal features were finally retained through 5-fold cross-validation, and a PET/MRI fusion model was constructed. The predictive ability of this model was evaluated by the difference in area under the curve (AUC) obtained from the receiver operating characteristic (ROC) curve.

Results

AUC of PET/MRI model for the training group and test group were 0.886 (0.787-0.985) and 0.847 (0.648-1.000), respectively. PET/MRI radiomics features revealed different degrees of correlation with the classification of lung adenocarcinoma and squamous cell carcinoma, with significant differences.

Conclusion

The prediction model constructed based on PET/MRI radiomics features can predict the preoperative histological classification of lung adenocarcinoma and squamous cell carcinoma without seminality and repeatability. It can also provide an objective basis for accurate clinical diagnosis and individualized treatment, thus having important guiding significance for clinical treatment.

AI in spotting high-risk characteristics of medical imaging and molecular pathology

Medical imaging provides a comprehensive perspective and rich information for disease diagnosis. Combined with artificial intelligence technology, medical imaging can be further mined for detailed pathological information. Many studies have shown that the macroscopic imaging characteristics of tumors are closely related to microscopic gene, protein and molecular changes. In order to explore the function of artificial intelligence algorithms in in-depth analysis of medical imaging information, this paper reviews the articles published in recent years from three perspectives: medical imaging analysis method, clinical applications and the development of medical imaging in the direction of pathological molecular prediction. We believe that AI-aided medical imaging analysis will be extensively contributing to precise and efficient clinical decision.