Predicting the Initial Treatment Response to Transarterial Chemoembolization in Intermediate-Stage Hepatocellular Carcinoma by the Integration of Radiomics and Deep Learning

Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma

Objectives

Combination therapy of lenvatinib and immune checkpoint inhibitors (CLICI) has emerged as a promising approach for managing unresectable hepatocellular carcinoma (HCC). However, the response to such treatment is observed in only a subset of patients, underscoring the pressing need for reliable methods to identify potential responders.

Materials & methods

This was a retrospective analysis involving 120 patients with unresectable HCC. They were divided into training (n = 72) and validation (n = 48) cohorts. We developed an interpretable deep learning model using multiphase computed tomography (CT) images to predict whether patients will respond or not to CLICI treatment, based on the Response Evaluation Criteria in Solid Tumors, version 1.1 (RECIST v1.1). We evaluated the models' performance and analyzed the impact of each CT phase. Critical regions influencing predictions were identified and visualized through heatmaps.

Results

The multiphase model outperformed the best biphase and uniphase models, achieving an area under the curve (AUC) of 0.802 (95% CI = 0.780-0.824). The portal phase images were found to significantly enhance the model's predictive accuracy. Heatmaps identified six critical features influencing treatment response, offering valuable insights to clinicians. Additionally, we have made this model accessible via a web server at http://uhccnet.com/ for ease of use.

Conclusions

The integration of multiphase CT images with deep learning-generated heatmaps for predicting treatment response provides a robust and practical tool for guiding CLICI therapy in patients with unresectable HCC.

Deep learning to estimate response of concurrent chemoradiotherapy in non-small-cell lung carcinoma

BACKGROUND

Concurrent chemoradiotherapy (CCRT) is a crucial treatment for non-small cell lung carcinoma (NSCLC). However, the use of deep learning (DL) models for predicting the response to CCRT in NSCLC remains unexplored. Therefore, we constructed a DL model for estimating the response to CCRT in NSCLC and explored the associated biological signaling pathways.

METHODS

Overall, 229 patients with NSCLC were recruited from six hospitals. Based on contrast-enhanced computed tomography (CT) images, a three-dimensional ResNet50 algorithm was used to develop a model and validate the performance in predicting response and prognosis. An associated analysis was conducted on CT image visualization, RNA sequencing, and single-cell sequencing.

RESULTS

The DL model exhibited favorable predictive performance, with an area under the curve of 0.86 (95% confidence interval [CI] 0.79-0·92) in the training cohort and 0.84 (95% CI 0.75-0.94) in the validation cohort. The DL model (low score vs. high score) was an independent predictive factor; it was significantly associated with progression-free survival and overall survival in both the training (hazard ratio [HR] = 0.54 [0.36-0.80], P = 0.002; 0.44 [0.28-0.68], P < 0.001) and validation cohorts (HR = 0.46 [0.24-0.88], P = 0.008; 0.30 [0.14-0.60], P < 0.001). The DL model was also positively related to the cell adhesion molecules, the P53 signaling pathway, and natural killer cell-mediated cytotoxicity. Single-cell analysis revealed that differentially expressed genes were enriched in different immune cells.

CONCLUSION

The DL model demonstrated a strong predictive ability for determining the response in patients with NSCLC undergoing CCRT. Our findings contribute to understanding the potential biological mechanisms underlying treatment responses in these patients.

Research progress on machine algorithm prediction of liver cancer prognosis after intervention therapy

The treatment for liver cancer has transitioned from traditional surgical resection to interventional therapies, which have become increasingly popular among patients due to their minimally invasive nature and significant local efficacy. However, with advancements in treatment technologies, accurately assessing patient response and predicting long-term survival has become a crucial research topic. Over the past decade, machine algorithms have made remarkable progress in the medical field, particularly in hepatology and prognosis studies of hepatocellular carcinoma (HCC). Machine algorithms, including deep learning and machine learning, can identify prognostic patterns and trends by analyzing vast amounts of clinical data. Despite significant advancements, several issues remain unresolved in the prognosis prediction of liver cancer using machine algorithms. Key challenges and main controversies include effectively integrating multi-source clinical data to improve prediction accuracy, addressing data privacy and ethical concerns, and enhancing the transparency and interpretability of machine algorithm decision-making processes. This paper aims to systematically review and analyze the current applications and potential of machine algorithms in predicting the prognosis of patients undergoing interventional therapy for liver cancer, providing theoretical and empirical support for future research and clinical practice.

Artificial intelligence techniques in liver cancer

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

Radiomics as a tool for prognostic prediction in transarterial chemoembolization for hepatocellular carcinoma: a systematic review and meta-analysis

INTRODUCTION

Transarterial chemoembolization (TACE) is one of the predominant locoregional therapeutic modalities for addressing hepatocellular carcinoma (HCC). However, achieving precise prognostic predictions and effective patient selection remains a challenging pursuit. The primary objective of this systematic review and meta-analysis is to evaluate the efficacy of radiomics in forecasting the prognosis associated with TACE treatment.

METHODS

A comprehensive exploration of pertinent original studies was undertaken, encompassing databases of PubMed, Web of Science and Embase. The studies' quality was meticulously evaluated employing the quality assessment of diagnostic accuracy studies 2 (QUADAS-2), the radiomics quality score (RQS) and the METhodological RadiomICs Score (METRICS). Pooled statistics, along with 95% confidence intervals (95% CI), were computed for sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR). Additionally, a summary receiver operating characteristic curve (sROC) was generated. To discern potential sources of heterogeneity, meta-regression and subgroup analyses were performed.

RESULTS

The systematic review incorporated 29 studies, comprising a total of 5483 patients, with 14 studies involving 2691 patients qualifying for inclusion in the meta-analysis. The assessed studies exhibited commendable quality with regard to bias risk, with mean RQS of 12.90 ± 5.13 (35.82% ± 14.25%) and mean METRICS of 62.98% ± 14.58%. The pooled sensitivity was 0.83 (95% CI: 0.78-0.87), specificity was 0.86 (95% CI: 0.79-0.92), PLR was 6.13 (95% CI: 3.79-9.90), and NLR was 0.20 (95% CI: 0.15-0.27). The area under the sROC was 0.90 (95% CI: 0.87-0.93). Significant heterogeneity within all the included studies was observed, while meta-regression and subgroup analyses revealed homogeneous and promising findings in subgroups where principal methodological variables such as modeling algorithms, imaging modalities, and imaging phases were specified.

CONCLUSION

Radiomics models have exhibited robust predictive capabilities concerning prognosis subsequent to TACE, thereby presenting promising prospects for clinical translation.

Sub-regional CT Radiomics for the Prediction of Ki-67 Proliferation Index in Gastrointestinal Stromal Tumors: A Multi-center Study

RATIONALE AND OBJECTIVES

The objective was to assess and examine radiomics models derived from contrast-enhanced CT for their predictive capacity using the sub-regional radiomics regarding the Ki-67 proliferation index (PI) in patients with pathologically confirmed gastrointestinal stromal tumors (GIST).

METHODS

In this retrospective study, a total of 412 GIST patients across three institutions (223 from center 1, 106 from center 2, and 83 from center 3) was enrolled. Radiomic features were derived from various sub-regions of the tumor region of interest employing the K-means approach. The Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to identify features correlated with Ki-67 PI level in GIST patients. A support vector machine (SVM) model was then constructed to predict the high level of Ki-67 (Ki-67 index >8%), drawing on the radiomics features from each sub-region within the training cohort.

RESULTS

After features selection process, 6, 9, 9, 7 features were obtained to construct SVM models based on sub-region 1, 2, 3 and the entire tumor, respectively. Among different models, the model developed by the sub-region 1 achieved an area under the receiver operating characteristic curve (AUC) of 0.880 (95% confidence interval [CI]: 0.830 to 0.919), 0.852 (95% CI: 0.770-0.914), 0.799 (95% CI: 0.697-0.879) in the training, external test set 1, and 2, respectively.

CONCLUSION

The results of the present study suggested that SVM model based on the sub-regional radiomics features had the potential of predicting Ki-67 PI level in patients with GIST.

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

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

Ethiodized oil as an imaging biomarker after conventional transarterial chemoembolization

Conventional transarterial chemoembolization (cTACE) utilizing ethiodized oil as a chemotherapy carrier has become a standard treatment for intermediate-stage hepatocellular carcinoma (HCC) and has been adopted as a bridging and downstaging therapy for liver transplantation. Water-in-oil emulsion made up of ethiodized oil and chemotherapy solution is retained in tumor vasculature resulting in high tissue drug concentration and low systemic chemotherapy doses. The density and distribution pattern of ethiodized oil within the tumor on post-treatment imaging are predictive of the extent of tumor necrosis and duration of response to treatment. This review describes the multiple roles of ethiodized oil, particularly in its role as a biomarker of tumor response to cTACE. CLINICAL RELEVANCE: With the increasing complexity of locoregional therapy options, including the use of combination therapies, treatment response assessment has become challenging; Ethiodized oil deposition patterns can serve as an imaging biomarker for the prediction of treatment response, and perhaps predict post-treatment prognosis. KEY POINTS: • Treatment response assessment after locoregional therapy to hepatocellular carcinoma is fraught with multiple challenges given the varied post-treatment imaging appearance. • Ethiodized oil is unique in that its' radiopacity can serve as an imaging biomarker to help predict treatment response. • The pattern of deposition of ethiodozed oil has served as a mechanism to detect portions of tumor that are undertreated and can serve as an adjunct to enhancement in order to improve management in patients treated with intraarterial embolization with ethiodized oil.

A novel sub-regional radiomics model to predict immunotherapy response in non-small cell lung carcinoma

BACKGROUND

Identifying precise biomarkers of immunotherapy response for non-small cell lung carcinoma (NSCLC) before treatment is challenging. This study aimed to construct and investigate the potential performance of a sub-regional radiomics model (SRRM) as a novel tumor biomarker in predicting the response of patients with NSCLC treated with immune checkpoint inhibitors, and test whether its predictive performance is superior to that of conventional radiomics, tumor mutational burden (TMB) score and programmed death ligand-1 (PD-L1) expression.

METHODS

We categorized 264 patients from retrospective databases of two centers into training (n = 159) and validation (n = 105) cohorts. Radiomic features were extracted from three sub-regions of the tumor region of interest using the K-means method. We extracted 1,896 features from each sub-region, resulting in 5688 features per sample. The least absolute shrinkage and selection operator regression method was used to select sub-regional radiomic features. The SRRM was constructed and validated using the support vector machine algorithm. We used next-generation sequencing to classify patients from the two cohorts into high TMB (≥ 10 muts/Mb) and low TMB (< 10 muts/Mb) groups; immunohistochemistry was performed to assess PD-L1 expression in formalin-fixed, paraffin-embedded tumor sections, with high expression defined as ≥ 50% of tumor cells being positive. Associations between the SRRM and progression-free survival (PFS) and variant genes were assessed.

RESULTS

Eleven sub-regional radiomic features were employed to develop the SRRM. The areas under the receiver operating characteristic curve (AUCs) of the proposed SRRM were 0.90 (95% confidence interval [CI] 0.84-0.96) and 0.86 (95% CI 0.76-0.95) in the training and validation cohorts, respectively. The SRRM (low vs. high; cutoff value = 0.936) was significantly associated with PFS in the training (hazard ratio [HR] = 0.35 [0.24-0.50], P < 0.001) and validation (HR = 0.42 [0.26-0.67], P = 0.001) cohorts. A significant correlation between the SRRM and three variant genes (H3C4, PAX5, and EGFR) was observed. In the validation cohort, the SRRM demonstrated a higher AUC (0.86, P < 0.001) than that for PD-L1 expression (0.66, P = 0.034) and TMB score (0.54, P = 0.552).

CONCLUSIONS

The SRRM had better predictive performance and was superior to conventional radiomics, PD-L1 expression, and TMB score. The SRRM effectively stratified the progression-free survival (PFS) risk among patients with NSCLC receiving immunotherapy.

Machine Learning Combined with Radiomics Facilitating the Personal Treatment of Malignant Liver Tumors

In the realm of managing malignant liver tumors, the convergence of radiomics and machine learning has redefined the landscape of medical practice. The field of radiomics employs advanced algorithms to extract thousands of quantitative features (including intensity, texture, and structure) from medical images. Machine learning, including its subset deep learning, aids in the comprehensive analysis and integration of these features from diverse image sources. This potent synergy enables the prediction of responses of malignant liver tumors to various treatments and outcomes. In this comprehensive review, we examine the evolution of the field of radiomics and its procedural framework. Furthermore, the applications of radiomics combined with machine learning in the context of personalized treatment for malignant liver tumors are outlined in aspects of surgical therapy and non-surgical treatments such as ablation, transarterial chemoembolization, radiotherapy, and systemic therapies. Finally, we discuss the current challenges in the amalgamation of radiomics and machine learning in the study of malignant liver tumors and explore future opportunities.

Imaging in interventional oncology, the better you see, the better you treat

Imaging and image processing is the fundamental pillar of interventional oncology in which diagnostic, procedure planning, treatment and follow-up are sustained. Knowing all the possibilities that the different image modalities can offer is capital to select the most appropriate and accurate guidance for interventional procedures. Despite there is a wide variability in physicians preferences and availability of the different image modalities to guide interventional procedures, it is important to recognize the advantages and limitations for each of them. In this review, we aim to provide an overview of the most frequently used image guidance modalities for interventional procedures and its typical and future applications including angiography, computed tomography (CT) and spectral CT, magnetic resonance imaging, Ultrasound and the use of hybrid systems. Finally, we resume the possible role of artificial intelligence related to image in patient selection, treatment and follow-up.

Determining the prognosis of Lung cancer from mutated genes using a deep learning survival model: a large multi-center study

BACKGROUND

Gene status has become the focus of prognosis prediction. Furthermore, deep learning has frequently been implemented in medical imaging to diagnose, prognosticate, and evaluate treatment responses in patients with cancer. However, few deep learning survival (DLS) models based on mutational genes that are directly associated with patient prognosis in terms of progression-free survival (PFS) or overall survival (OS) have been reported. Additionally, DLS models have not been applied to determine IO-related prognosis based on mutational genes. Herein, we developed a deep learning method to predict the prognosis of patients with lung cancer treated with or without immunotherapy (IO).

METHODS

Samples from 6542 patients from different centers were subjected to genome sequencing. A DLS model based on multi-panels of somatic mutations was trained and validated to predict OS in patients treated without IO and PFS in patients treated with IO.

RESULTS

In patients treated without IO, the DLS model (low vs. high DLS) was trained using the training MSK-MET cohort (HR = 0.241 [0.213-0.273], P < 0.001) and tested in the inter-validation MSK-MET cohort (HR = 0.175 [0.148-0.206], P < 0.001). The DLS model was then validated with the OncoSG, MSK-CSC, and TCGA-LUAD cohorts (HR = 0.420 [0.272-0.649], P < 0.001; HR = 0.550 [0.424-0.714], P < 0.001; HR = 0.215 [0.159-0.291], P < 0.001, respectively). Subsequently, it was fine-tuned and retrained in patients treated with IO. The DLS model (low vs. high DLS) could predict PFS and OS in the MIND, MSKCC, and POPLAR/OAK cohorts (P < 0.001, respectively). Compared with tumor-node-metastasis staging, the COX model, tumor mutational burden, and programmed death-ligand 1 expression, the DLS model had the highest C-index in patients treated with or without IO.

CONCLUSIONS

The DLS model based on mutational genes can robustly predict the prognosis of patients with lung cancer treated with or without IO.

Using Machine Learning to Predict Response to Image-guided Therapies for Hepatocellular Carcinoma

Interventional oncology is a rapidly growing field with advances in minimally invasive image-guided local-regional treatments for hepatocellular carcinoma (HCC), including transarterial chemoembolization, transarterial radioembolization, and thermal ablation. However, current standardized clinical staging systems for HCC are limited in their ability to optimize patient selection for treatment as they rely primarily on serum markers and radiologist-defined imaging features. Given the variation in treatment responses, an updated scoring system that includes multidimensional aspects of the disease, including quantitative imaging features, serum markers, and functional biomarkers, is needed to optimally triage patients. With the vast amounts of numerical medical record data and imaging features, researchers have turned to image-based methods, such as radiomics and artificial intelligence (AI), to automatically extract and process multidimensional data from images. The synthesis of these data can provide clinically relevant results to guide personalized treatment plans and optimize resource utilization. Machine learning (ML) is a branch of AI in which a model learns from training data and makes effective predictions by teaching itself. This review article outlines the basics of ML and provides a comprehensive overview of its potential value in the prediction of treatment response in patients with HCC after minimally invasive image-guided therapy.

Prediction model of no-response before the first transarterial chemoembolization for hepatocellular carcinoma: TACF score

Previous clinic models for patients with hepatocellular carcinoma (HCC) receiving transarterial chemoembolization (TACE) mainly focused on the overall survival, whereas a simple-to-use tool for predicting the response to the first TACE and the management of risk classification before TACE are lacking. Our aim was to develop a scoring system calculated manually for these patients. A total of 437 patients with hepatocellular carcinoma (HCC) who underwent TACE treatment were carefully selected for analysis. They were then randomly divided into two groups: a training group comprising 350 patients and a validation group comprising 77 patients. Furthermore, 45 HCC patients who had recently undergone TACE treatment been included in the study to validate the model's efficacy and applicability. The factors selected for the predictive model were comprehensively based on the results of the LASSO, univariate and multivariate logistic regression analyses. The discrimination, calibration ability and clinic utility of models were evaluated in both the training and validation groups. A prediction model incorporated 3 objective imaging characteristics and 2 indicators of liver function. The model showed good discrimination, with AUROCs of 0.735, 0.706 and 0.884 and in the training group and validation groups, and good calibration. The model classified the patients into three groups based on the calculated score, including low risk, median risk and high-risk groups, with rates of no response to TACE of 26.3%, 40.2% and 76.8%, respectively. We derived and validated a model for predicting the response of patients with HCC before receiving the first TACE that had adequate performance and utility. This model may be a useful and layered management tool for patients with HCC undergoing TACE.

Contrast-Enhanced CT Imaging Features Combined with Clinical Factors to Predict the Efficacy and Prognosis for Transarterial Chemoembolization of Hepatocellular Carcinoma

RATIONALE AND OBJECTIVES

Accurate prediction of treatment response to transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) is critical for precision treatment. This study aimed to develop a comprehensive model (DLRC) that incorporates contrast-enhanced computed tomography (CECT) images and clinical factors to predict the response to TACE in patients with HCC.

MATERIALS AND METHODS

A total of 399 patients with intermediate-stage HCC were included in this retrospective study. Deep learning and radiomic signatures were established based on arterial phase CECT images, Correlation analysis and the least absolute shrinkage and selection (LASSO) regression analysis were applied for features selection. The DLRC model incorporating deep learning radiomic signatures and clinical factors was developed using multivariate logistic regression. The area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA) were used to evaluate the performance of the models. Kaplan-Meier survival curves based on the DLRC were plotted to assess overall survival in the follow-up cohort (n = 261).

RESULTS

The DLRC model was developed using 19 quantitative radiomic features, 10 deep learning features, and 3 clinical factors. The AUC of the DLRC model was 0.937 (95% confidence interval [CI], 0.912-0.962) and 0.909 (95% CI, 0.850-0.968) in the training and validation cohorts, respectively, outperforming models established with two signatures or a single signature (p < 0.05). Stratified analysis showed that the DLRC was not statistically different between subgroups (p > 0.05), and the DCA confirmed the greater net clinical benefit. In addition, multivariable cox regression revealed that DLRC model outputs were independent risk factors for the overall survival (hazard ratios: 1.20, 95% CI: 1.03-1.40; p = 0.019).

CONCLUSION

The DLRC model exhibited a remarkable accuracy in predicting response to TACE, and it can be utilized as a potent tool for precision treatment.

Radiomics features of computed tomography and magnetic resonance imaging for predicting response to transarterial chemoembolization in hepatocellular carcinoma: a meta-analysis

Purpose

To examine the methodological quality of radiomics-related studies and evaluate the ability of radiomics to predict treatment response to transarterial chemoembolization (TACE) for hepatocellular carcinoma (HCC).

Methods

A systematic review was performed on radiomics-related studies published until October 15, 2022, predicting the effectiveness of TACE for HCC. Methodological quality and risk of bias were assessed using the Radiomics Quality Score (RQS) and Quality Assessment of Diagnostic Accuracy Studies-2 tools, respectively. Pooled sensitivity, pooled specificity, and area under the curve (AUC) were determined to evaluate the utility of radiomics in predicting the response to TACE for HCC.

Results

In this systematic review, ten studies were eligible, and six of these studies were used in our meta-analysis. The RQS ranged from 7-21 (maximum possible score: 36). The pooled sensitivity and specificity were 0.89 (95% confidence interval (CI) = 0.79-0.95) and 0.82 (95% CI = 0.64-0.92), respectively. The overall AUC was 0.93 (95% CI = 0.90-0.95).

Conclusion

Radiomics-related studies evaluating the efficacy of TACE in patients with HCC revealed promising results. However, prospective and multicenter trials are warranted to make radiomics more feasible and acceptable.

What Imaging Modality Is More Effective in Predicting Early Recurrence of Hepatocellular Carcinoma after Hepatectomy Using Radiomics Analysis: CT or MRI or Both?

BACKGROUND

It is of great importance to predict the early recurrence (ER) of hepatocellular carcinoma (HCC) after hepatectomy using preoperative imaging modalities. Nevertheless, no comparative studies have been conducted to determine which modality, CT or MRI with radiomics analysis, is more effective.

METHODS

We retrospectively enrolled 119 HCC patients who underwent preoperative CT and MRI. A total of 3776 CT features and 4720 MRI features were extracted from the whole tumor. The minimum redundancy and maximum relevance algorithm (MRMR) and least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection, then support vector machines (SVMs) were applied for model construction. Multivariable logistic regression analysis was employed to construct combined models that integrate clinical-radiological-pathological (CRP) traits and radscore. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were used to compare the efficacy of CT, MRI, and CT and MRI models in the test cohort.

RESULTS

The CT model and MRI model showed no significant difference in the prediction of ER in HCC patients (p = 0.911). Radiomics^CT&MRI demonstrated a superior predictive performance than either Radiomics^CT or Radiomics^MRI alone (p = 0.032, 0.039). The combined CT and MRI model can significantly stratify patients at high risk of ER (area under the curve (AUC) of 0.951 in the training set and 0.955 in the test set) than the CT model (AUC of 0.894 and 0.784) and the MRI model (AUC of 0.856 and 0.787). DCA demonstrated that the CT and MRI model provided a greater net benefit than the models without radiomics analysis.

CONCLUSIONS

No significant difference was found in predicting the ER of HCC between CT models and MRI models. However, the multimodal radiomics model derived from CT and MRI can significantly improve the prediction of ER in HCC patients after resection.

Dynamic radiomics for predicting the efficacy of antiangiogenic therapy in colorectal liver metastases

Background and objective

For patients with advanced colorectal liver metastases (CRLMs) receiving first-line anti-angiogenic therapy, an accurate, rapid and noninvasive indicator is urgently needed to predict its efficacy. In previous studies, dynamic radiomics predicted more accurately than conventional radiomics. Therefore, it is necessary to establish a dynamic radiomics efficacy prediction model for antiangiogenic therapy to provide more accurate guidance for clinical diagnosis and treatment decisions.

Methods

In this study, we use dynamic radiomics feature extraction method that extracts static features using tomographic images of different sequences of the same patient and then quantifies them into new dynamic features for the prediction of treatmentefficacy. In this retrospective study, we collected 76 patients who were diagnosed with unresectable CRLM between June 2016 and June 2021 in the First Hospital of China Medical University. All patients received standard treatment regimen of bevacizumab combined with chemotherapy in the first-line treatment, and contrast-enhanced abdominal CT (CECT) scans were performed before treatment. Patients with multiple primary lesions as well as missing clinical or imaging information were excluded. Area Under Curve (AUC) and accuracy were used to evaluate model performance. Regions of interest (ROIs) were independently delineated by two radiologists to extract radiomics features. Three machine learning algorithms were used to construct two scores based on the best response and progression-free survival (PFS).

Results

For the task that predict the best response patients will achieve after treatment, by using ROC curve analysis, it can be seen that the relative change rate (RCR) feature performed best among all features and best in linear discriminantanalysis (AUC: 0.945 and accuracy: 0.855). In terms of predicting PFS, the Kaplan-Meier plots suggested that the score constructed using the RCR features could significantly distinguish patients with good response from those with poor response (Two-sided P<0.0001 for survival analysis).

Conclusions

This study demonstrates that the application of dynamic radiomics features can better predict the efficacy of CRLM patients receiving antiangiogenic therapy compared with conventional radiomics features. It allows patients to have a more accurate assessment of the effect of medical treatment before receiving treatment, and this assessment method is noninvasive, rapid, and less expensive. Dynamic radiomics model provides stronger guidance for the selection of treatment options and precision medicine.

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.

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.

Immune-related gene signature to predict TACE refractoriness in patients with hepatocellular carcinoma based on artificial neural network

Background: Transarterial chemoembolization (TACE) is the standard treatment option for intermediate-stage hepatocellular carcinoma (HCC), while response varies among patients. This study aimed to identify novel immune-related genes (IRGs) and establish a prediction model for TACE refractoriness in HCC patients based on machine learning methods. Methods: Gene expression data were downloaded from GSE104580 dataset of Gene Expression Omnibus (GEO) database, differential analysis was first performed to screen differentially expressed genes (DEGs). The least absolute shrinkage and selection operator (LASSO) regression analysis was performed to further select significant DEGs. Weighted gene co-expression network analysis (WGCNA) was utilized to build a gene co-expression network and filter the hub genes. Final signature genes were determined by the intersection of LASSO analysis results, WGCNA results and IRGs list. Based on the above results, the artificial neural network (ANN) model was constructed in the training cohort and verified in the validation cohort. Receiver operating characteristics (ROC) analysis was used to assess the prediction accuracy. Correlation of signature genes with tumor microenvironment scores, immune cells and immune checkpoint molecules were further analyzed. The tumor immune dysfunction and exclusion (TIDE) score was used to evaluate the response to immunotherapy. Results: One hundred and forty-seven samples were included in this study, which was randomly divided into the training cohort (n = 103) and validation cohort (n = 44). In total, 224 genes were identified as DEGs. Further LASSO regression analysis screened out 25 genes from all DEGs. Through the intersection of LASSO results, WGCNA results and IRGs list, S100A9, TREM1, COLEC12, and IFIT1 were integrated to construct the ANN model. The areas under the curves (AUCs) of the model were .887 in training cohort and .765 in validation cohort. The four IRGs also correlated with tumor microenvironment scores, infiltrated immune cells and immune checkpoint genes in various degrees. Patients with TACE-Response, lower expression of COLEC12, S100A9, TREM1 and higher expression of IFIT1 had better response to immunotherapy. Conclusion: This study constructed and validated an IRG signature to predict the refractoriness to TACE in patients with HCC, which may have the potential to provide insights into the TACE refractoriness in HCC and become the immunotherapeutic targets for HCC patients with TACE refractoriness.

Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview

Gastrointestinal (GI) cancers are the major cause of cancer-related mortality globally. Medical imaging is an important auxiliary means for the diagnosis, assessment and prognostic prediction of GI cancers. Radiomics is an emerging and effective technology to decipher the encoded information within medical images, and traditional machine learning is the most commonly used tool. Recent advances in deep learning technology have further promoted the development of radiomics. In the field of GI cancer, although there are several surveys on radiomics, there is no specific review on the application of deep-learning-based radiomics (DLR). In this review, a search was conducted on Web of Science, PubMed, and Google Scholar with an emphasis on the application of DLR for GI cancers, including esophageal, gastric, liver, pancreatic, and colorectal cancers. Besides, the challenges and recommendations based on the findings of the review are comprehensively analyzed to advance DLR.

Deep learning to estimate durable clinical benefit and prognosis from patients with non-small cell lung cancer treated with PD-1/PD-L1 blockade

Different biomarkers based on genomics variants have been used to predict the response of patients treated with PD-1/programmed death receptor 1 ligand (PD-L1) blockade. We aimed to use deep-learning algorithm to estimate clinical benefit in patients with non-small-cell lung cancer (NSCLC) before immunotherapy. Peripheral blood samples or tumor tissues of 915 patients from three independent centers were profiled by whole-exome sequencing or next-generation sequencing. Based on convolutional neural network (CNN) and three conventional machine learning (cML) methods, we used multi-panels to train the models for predicting the durable clinical benefit (DCB) and combined them to develop a nomogram model for predicting prognosis. In the three cohorts, the CNN achieved the highest area under the curve of predicting DCB among cML, PD-L1 expression, and tumor mutational burden (area under the curve [AUC] = 0.965, 95% confidence interval [CI]: 0.949–0.978, P< 0.001; AUC =0.965, 95% CI: 0.940–0.989, P< 0.001; AUC = 0.959, 95% CI: 0.942–0.976, P< 0.001, respectively). Patients with CNN-high had longer progression-free survival (PFS) and overall survival (OS) than patients with CNN-low in the three cohorts. Subgroup analysis confirmed the efficient predictive ability of CNN. Combining three cML methods (CNN, SVM, and RF) yielded a robust comprehensive nomogram for predicting PFS and OS in the three cohorts (each P< 0.001). The proposed deep-learning method based on mutational genes revealed the potential value of clinical benefit prediction in patients with NSCLC and provides novel insights for combined machine learning in PD-1/PD-L1 blockade.