Radiomics in liver diseases: Current progress and future opportunities

New frontiers in hepatocellular carcinoma: Precision imaging for microvascular invasion prediction

This paper highlights the innovative approach and findings of the recently published study by Xu et al, which underscores the integration of radiomics and clinicoradiological factors to enhance the preoperative prediction of microvascular invasion in patients with hepatitis B virus-related hepatocellular carcinoma (HBV-HCC). The study’s use of contrast-enhanced computed tomography radiomics to construct predictive models offers a significant advancement in the surgical planning and management of HBV-HCC, potentially transforming patient outcomes through more personalized treatment strategies. This editorial commends the study's contribution to precision medicine and discusses its implications for future research and clinical practice.

Ultrasound radiomics-based logistic regression model for fibrotic NASH

BACKGROUND

Those who have severe fibrosis (F2 ≥ 2 stage) are at the greatest risk for the advancement of the illness among non-alcoholic fatty liver patients. To forecast the non-alcoholic steatohepatitis (NASH) probability accompanied by significant fibrosis, we propose to develop and validate a nomogram liver imaging reporting and data system, providing robust evidence for preventing and treating clinical liver diseases.

METHODS

The study used SD rats to create a model of hepatic steatosis and fibrosis by feeding them a high-fat diet and injecting Ccl4 subcutaneously. Radiomics characteristics were derived from two-dimensional liver ultrasound images of the rats, and a radiomics model was constructed, with rad-scores calculated accordingly. Univariate and multivariate logistic regression was employed to ascertain the clinical characteristics of rats and liver elasticity values, aiming to establish a clinical model. Ultimately, a clinical radiomics model was created by integrating the rad-score from the radiomics model with independent clinical characteristics from the clinical model. A forest plot was generated to depict this integration. The forest plot's performance was assessed by the use of the area under the receiver operating characteristic (ROC) curve (AUC), decision curve analysis, and calibration curve.

RESULTS

The areas under the receiver operating characteristic curve (AUC) for the training set and validation set of the clinical radiomics model were 0.986 and 0.971, respectively. Decision curve analysis showed that the clinical radiomics model had the highest net benefit across most threshold probability ranges.

CONCLUSION

The nomogram and clinical radiomics model, which consists of clinical characteristics, real-time shear wave elastography, and radiomics, provide excellent predictive capability in assessing the likelihood of fibrotic NASH.

Deep learning model based on contrast-enhanced ultrasound for predicting vessels encapsulating tumor clusters in hepatocellular carcinoma

OBJECTIVES

To establish and validate a non-invasive deep learning (DL) model based on contrast-enhanced ultrasound (CEUS) to predict vessels encapsulating tumor clusters (VETC) patterns in hepatocellular carcinoma (HCC).

MATERIALS AND METHODS

This retrospective study included consecutive HCC patients with preoperative CEUS images and available tissue specimens. Patients were randomly allocated into the training and test cohorts. CEUS images were analyzed using the ResNet-18 convolutional neural network for the development and validation of the VETC predictive model. The predictive value for postoperative early recurrence (ER) of the proposed model was further evaluated.

RESULTS

A total of 242 patients were enrolled finally, including 195 in the training cohort (54.6 ± 11.2 years, 178 males) and 47 in the test cohort (55.1 ± 10.6 years, 40 males). The DL model (DL signature) achieved favorable performance in both the training cohort (area under the receiver operating characteristics curve [AUC]: 0.92, 95% confidence interval [CI]: 0.88-0.96) and test cohort (AUC: 0.90, 95% CI: 0.82-0.99). The stratified analysis demonstrated good discrimination of DL signature regardless of tumor size. Moreover, the DL signature was found independently correlated with postoperative ER (hazard ratio [HR]: 1.99, 95% CI: 1.29-3.06, p = 0.002). C-indexes of 0.70 and 0.73 were achieved when the DL signature was used to predict ER independently and combined with clinical features.

CONCLUSION

The proposed DL signature provides a non-invasive and practical method for VETC-HCC prediction, and contributes to the identification of patients with high risk of postoperative ER.

CLINICAL RELEVANCE STATEMENT

This DL model based on contrast-enhanced US displayed an important role in non-invasive diagnosis and prognostication for patients with VETC-HCC, which was helpful in individualized management.

KEY POINTS

Preoperative biopsy to determine VETC status in HCC patients is limited. The contrast-enhanced DL model provides a non-invasive tool for the prediction of VETC-HCC. The proposed deep-learning signature assisted in identifying patients with a high risk of postoperative ER.

An MRI-Based Radiomics Model for Preoperative Prediction of Microvascular Invasion and Outcome in Intrahepatic Cholangiocarcinoma

PURPOSE

Microvascular invasion (MVI) serves as a significant predictor of poor prognosis in intrahepatic cholangiocarcinoma (ICC). This study aims to establish a comprehensive model utilizing MR radiomics for preoperative MVI status stratification and outcome prediction in ICC patients.

MATERIALS AND METHODS

A total of 249 ICC patients were randomly assigned to training and validation cohorts (174:75), along with a time-independent test cohort consisting of 47 ICC patients. Independent clinical and imaging predictors were identified by univariate and multivariate logistic regression analyses. The radiomic model was developed based on robust radiomic features extracted using a logistic regression classifier. The predictive efficacy of the models was evaluated by receiver operating characteristic curves, calibration curves and decision curves. Multivariate Cox analysis identified the independent risk factors for recurrence-free survival and overall survival, Kaplan-Meier curves were plotted, and a nomogram was used to visualize the predictive model.

RESULTS

The imaging model included tumor size and intrahepatic duct dilatation. The radiomics model comprised 25 stable radiomics features. The Imaging-Radiomics (IR) model, which integrates independent predictors and robust radiomics features, demonstrates desirable performance for MVI (AUCtraining= 0.890, AUCvalidation= 0.885 and AUCtest= 0.815). The calibration curve and decision curve validate the clinical utility. Preoperative MVI prediction based on IR model demonstrated comparable accuracy in MVI stratification and outcome prediction when compared to histological MVI.

CONCLUSION

The IR model and the nomogram based on IR model-predicted MVI status may serve as potential tools for MVI status stratification and outcome prediction in ICC patients preoperatively.

Development and Validation of a Modality-Invariant 3D Swin U-Net Transformer for Liver and Spleen Segmentation on Multi-Site Clinical Bi-parametric MR Images

To develop and validate a modality-invariant Swin U-Net Transformer (UNETR) deep learning model for liver and spleen segmentation on abdominal T1-weighted (T1w) or T2-weighted (T2w) MR images from multiple institutions for pediatric and adult patients with known or suspected chronic liver diseases. In this IRB-approved retrospective study, clinical abdominal axial T1w and T2w MR images from pediatric and adult patients were retrieved from four study sites, including Cincinnati Children's Hospital Medical Center (CCHMC), New York University (NYU), University of Wisconsin (UW) and University of Michigan / Michigan Medicine (UM). The whole liver and spleen were manually delineated as the ground truth masks. We developed a modality-invariant 3D Swin UNETR using a modality-invariant training strategy, in which each patient's T1w and T2w MR images were treated as separate training samples. We conducted both internal and external validation experiments. A total of 241 T1w and 339 T2w MR sequences from 304 patients (age [mean ± standard deviation], 31.8 ± 20.3 years; 132 [43%] female) were included for model development. The Swin UNETR achieved a Dice similarity coefficient (DSC) of 0.95 ± 0.02 on T1w images and 0.93 ± 0.05 on T2w images for liver segmentation. This is significantly better than the U-Net model (0.90 ± 0.05, p < 0.001 and 0.90 ± 0.13, p < 0.001, respectively). The Swin UNETR achieved a DSC of 0.88 ± 0.12 on T1w images and 0.93 ± 0.10 on T2w images for spleen segmentation, and it significantly outperformed a modality-invariant U-Net model (0.80 ± 0.18, p = 0.001 and 0.88 ± 0.12, p = 0.002, respectively). Our study demonstrated that a modality-invariant Swin UNETR model can segment the liver and spleen on routinely collected clinical bi-parametric abdominal MR images from children and adult patients.

18F-FDG PET/CT-based habitat radiomics combining stacking ensemble learning for predicting prognosis in hepatocellular carcinoma: a multi-center study

BACKGROUND

This study aims to develop habitat radiomic models to predict overall survival (OS) for hepatocellular carcinoma (HCC), based on the characterization of the intratumoral heterogeneity reflected in 18F-FDG PET/CT images.

METHODS

A total of 137 HCC patients from two institutions were retrospectively included. First, intratumoral habitats were achieved by a two-step unsupervised clustering process based on k-means clustering. Second, a total of 4032 radiomic features were extracted based on each habitat, including 2016 PET-based and 2016 CT-based radiomic features. Then, after feature selection, the stacking ensemble learning approach which combined six machine learning classifiers as the first-level learners with Cox proportional hazards regression as the second-level learner, was employed to build multiple radiomic models. Finally, the optimal model was selected based on the calculation of the C-index, and a combined model integrating with a clinical model was also constructed to identify the potentially complementary effect.

RESULTS

Three spatially distinct habitats were identified in the two cohorts. Among a total of 30 stacking ensemble learning models established based on different combinations of 5 types of segmented volumes of interest (VOIs) with 6 types of classifiers, the MLP-Cox-habitat-2 model was selected as the optimal radiomic model with a C-index of 0.702 in the external validation cohort. Furthermore, the combined model integrating the optimal radiomic model with the clinical model achieved an improved C-index of 0.747. Consistently, the combined model outperformed the other models for OS prediction, with a time-dependent AUC of 0.835, 0.828, and 0.800 in the 1-year, 2-year, and 3-year OS, respectively.

CONCLUSION

18F-FDG PET/CT-based habitat radiomics outperformed traditional radiomics in OS prediction for HCC, with a further improved predictive power by integrating with the clinical model. The optimal combined habitat model was potentially promising in guiding individualized treatment for HCC.

TRIAL REGISTRATION

This study was a retrospective study, so it was free from registration.

A combination model of CT-based radiomics and clinical biomarkers for staging liver fibrosis in the patients with chronic liver disease

A combined model was developed using contrast-enhanced CT-based radiomics features and clinical characteristics to predict liver fibrosis stages in patients with chronic liver disease (CLD). We retrospectively analyzed multiphase CT scans and biopsy-confirmed liver fibrosis. 160 CLD patients were randomly divided into 7:3 training/validation ratio. Clinical laboratory indicators associated with liver fibrosis were identified using Spearman's correlation and multivariate logistic regression correlation. Radiomic features were extracted after segmenting the entire liver from multiphase CT images. Feature dimensionality reduction was performed using RF-RFE, LASSO, and mRMR methods. Six radiomics-based models were developed in the training cohort of 112 patients. Internal validation was conducted on 48 randomly assigned patients. Receptor Operating Characteristic (ROC) curves and confusion matrices were constructed to evaluate model performance. The radiomics model exhibited robust performance, with AUC values of 0.810 to 1.000 for significant fibrosis, advanced fibrosis, and cirrhosis. The integrated clinical-radiomics model had superior diagnostic efficacy in the validation cohort, with AUC values of 0.836 to 0.997. Moreover, these models outperformed established biomarkers such as the aspartate aminotransferase to platelet ratio index (APRI) and the fibrosis 4 score (FIB-4), as well as the gamma glutamyl transpeptidase to platelet ratio (GPR), in predicting the fibrotic stages. The clinical-radiomics model holds considerable promise as a non-invasive diagnostic tool for the assessment and staging of liver fibrosis in the patients with CLD, potentially leading to better patient management and outcomes.

Development and validation of a CT-based nomogram for accurate hepatocellular carcinoma detection in high risk patients

Purpose

To establish and validate a CT-based nomogram for accurately detecting HCC in patients at high risk for the disease.

Methods

A total of 223 patients were divided into training (n=161) and validation (n=62) cohorts between January of 2017 and May of 2022. Logistic analysis was performed, and clinical model and radiological model were developed separately. Finally, a nomogram was established based on clinical and radiological features. All models were evaluated using the area under the curve (AUC). DeLong's test was used to evaluate the differences among these models.

Results

In the multivariate analysis, gender (p = 0.014), increased Alpha-fetoprotein (AFP) (p = 0.017), non-rim arterial phase hyperenhancement (APHE) (p = 0.011), washout (p = 0.011), and enhancing capsule (p = 0.001) were the independent differential predictors of HCC. A nomogram was formed with well-fitted calibration curves based on these five factors. The area under the curve (AUC) of the nomogram in the training and validation cohorts was 0.961(95%CI: 0.935~0.986) and 0.979 (95% CI: 0.949~1), respectively. The nomogram outperformed the clinical and the radiological models in training and validation cohorts.

Conclusion

The nomogram incorporating clinical and CT features can be a simple and reliable tool for detecting HCC and achieving risk stratification in patients at high risk for HCC.

Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics

OBJECTIVES

To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI).

MATERIALS AND METHODS

This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by the Dice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC).

RESULTS

In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets.

CONCLUSION

Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction.

CLINICAL RELEVANCE STATEMENT

Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI.

KEY POINTS

• This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.

Early warning of hepatocellular carcinoma in cirrhotic patients by three-phase CT-based deep learning radiomics model: a retrospective, multicentre, cohort study

Background

The diagnosis of hepatocellular carcinoma (HCC) often experiences latency, ultimately leading to unfavorable patient outcomes due to delayed therapeutic interventions. Our study is designed to develop and validate a model that employs triple-phase computerized tomography (CT)-based deep learning radiomics and clinical variables for early warning of HCC in patients with cirrhosis.

Methods

We studied 1858 patients with cirrhosis primarily from the PreCar cohort (NCT03588442) between June 2018 and January 2020 at 11 centres, and collected triple-phase CT images and laboratory results 3-12 months prior to HCC diagnosis or non-HCC final follow-up. Using radiomics and deep learning techniques, early warning model was developed in the discovery cohort (n = 924), and then validated in an internal validation cohort (n = 231), and an external validation cohort from 10 external centres (n = 703).

Findings

We developed a hybrid model, named ALARM model, which integrates deep learning radiomics with clinical variables, enabling early warning of the majority of HCC cases. The ALARM model effectively predicted short-term HCC development in cirrhotic patients with area under the curve (AUC) of 0.929 (95% confidence interval 0.918-0.941) in the discovery cohort, 0.902 (0.818-0.987) in the internal validation cohort, and 0.918 (0.898-0.961) in the external validation cohort. By applying optimal thresholds of 0.21 and 0.65, the high-risk (n = 221, 11.9%) and medium-risk (n = 433, 23.3%) groups, which covered 94.4% (84/89) of the patients who developed HCC, had significantly higher rates of HCC occurrence compared to the low-risk group (n = 1204, 64.8%) (24.3% vs 6.4% vs 0.42%, P < 0.001). Furthermore, ALARM also demonstrated consistent performance in subgroup analysis.

Interpretation

The novel ALARM model, based on deep learning radiomics with clinical variables, provides reliable estimates of short-term HCC development for cirrhotic patients, and may have the potential to improve the precision in clinical decision-making and early initiation of HCC treatments.

Funding

This work was supported by National Key Research and Development Program of China (2022YFC2303600, 2022YFC2304800), and the National Natural Science Foundation of China (82170610), Guangdong Basic and Applied Basic Research Foundation (2023A1515011211).

Fully automated hybrid approach on conventional MRI for triaging clinically significant liver fibrosis: A multi-center cohort study

Establishing reliable noninvasive tools to precisely diagnose clinically significant liver fibrosis (SF, ≥F2) remains an unmet need. We aimed to build a combined radiomics-clinic (CoRC) model for triaging SF and explore the additive value of the CoRC model to transient elastography-based liver stiffness measurement (FibroScan, TE-LSM). This retrospective study recruited 595 patients with biopsy-proven liver fibrosis at two centers between January 2015 and December 2021. At Center 1, the patients before December 2018 were randomly split into training (276) and internal test (118) sets, the remaining were time-independent as a temporal test set (96). Another data set (105) from Center 2 was collected for external testing. Radiomics scores were built with selected features from Deep learning-based (ResUNet) automated whole liver segmentations on MRI (T2FS and delayed enhanced-T1WI). The CoRC model incorporated radiomics scores and relevant clinical variables with logistic regression, comparing routine approaches. Diagnostic performance was evaluated by the area under the receiver operating characteristic curve (AUC). The additive value of the CoRC model to TE-LSM was investigated, considering necroinflammation. The CoRC model achieved AUCs of 0.79 (0.70, 0.86), 0.82 (0.73, 0.89), and 0.81 (0.72-0.91), outperformed FIB-4, APRI (all p < 0.05) in the internal, temporal, and external test sets and maintained the discriminatory power in G0-1 subgroups (AUCs range, 0.85-0.86; all p < 0.05). The AUCs of joint CoRC-LSM model were 0.86 (0.79-0.94), and 0.81 (0.72-0.90) in the internal and temporal sets (p = 0.01). The CoRC model was useful for triaging SF, and may add value to TE-LSM.

Simultaneous grading diagnosis of liver fibrosis, inflammation, and steatosis using multimodal quantitative ultrasound and artificial intelligence framework

Noninvasive, accurate, and simultaneous grading of liver fibrosis, inflammation, and steatosis is valuable for reversing the progression and improving the prognosis quality of chronic liver diseases (CLDs). In this study, we established an artificial intelligence framework for simultaneous grading diagnosis of these three pathological types through fusing multimodal tissue characterization parameters dug by quantitative ultrasound methods derived from ultrasound radiofrequency signals, B-mode images, shear wave elastography images, and clinical ultrasound systems, using the liver biopsy results as the classification criteria. One hundred forty-two patients diagnosed with CLD were enrolled in this study. The results show that for the classification of fibrosis grade ≥ F1, ≥ F2, ≥ F3, and F4, the highest AUCs were respectively 0.69, 0.82, 0.84, and 0.88 with single clinical indicator alone, and were 0.81, 0.83, 0.89, and 0.91 with the proposed method. For the classification of inflammation grade ≥ A2 and A3, the highest AUCs were respectively 0.66 and 0.76 with single clinical indicator alone and were 0.80 and 0.93 with the proposed method. For the classification of steatosis grade ≥ S1 and ≥ S2, the highest AUCs were respectively 0.71 and 0.90 with single clinical indicator alone and were 0.75 and 0.92 with the proposed method. The proposed method can effectively improve the grading diagnosis performance compared with the present clinical indicators and has potential applications for noninvasive, accurate, and simultaneous diagnosis of CLDs.

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

OBJECTIVES

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

METHODS

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

RESULTS

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

CONCLUSION

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

CRITICAL RELEVANCE STATEMENT

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

KEY POINTS

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

A clinical-radiomic-pathomic model for prognosis prediction in patients with hepatocellular carcinoma after radical resection

PURPOSE

Radical surgery, the first-line treatment for patients with hepatocellular cancer (HCC), faces the dilemma of high early recurrence rates and the inability to predict effectively. We aim to develop and validate a multimodal model combining clinical, radiomics, and pathomics features to predict the risk of early recurrence.

MATERIALS AND METHODS

We recruited HCC patients who underwent radical surgery and collected their preoperative clinical information, enhanced computed tomography (CT) images, and whole slide images (WSI) of hematoxylin and eosin (H & E) stained biopsy sections. After feature screening analysis, independent clinical, radiomics, and pathomics features closely associated with early recurrence were identified. Next, we built 16 models using four combination data composed of three type features, four machine learning algorithms, and 5-fold cross-validation to assess the performance and predictive power of the comparative models.

RESULTS

Between January 2016 and December 2020, we recruited 107 HCC patients, of whom 45.8% (49/107) experienced early recurrence. After analysis, we identified two clinical features, two radiomics features, and three pathomics features associated with early recurrence. Multimodal machine learning models showed better predictive performance than bimodal models. Moreover, the SVM algorithm showed the best prediction results among the multimodal models. The average area under the curve (AUC), accuracy (ACC), sensitivity, and specificity were 0.863, 0.784, 0.731, and 0.826, respectively. Finally, we constructed a comprehensive nomogram using clinical features, a radiomics score and a pathomics score to provide a reference for predicting the risk of early recurrence.

CONCLUSIONS

The multimodal models can be used as a primary tool for oncologists to predict the risk of early recurrence after radical HCC surgery, which will help optimize and personalize treatment strategies.

Exploring tumor heterogeneity in colorectal liver metastases by imaging: Unsupervised machine learning of preoperative CT radiomics features for prognostic stratification

OBJECTIVES

This study aimed to investigate tumor heterogeneity of colorectal liver metastases (CRLM) and stratify the patients into different risk groups of prognoses following liver resection by applying an unsupervised radiomics machine-learning approach to preoperative CT images.

METHODS

This retrospective study retrieved clinical information and CT images of 197 patients with CRLM from The Cancer Imaging Archive (TCIA) database. Radiomics features were extracted from a segmented liver lesion identified at the portal venous phase. Those features which showed high stability, non-redundancy, and indicative information were selected. An unsupervised consensus clustering analysis on these features was adopted to identify subgroups of CRLM patients. Overall survival (OS), disease-free survival (DFS), and liver-specific DFS were compared between the identified subgroups. Cox regression analysis was applied to evaluate prognostic risk factors.

RESULTS

A total of 851 radiomics features were extracted, and 56 robust features were finally selected for unsupervised clustering analysis which identified two distinct subgroups (96 and 101 patients respectively). There were significant differences in the OS, DFS, and liver-specific DFS between the subgroups (all log-rank p < 0.05). The subgroup with worse outcome using the proposed radiomics model was consistently associated with shorter OS, DFS, and liver-specific DFS, with hazard ratios of 1.78 (95 %CI: 1.12-2.83), 1.72 (95 %CI: 1.16-2.54), and 1.59 (95 %CI: 1.10-2.31), respectively. The general performance of this radiomics model outperformed the traditional Clinical Risk Score and Tumor Burden Score in the prognosis prediction after surgery for CRLM.

CONCLUSION

Radiomics features derived from preoperative CT images can reveal the heterogeneity of CRLM and stratify the patients with CRLM into subgroups with significantly different clinical outcomes.

Radiomics signature of osteoarthritis: Current status and perspective

Osteoarthritis (OA) is one of the fast-growing disability-related diseases worldwide, which has significantly affected the quality of patients' lives and brings about substantial socioeconomic burdens in medical expenditure. There is currently no cure for OA once the bone damage is established. Unfortunately, the existing radiological examination is limited to grading the disease's severity and is insufficient to precisely diagnose OA, detect early OA or predict OA progression. Therefore, there is a pressing need to develop novel approaches in medical image analysis to detect subtle changes for identifying early OA development and rapid progressors. Recently, radiomics has emerged as a unique approach to extracting high-dimensional imaging features that quantitatively characterise visible or hidden information from routine medical images. Radiomics data mining via machine learning has empowered precise diagnoses and prognoses of disease, mainly in oncology. Mounting evidence has shown its great potential in aiding the diagnosis and contributing to the study of musculoskeletal diseases. This paper will summarise the current development of radiomics at the crossroads between engineering and medicine and discuss the application and perspectives of radiomics analysis for OA diagnosis and prognosis.

The translational potential of this article

Radiomics is a novel approach used in oncology, and it may also play an essential role in the diagnosis and prognosis of OA. By transforming medical images from qualitative interpretation to quantitative data, radiomics could be the solution for precise early OA detection, progression tracking, and treatment efficacy prediction. Since the application of radiomics in OA is still in the early stages and primarily focuses on fundamental studies, this review may inspire more explorations and bring more promising diagnoses, prognoses, and management results of OA.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

Radiomics analysis of contrast-enhanced computerized tomography for differentiation of gastric schwannomas from gastric gastrointestinal stromal tumors

PURPOSE

To assess the performance of radiomics-based analysis of contrast-enhanced computerized tomography (CE-CT) images for distinguishing GS from gastric GIST.

METHODS

Forty-nine patients with GS and two hundred fifty-three with GIST were enrolled in this retrospective study. CT features were evaluated by two associate chief radiologists. Radiomics features were extracted from portal venous phase images using Pyradiomics software. A non-radiomics dataset (combination of clinical characteristics and radiologist-determined CT features) and a radiomics dataset were used to build stepwise logistic regression and least absolute shrinkage and selection operator (LASSO) logistic regression models, respectively. Model performance was evaluated according to sensitivity, specificity, accuracy, and receiver operating characteristic (ROC) curve, and Delong's test was applied to compare the area under the curve (AUC) between different models.

RESULTS

A total of 1223 radiomics features were extracted from portal venous phase images. After reducing dimensions by calculating Pearson correlation coefficients (PCCs), 20 radiomics features, 20 clinical characteristics + CT features were used to build the models, respectively. The AUC values for the models using radiomics features and those using clinical features were more than 0.900 for both the training and validation groups. There were no significant differences in predictive performance between the radiomic and clinical data models according to Delong's test.

CONCLUSION

A radiomics-based model applied to CE-CT images showed comparable predictive performance to senior physicians in the differentiation of GS from GIST.

An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies

The aim of this informative review was to investigate the application of radiomics in cancer imaging and to summarize the results of recent studies to support oncological imaging with particular attention to breast cancer, rectal cancer and primitive and secondary liver cancer. This review also aims to provide the main findings, challenges and limitations of the current methodologies. Clinical studies published in the last four years (2019-2022) were included in this review. Among the 19 studies analyzed, none assessed the differences between scanners and vendor-dependent characteristics, collected images of individuals at additional points in time, performed calibration statistics, represented a prospective study performed and registered in a study database, conducted a cost-effectiveness analysis, reported on the cost-effectiveness of the clinical application, or performed multivariable analysis with also non-radiomics features. Seven studies reached a high radiomic quality score (RQS), and seventeen earned additional points by using validation steps considering two datasets from two distinct institutes and open science and data domains (radiomics features calculated on a set of representative ROIs are open source). The potential of radiomics is increasingly establishing itself, even if there are still several aspects to be evaluated before the passage of radiomics into routine clinical practice. There are several challenges, including the need for standardization across all stages of the workflow and the potential for cross-site validation using real-world heterogeneous datasets. Moreover, multiple centers and prospective radiomics studies with more samples that add inter-scanner differences and vendor-dependent characteristics will be needed in the future, as well as the collecting of images of individuals at additional time points, the reporting of calibration statistics and the performing of prospective studies registered in a study database.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application

Radiomics allows the extraction of quantitative imaging features from clinical magnetic resonance imaging (MRI) and computerized tomography (CT) studies. The advantages of radiomics have primarily been exploited in oncological applications, including better characterization and staging of oncological lesions and prediction of patient outcomes and treatment response. The potential introduction of radiomics in the clinical setting requires the establishment of a standardized radiomics pipeline and a quality assurance program. Radiomics and texture analysis of the liver have improved the differentiation of hypervascular lesions such as adenomas, focal nodular hyperplasia, and hepatocellular carcinoma (HCC) during the arterial phase, and in the pretreatment determination of HCC prognostic factors (e.g., tumor grade, microvascular invasion, Ki-67 proliferation index). Radiomics of pancreatic CT and MR images has enhanced pancreatic ductal adenocarcinoma detection and its differentiation from pancreatic neuroendocrine tumors, mass-forming chronic pancreatitis, or autoimmune pancreatitis. Radiomics can further help to better characterize incidental pancreatic cystic lesions, accurately discriminating benign from malignant intrapancreatic mucinous neoplasms. Nonetheless, despite their encouraging results and exciting potential, these tools have yet to be implemented in the clinical setting. This non-systematic review will describe the essential steps in the implementation of the radiomics and feature extraction workflow from liver and pancreas CT and MRI studies for their potential clinical application. A succinct overview of reported radiomics applications in the liver and pancreas and the challenges and limitations of their implementation in the clinical setting is also discussed, concluding with a brief exploration of the future perspectives of radiomics in the gastroenterology field.

Image-based AI diagnostic performance for fatty liver: a systematic review and meta-analysis

BACKGROUND

The gold standard to diagnose fatty liver is pathology. Recently, image-based artificial intelligence (AI) has been found to have high diagnostic performance. We systematically reviewed studies of image-based AI in the diagnosis of fatty liver.

METHODS

We searched the Cochrane Library, Pubmed, Embase and assessed the quality of included studies by QUADAS-AI. The pooled sensitivity, specificity, negative likelihood ratio (NLR), positive likelihood ratio (PLR), and diagnostic odds ratio (DOR) were calculated using a random effects model. Summary receiver operating characteristic curves (SROC) were generated to identify the diagnostic accuracy of AI models.

RESULTS

15 studies were selected in our meta-analysis. Pooled sensitivity and specificity were 92% (95% CI: 90-93%) and 94% (95% CI: 93-96%), PLR and NLR were 12.67 (95% CI: 7.65-20.98) and 0.09 (95% CI: 0.06-0.13), DOR was 182.36 (95% CI: 94.85-350.61). After subgroup analysis by AI algorithm (conventional machine learning/deep learning), region, reference (US, MRI or pathology), imaging techniques (MRI or US) and transfer learning, the model also demonstrated acceptable diagnostic efficacy.

CONCLUSION

AI has satisfactory performance in the diagnosis of fatty liver by medical imaging. The integration of AI into imaging devices may produce effective diagnostic tools, but more high-quality studies are needed for further evaluation.

3D automatic liver and spleen assessment in predicting overt hepatic encephalopathy before TIPS: a multi-center study

BACKGROUND

Overt hepatic encephalopathy (HE) should be predicted preoperatively to identify suitable candidates for transjugular intrahepatic portosystemic shunt (TIPS) instead of first-line treatment. This study aimed to construct a 3D assessment-based model to predict post-TIPS overt HE.

METHODS

In this multi-center cohort study, 487 patients who underwent TIPS were subdivided into a training dataset (390 cases from three hospitals) and an external validation dataset (97 cases from another two hospitals). Candidate factors included clinical, vascular, and 2D and 3D data. Combining the least absolute shrinkage and operator method, support vector machine, and probability calibration by isotonic regression, we constructed four predictive models: clinical, 2D, 3D, and combined models. Their discrimination and calibration were compared to identify the optimal model, with subgroup analysis performed.

RESULTS

The 3D model showed better discrimination than did the 2D model (training: 0.719 vs. 0.691; validation: 0.730 vs. 0.622). The model combining clinical and 3D factors outperformed the clinical and 3D models (training: 0.802 vs. 0.735 vs. 0.719; validation: 0.816 vs. 0.723 vs. 0.730; all p < 0.050). Moreover, the combined model had the best calibration. The performance of the best model was not affected by the total bilirubin level, Child-Pugh score, ammonia level, or the indication for TIPS.

CONCLUSION

3D assessment of the liver and the spleen provided additional information to predict overt HE, improving the chance of TIPS for suitable patients. 3D assessment could also be used in similar studies related to cirrhosis.

Clinic-radiomics model using liver magnetic resonance imaging helps predict chronicity of drug-induced liver injury

BACKGROUND AND AIMS

Some drug-induced liver injury (DILI) cases may become chronic, even after drug withdrawal. Radiomics can predict liver disease progression. We established and validated a predictive model incorporating the clinical characteristics and radiomics features for predicting chronic DILI.

METHODS

One hundred sixty-eight DILI patients who underwent liver gadolinium-diethylenetriamine pentaacetate-enhanced magnetic resonance imaging were recruited. The patients were clinically diagnosed using the Roussel Uclaf causality assessment method. Patients who progressed to chronicity or recovery were randomly divided into the training (70%) and validation (30%) cohorts, respectively. Hepatic T1-weighted images were segmented to extract 1672 radiomics features. Least absolute shrinkage and selection operator regression was used for feature selection, and Rad-score was constructed using support vector machines. Multivariable logistic regression analysis was performed to build a clinic-radiomics model incorporating clinical characteristics and Rad-scores. The clinic-radiomics model was evaluated for its discrimination, calibration, and clinical usefulness in the independent validation set.

RESULTS

Of 1672 radiomics features, 28 were selected to develop the Rad-score. Cholestatic/mixed patterns and Rad-score were independent risk factors of chronic DILI. The clinic-radiomics model, including the Rad-score and injury patterns, distinguished chronic from recovered DILI patients in the training (area under the receiver operating characteristic curve [AUROC]: 0.89, 95% confidence interval [95% CI]: 0.87-0.92) and validation (AUROC: 0.88, 95% CI: 0.83-0.91) cohorts with good calibration and great clinical utility.

CONCLUSION

The clinic-radiomics model yielded sufficient accuracy for predicting chronic DILI, providing a practical and non-invasive tool for managing DILI patients.

Repeatability of computed tomography liver radiomic features in a nonhuman primate model of diet-induced steatosis

Purpose

We describe a method to identify repeatable liver computed tomography (CT) radiomic features, suitable for detection of steatosis, in nonhuman primates. Criteria used for feature selection exclude nonrepeatable features and may be useful to improve the performance and robustness of radiomics-based predictive models.

Approach

Six crab-eating macaques were equally assigned to two experimental groups, fed regular chow or an atherogenic diet. High-resolution CT images were acquired over several days for each macaque. First-order and second-order radiomic features were extracted from six regions in the liver parenchyma, either with or without liver-to-spleen intensity normalization from images reconstructed using either a standard (B-filter) or a bone-enhanced (D-filter) kernel. Intrasubject repeatability of each feature was assessed using a paired t -test for all scans and the minimum p -value was identified for each macaque. Repeatable features were defined as having a minimum p -value among all macaques above the significance level after Bonferroni's correction. Features showing a significant difference with respect to diet group were identified using a two-sample t -test.

Results

A list of repeatable features was generated for each type of image. The largest number of repeatable features was achieved from spleen-normalized D-filtered images, which also produced the largest number of second-order radiomic features that were repeatable and different between diet groups.

Conclusions

Repeatability depends on reconstruction kernel and normalization. Features were quantified and ranked based on their repeatability. Features to be excluded for more robust models were identified. Features that were repeatable but different between diet groups were also identified.

Prediction of the mean transit time using machine learning models based on radiomics features from digital subtraction angiography in moyamoya disease or moyamoya syndrome-a development and validation model study

Background

Digital subtraction angiography (DSA) is an important technique for diagnosis of moyamoya disease (MMD) or moyamoya syndrome (MMS), and computed tomography perfusion (CTP) is essential for assessing intracranial blood supply. The aim of this study was to assess whether radiomics features based on images of DSA could predict the mean transit time (MTT; outcome of CTP) using machine learning models.

Methods

The DSA images and MTT values of adult patients with MMD or MMS, according to the diagnostic guidelines for MMD, as well as control cases, were retrospectively collected in the Guangdong Provincial People's Hospital between January 2018 and December 2020. A total of 93 features were extracted from the images of each case through 3-dimensional (3D) slicer. After features preprocessing and filtering, 3-4 features were selected by the least absolute shrinkage and selection operator (LASSO) regression algorithm. Prediction models were established using random forest (RF) and support vector machine (SVM) for MTT values. Single-factor receiver operating characteristic (ROC) curve analysis and partial-dependence (PD) profiles were conducted to investigate selected features and prediction models.

Results

Our results showed that prediction models based on RF models had the best performance in frontal lobe {area under the curve (AUC) [95% confidence interval (CI)] =1.000 (1.000-1.000)], parietal lobe [AUC (95% CI) =1.000 (1.000-1.000)], and basal ganglia/thalamus [AUC (95% CI) =0.922 (0.797-1.000)] in the test set, whereas the SVM model performed the best in the temporal lobe [AUC (95% CI) =0.962 (0.876-1.000)] in the test set. The AUC values in the test set were greater than 0.9. The PD profiles showed good robustness and consistency.

Conclusions

Prediction models based on radiomics features extracted from DSA images demonstrate excellent performance in predicting MTT in patients with MMD or MMS, which may provide guidance for future clinical practice.

Application and prospects of AI-based radiomics in ultrasound diagnosis

Artificial intelligence (AI)-based radiomics has attracted considerable research attention in the field of medical imaging, including ultrasound diagnosis. Ultrasound imaging has unique advantages such as high temporal resolution, low cost, and no radiation exposure. This renders it a preferred imaging modality for several clinical scenarios. This review includes a detailed introduction to imaging modalities, including Brightness-mode ultrasound, color Doppler flow imaging, ultrasound elastography, contrast-enhanced ultrasound, and multi-modal fusion analysis. It provides an overview of the current status and prospects of AI-based radiomics in ultrasound diagnosis, highlighting the application of AI-based radiomics to static ultrasound images, dynamic ultrasound videos, and multi-modal ultrasound fusion analysis.

A novel collaborative self-supervised learning method for radiomic data

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

Radiomics Applications in Spleen Imaging: A Systematic Review and Methodological Quality Assessment

The spleen, often referred to as the "forgotten organ", plays numerous important roles in various diseases. Recently, there has been an increased interest in the application of radiomics in different areas of medical imaging. This systematic review aims to assess the current state of the art and evaluate the methodological quality of radiomics applications in spleen imaging. A systematic search was conducted on PubMed, Scopus, and Web of Science. All the studies were analyzed, and several characteristics, such as year of publication, research objectives, and number of patients, were collected. The methodological quality was evaluated using the radiomics quality score (RQS). Fourteen articles were ultimately included in this review. The majority of these articles were published in non-radiological journals (78%), utilized computed tomography (CT) for extracting radiomic features (71%), and involved not only the spleen but also other organs for feature extraction (71%). Overall, the included papers achieved an average RQS total score of 9.71 ± 6.37, corresponding to an RQS percentage of 27.77 ± 16.04. In conclusion, radiomics applications in spleen imaging demonstrate promising results in various clinical scenarios. However, despite all the included papers reporting positive outcomes, there is a lack of consistency in the methodological approaches employed.

Machine learning based on gadoxetic acid-enhanced MRI for differentiating atypical intrahepatic mass-forming cholangiocarcinoma from poorly differentiated hepatocellular carcinoma

PURPOSE

The study was to develop a Gd-EOB-DTPA-enhanced MRI radiomics model for differentiating atypical intrahepatic mass-forming cholangiocarcinoma (aIMCC) from poorly differentiated hepatocellular carcinoma (pHCC).

MATERIALS AND METHODS

A total of 134 patients (51 aIMCC and 83 pHCC) who underwent Gadoxetic acid-enhanced MRI between March 2016 and March 2022 were enrolled in this study and then randomly assigned to the training and validation cohorts by 7:3 (93 patients and 41 patients, respectively). The radiomics features were extracted from the hepatobiliary phase of Gadoxetic acid-enhanced MRI. In the training cohort, the SelectKBest and the least absolute shrinkage and selection operator (LASSO) were used to select the radiomics features. The clinical, radiomics, and clinical-radiomics model were established using four machine learning algorithms. The performance of the model was evaluated by the receiver operating characteristic (ROC) curve. Comparison of the radiomics and clinical-radiomics model was done by the Delong test. The clinical usefulness of the model was evaluated using decision curve analysis (DCA).

RESULTS

In 1132 extracted radiomic features, 15 were selected to develop radiomics signature. For identifying aIMCC and pHCC, the radiomics model constructed by random forest algorithm showed the high performance (AUC = 0.90) in the training cohort. The performance of the clinical-radiomics model (AUC = 0.89) was not significantly different (P = 0.88) from that of the radiomics model constructed by random forest algorithm (AUC = 0.86) in the validation cohort. DCA demonstrated that the clinical-radiomics model constructed by random forest algorithm had a high net clinical benefit.

CONCLUSION

The clinical-radiomics model is an effective tool to distinguish aIMCC from pHCC and may provide additional value for the development of treatment plans.

Machine learning-based radiomics analysis of preoperative functional liver reserve with MRI and CT image

OBJECTIVE

The indocyanine green retention rate at 15 min (ICG-R15) is a useful tool to evaluate the functional liver reserve before hepatectomy for liver cancer. Taking ICG-R15 as criteria, we investigated the ability of a machine learning (ML)-based radiomics model produced by Gd-EOB-DTPA-enhanced hepatic magnetic resonance imaging (MRI) or contrast-enhanced computed tomography (CT) image in evaluating functional liver reserve of hepatocellular carcinoma (HCC) patients.

METHODS

A total of 190 HCC patients with CT, among whom 112 also with MR, were retrospectively enrolled and randomly classified into a training dataset (CT: n = 133, MR: n = 78) and a test dataset (CT: n = 57, MR: n = 34). Then, radiomics features from Gd-EOB-DTPA MRI and CT images were extracted. The features associated with the ICG-R15 classification were selected. Five ML classifiers were used for the ML-model investigation. The accuracy (ACC) and the area under curve (AUC) of receiver operating characteristic (ROC) with 95% confidence intervals (CI) were utilized for ML-model performance evaluation.

RESULTS

A total of 107 different radiomics features were extracted from MRI and CT, respectively. The features related to ICG-R15 which was classified into 10%, 20% and 30% were selected. In MRI groups, classifier XGBoost performed best with its AUC = 0.917 and ACC = 0.882 when the threshold was set as ICG-R15 = 10%. When ICG-R15 = 20%, classifier Random Forest performed best with AUC = 0.979 and ACC = 0.882. When ICG-R15 = 30%, classifier XGBoost performed best with AUC = 0.961 and ACC = 0.941. For CT groups, the classifier XGBoost performed best when ICG-R15 = 10% with AUC = 0.822 and ACC = 0.842. When ICG-R15 = 20%, classifier SVM performed best with AUC = 0.860 and ACC = 0.842. When ICG-R15 = 30%, classifier XGBoost performed best with AUC = 0.938 and ACC = 0.965.

CONCLUSIONS

Both the MRI- and CT-based machine learning models are proved to be valuable noninvasive methods for functional liver reserve evaluation.

Deep learning and ultrasound feature fusion model predicts the malignancy of complex cystic and solid breast nodules with color Doppler images

This study aimed to evaluate the performance of traditional-deep learning combination model based on Doppler ultrasound for diagnosing malignant complex cystic and solid breast nodules. A conventional statistical prediction model based on the ultrasound features and basic clinical information was established. A deep learning prediction model was used to train the training group images and derive the deep learning prediction model. The two models were validated, and their accuracy rates were compared using the data and images of the test group, respectively. A logistic regression method was used to combine the two models to derive a combination diagnostic model and validate it in the test group. The diagnostic performance of each model was represented by the receiver operating characteristic curve and the area under the curve. In the test cohort, the diagnostic efficacy of the deep learning model was better than traditional statistical model, and the combined diagnostic model was better and outperformed the other two models (combination model vs traditional statistical model: AUC: 0.95 > 0.70, P = 0.001; combination model vs deep learning model: AUC: 0.95 > 0.87, P = 0.04). A combination model based on deep learning and ultrasound features has good diagnostic value.

Imaging of Hepatobiliary Cancer

The liver and biliary tree are common sites of primary and secondary malignancies. MRI followed by CT is the mainstay for the imaging characterization of these malignancies with the dynamically acquired contrast enhanced phases being the most important for diagnosis. The liver imaging reporting and data system classification provides a useful framework for reporting lesions in patents with underlying cirrhosis or who are at high risk for developing hepatocellular carcinoma. Detection of metastases is improved with the use of liver specific MRI contrast agents and diffusion weighted sequences. Aside from hepatocellular carcinoma, which is often diagnosed noninvasively, other primary hepatobiliary tumors may require biopsy for definite diagnosis, especially when presenting with nonclassic imaging findings. In this review, we examine the imaging findings of common and less common hepatobiliary tumors.

Radiobioinformatics: A novel bridge between basic research and clinical practice for clinical decision support in diffuse liver diseases

The liver is a multifaceted organ that is responsible for many critical functions encompassing amino acid, carbohydrate, and lipid metabolism, all of which make a healthy liver essential for the human body. Contemporary imaging methodologies have remarkable diagnostic accuracy in discerning focal liver lesions; however, a comprehensive understanding of diffuse liver diseases is a requisite for radiologists to accurately diagnose or predict the progression of such lesions within clinical contexts. Nonetheless, the conventional attributes of radiological features, including morphology, size, margin, density, signal intensity, and echoes, limit their clinical utility. Radiomics is a widely used approach that is characterized by the extraction of copious image features from radiographic depictions, which gives it considerable potential in addressing this limitation. It is worth noting that functional or molecular alterations occur significantly prior to the morphological shifts discernible by imaging modalities. Consequently, the explication of potential mechanisms by multiomics analyses (encompassing genomics, epigenomics, transcriptomics, proteomics, and metabolomics) is essential for investigating putative signal pathway regulations from a radiological viewpoint. In this review, we elaborate on the principal pathological categorizations of diffuse liver diseases, the evaluation of multiomics approaches pertaining to diffuse liver diseases, and the prospective value of predictive models. Accordingly, the overarching objective of this review is to scrutinize the interrelations between radiological features and bioinformatics as well as to consider the development of prediction models predicated on radiobioinformatics as integral components of clinical decision support systems for diffuse liver diseases.

Imaging of pediatric liver tumors: A COG Diagnostic Imaging Committee/SPR Oncology Committee White Paper

Primary hepatic malignancies are relatively rare in the pediatric population, accounting for approximately 1%-2% of all pediatric tumors. Hepatoblastoma and hepatocellular carcinoma are the most common primary liver malignancies in children under the age of 5 years and over the age of 10 years, respectively. This paper provides consensus-based imaging recommendations for evaluation of patients with primary hepatic malignancies at diagnosis and follow-up during and after therapy.

Recognition of liver tumors by predicted hyperspectral features based on patient's Computed Tomography radiomics features

BACKGROUND

Primary liver tumors have posed a serious threat to human life and health, and their early diagnosis is urgent. Therefore, enhancing the accuracy of non-invasive early detection of liver tumors is imperative.

METHODS

Firstly, image enhancement was applied to augment the dataset, resulting in a total of 464 samples after employing seven data augmentation methods. Subsequently, the XGBoost model was utilized to construct and learn the mapping relationship between Computed Tomography (CT) and corresponding hyperspectral imaging (HSI) data. This model enables the prediction of HSI features corresponding to CT features, thereby enriching CT with more comprehensive hyperspectral information.

RESULTS

Four classifiers were employed to discern the presence of tumors in patients. The results demonstrated exceptional performance, with a classification accuracy exceeding 90%.

CONCLUSIONS

This study proposes an artificial intelligence-based methodology that utilizes early CT radiomics features to predict HSI features. Subsequently, the results are utilized for non-invasive tumor prediction and early screening, thereby enhancing the accuracy of non-invasive liver tumor detection.

Artificial Intelligence-Based Opportunities in Liver Pathology-A Systematic Review

BACKGROUND

Artificial Intelligence (AI)-based Deep Neural Networks (DNNs) can handle a wide range of applications in image analysis, ranging from automated segmentation to diagnostic and prediction. As such, they have revolutionized healthcare, including in the liver pathology field.

OBJECTIVE

The present study aims to provide a systematic review of applications and performances provided by DNN algorithms in liver pathology throughout the Pubmed and Embase databases up to December 2022, for tumoral, metabolic and inflammatory fields.

RESULTS

42 articles were selected and fully reviewed. Each article was evaluated through the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool, highlighting their risks of bias.

CONCLUSIONS

DNN-based models are well represented in the field of liver pathology, and their applications are diverse. Most studies, however, presented at least one domain with a high risk of bias according to the QUADAS-2 tool. Hence, DNN models in liver pathology present future opportunities and persistent limitations. To our knowledge, this review is the first one solely focused on DNN-based applications in liver pathology, and to evaluate their bias through the lens of the QUADAS2 tool.

Magnetic resonance imaging for treatment response evaluation and prognostication of hepatocellular carcinoma after thermal ablation

Hepatocellular carcinoma (HCC) accounts for the vast majority of primary liver cancer and constitutes a major global health challenge. Tumor ablation with either radiofrequency ablation (RFA) or microwave ablation (MWA) is recommended as a curative-intent treatment for early-stage HCC. Given the widespread use of thermal ablation in routine clinical practice, accurate evaluation of treatment response and patient outcomes has become crucial in optimizing individualized management strategies. Noninvasive imaging occupies the central role in the routine management of patients with HCC. Magnetic resonance imaging (MRI) could provide full wealth of information with respect to tumor morphology, hemodynamics, function and metabolism. With accumulation of liver MR imaging data, radiomics analysis has been increasingly applied to capture tumor heterogeneity and provide prognostication by extracting high-throughput quantitative imaging features from digital medical images. Emerging evidence suggests the potential role of several qualitative, quantitative and radiomic MRI features in prediction of treatment response and patient prognosis after ablation of HCC. Understanding the advancements of MRI in the evaluation of ablated HCCs may facilitate optimal patient care and improved outcomes. This review provides an overview of the emerging role of MRI in treatment response evaluation and prognostication of HCC patients undergoing ablation. CLINICAL RELEVANCE STATEMENT: MRI-based parameters can help predict treatment response and patient prognosis after HCC ablation and thus guide treatment planning. KEY POINTS: 1. ECA-MRI provides morphological and hemodynamic assessment of ablated HCC. 2. EOB-MRI provides more information for tumor response prediction after ablation. 3. DWI improve the characterization of HCC and optimize treatment decision. 4. Radiomics analysis enables characterization of tumor heterogeneity guidance of clinical decision-making. 5. Further studies with multiple radiologists and sufficient follow-up period are needed.

Radiological Shape of the Tumor Predicts Progression and Survival in Resected Extrahepatic Cholangiocarcinoma

BACKGROUND

The histological features and radiological shape of extrahepatic cholangiocarcinoma (eCCA) have not been widely studied in relation to prognosis. Multi-detector computed tomography (MDCT) is thought to be useful in diagnosis of progress and tumor distribution; it can also show morphological differences (round, triangular, and square forms) at the tumoral obstruction sites. Histological types of eCCA may be revealed, with potential association with tumor growth and survival.

METHODS

We examined the distribution of tumor radiological shape subtypes on MDCT. The surgical outcomes of consecutive patients with eCCA who underwent macroscopic curative resection were reviewed.

RESULTS

CT subtypes in 109 patients were 62 triangular, 35 square, and 12 round. There were clear prognostic differences in long-term survival rates (P < 0.001); 5-year survival rates were 100% in round, 64% in triangular, and 19% in square types. There was no recurrence in any cases of round-type tumor at the site of obstruction. Depth of tumor invasion and rates of nodal involvement were significantly higher in triangular and square-type tumors than in round-type tumors. In papillary adenocarcinoma, radiological obstructions were round type in seven patients (78%) and triangular type in two patients (22%). In tubular adenocarcinoma, all round-type tumors were well differentiated, the ratio of square-type tumors increasing as the degree of differentiation decreased from "well" to "moderate," and "poor" respectively (23%, 39%, 57%; P = 0.033).

CONCLUSIONS

Tumor radiological shape predicts tumor progression, histological type, and survival in eCCA. This information may be helpful in preoperative radiological staging on MDCT.

Radiomics on Gadoxetate Disodium-enhanced MRI: Non-invasively Identifying Glypican 3-Positive Hepatocellular Carcinoma and Postoperative Recurrence

RATIONALE AND OBJECTIVES

To investigate the impact of preoperative gadoxetate disodium (EOB) MRI-based radiomics on predicting glypican 3 (GPC3)-positive expression and the relevant recurrence-free survival (RFS) of HCC ≤ 5 cm.

MATERIALS AND METHODS

Between January 2014 and October 2018, 259 patients with solitary HCC ≤ 5 cm who underwent hepatectomy and preoperative EOB-MRI were retrieved. Multivariate logistic regression was implemented to identify independent predictors for GPC3. By combining five feature selection strategies and three classifiers, 15 GPC3-oriented radiomics models could be constructed, the best of which with independent clinicoradiologic predictors was integrated into the comprehensive nomogram.

RESULTS

GPC3 was an independent risk factor of postoperative recrudescence for HCC. Alpha-fetoprotein >20 ng/mL, homogenous T2 signal and hypointensity on hepatobiliary phase were independently related to GPC3-positive expression in the clinicoradiologic model. With 10 features selected by support vector machines-recursive feature elimination, logistic regression-based classifier achieved the best performance among 15 radiomics models. After five-fold cross-validation, our comprehensive nomogram acquired better average area under receiver operating characteristic curves (training and validation cohorts: 0.931 vs. 0.943) than the clinicoradiologic algorithm (0.738 vs. 0.739) and the optimal radiomics model (0.943 vs. 0.931). Net reclassification indexes further demonstrated the superiority of GPC3 nomogram over clinicoradiologic and radiomics algorithms (46.54%, p < 0.001; 7.84%, p = 0.207). Meanwhile, higher radiomics score significantly shortened the median RFS (from >77.9 to 48.2 months, p = 0.044), which was analogue to that of the histological GPC3-positive phenotype (from >73.9 to 43.2 months, p < 0.001).

CONCLUSIONS

Preoperative EOB-MRI radiomics-based nomogram satisfactorily distinguished GPC3 status and outcomes of solitary HCC ≤ 5 cm.

Detecting liver cirrhosis in computed tomography scans using clinically-inspired and radiomic features

Hepatic cirrhosis is an increasing cause of mortality in developed countries-it is the pathological sequela of chronic liver diseases, and the final liver fibrosis stage. Since cirrhosis evolves from the asymptomatic phase, it is of paramount importance to detect it as quickly as possible, because entering the symptomatic phase commonly leads to hospitalization and can be fatal. Understanding the state of the liver based on the abdominal computed tomography (CT) scans is tedious, user-dependent and lacks reproducibility. We tackle these issues and propose an end-to-end and reproducible approach for detecting cirrhosis from CT. It benefits from the introduced clinically-inspired features that reflect the patient's characteristics which are often investigated by experienced radiologists during the screening process. Such features are coupled with the radiomic ones extracted from the liver, and from the suggested region of interest which captures the liver's boundary. The rigorous experiments, performed over two heterogeneous clinical datasets (two cohorts of 241 and 32 patients) revealed that extracting radiomic features from the liver's rectified contour is pivotal to enhance the classification abilities of the supervised learners. Also, capturing clinically-inspired image features significantly improved the performance of such models, and the proposed features were consistently selected as the important ones. Finally, we showed that selecting the most discriminative features leads to the Pareto-optimal models with enhanced feature-level interpretability, as the number of features was dramatically reduced (280×) from thousands to tens.

Predicting hepatocellular carcinoma early recurrence after ablation based on magnetic resonance imaging radiomics nomogram

BACKGROUND

The aim of this study is to investigate a model for predicting the early recurrence of hepatocellular carcinoma (HCC) after ablation.

METHODS

A total of 181 patients with HCC after ablation (train group was 119 cases; validation group was 62 cases) were enrolled. The cases of early recurrence in the set of train and validation were 63 and 31, respectively. Radiomics features were extracted from the enhanced magnetic resonance imaging scanning, including pre-contrast injection, arterial phase, late arterial phase, portal venous phase, and delayed phase. The least absolute shrinkage and selection operator cox proportional hazards regression after univariate and multivariate analysis was used to screen radiomics features and build integrated models. The nomograms predicting recurrence and survival of patients of HCC after ablation were established based on the clinical, imaging, and radiomics features. The area under the curve (AUC) of the receiver operating characteristic curve and C-index for the train and validation group was used to evaluate model efficacy.

RESULTS

Four radiomics features were selected out of 34 texture features to formulate the rad-score. Multivariate analyses suggested that the rad-score, number of lesions, integrity of the capsule, pathological type, and alpha-fetoprotein were independent influencing factors. The AUC of predicting early recurrence at 1, 2, and 3 years in the train group was 0.79 (95% CI: 0.72-0.88), 0.72 (95% CI: 0.63-0.82), and 0.71 (95% CI: 0.61-0.83), respectively. The AUC of predicting early recurrence at 1, 2, and 3 years in the validation group was 0.72 (95% CI: 0.58-0.84), 0.61 (95% CI: 0.45-0.78) and 0.64 (95% CI: 0.40-0.87).

CONCLUSION

The model for early recurrence of HCC after ablation based on the clinical, imaging, and radiomics features presented good predictive performance. This may facilitate the early treatment of patients.

Radiomics in Abdominopelvic Solid-Organ Oncologic Imaging: Current Status

Radiomics is the process of extraction of high-throughput quantitative imaging features from medical images. These features represent noninvasive quantitative biomarkers that go beyond the traditional imaging features visible to the human eye. This article first reviews the steps of the radiomics pipeline, including image acquisition, ROI selection and image segmentation, image preprocessing, feature extraction, feature selection, and model development and application. Current evidence for the application of radiomics in abdominopelvic solid-organ cancers is then reviewed. Applications including diagnosis, subtype determination, treatment response assessment, and outcome prediction are explored within the context of hepatobiliary and pancreatic cancer, renal cell carcinoma, prostate cancer, gynecologic cancer, and adrenal masses. This literature review focuses on the strongest available evidence, including systematic reviews, meta-analyses, and large multicenter studies. Limitations of the available literature are highlighted, including marked heterogeneity in radiomics methodology, frequent use of small sample sizes with high risk of overfitting, and lack of prospective design, external validation, and standardized radiomics workflow. Thus, although studies have laid a foundation that supports continued investigation into radiomics models, stronger evidence is needed before clinical adoption.

Artificial intelligence for precision medicine in autoimmune liver disease

Autoimmune liver diseases (AiLDs) are rare autoimmune conditions of the liver and the biliary tree with unknown etiology and limited treatment options. AiLDs are inherently characterized by a high degree of complexity, which poses great challenges in understanding their etiopathogenesis, developing novel biomarkers and risk-stratification tools, and, eventually, generating new drugs. Artificial intelligence (AI) is considered one of the best candidates to support researchers and clinicians in making sense of biological complexity. In this review, we offer a primer on AI and machine learning for clinicians, and discuss recent available literature on its applications in medicine and more specifically how it can help to tackle major unmet needs in AiLDs.

Artificial intelligence performance in image-based ovarian cancer identification: A systematic review and meta-analysis

BACKGROUND

Accurate identification of ovarian cancer (OC) is of paramount importance in clinical treatment success. Artificial intelligence (AI) is a potentially reliable assistant for the medical imaging recognition. We systematically review articles on the diagnostic performance of AI in OC from medical imaging for the first time.

METHODS

The Medline, Embase, IEEE, PubMed, Web of Science, and the Cochrane library databases were searched for related studies published until August 1, 2022. Inclusion criteria were studies that developed or used AI algorithms in the diagnosis of OC from medical images. The binary diagnostic accuracy data were extracted to derive the outcomes of interest: sensitivity (SE), specificity (SP), and Area Under the Curve (AUC). The study was registered with the PROSPERO, CRD42022324611.

FINDINGS

Thirty-four eligible studies were identified, of which twenty-eight studies were included in the meta-analysis with a pooled SE of 88% (95%CI: 85-90%), SP of 85% (82-88%), and AUC of 0.93 (0.91-0.95). Analysis for different algorithms revealed a pooled SE of 89% (85-92%) and SP of 88% (82-92%) for machine learning; and a pooled SE of 88% (84-91%) and SP of 84% (80-87%) for deep learning. Acceptable diagnostic performance was demonstrated in subgroup analyses stratified by imaging modalities (Ultrasound, Magnetic Resonance Imaging, or Computed Tomography), sample size (≤300 or >300), AI algorithms versus clinicians, year of publication (before or after 2020), geographical distribution (Asia or non Asia), and the different risk of bias levels (≥3 domain low risk or < 3 domain low risk).

INTERPRETATION

AI algorithms exhibited favorable performance for the diagnosis of OC through medical imaging. More rigorous reporting standards that address specific challenges of AI research could improve future studies.

FUNDING

This work was supported by the Natural Science Foundation of China (No. 82073647 to Q-JW and No. 82103914 to T-TG), LiaoNing Revitalization Talents Program (No. XLYC1907102 to Q-JW), and 345 Talent Project of Shengjing Hospital of China Medical University (No. M0268 to Q-JW and No. M0952 to T-TG).

Quantitative Analysis of Liver Disease Using MRI-Based Radiomic Features of the Liver and Spleen

Background: Radiomics extracts quantitative image features to identify biomarkers for characterizing disease. Our aim was to characterize the ability of radiomic features extracted from magnetic resonance (MR) imaging of the liver and spleen to detect cirrhosis by comparing features from patients with cirrhosis to those without cirrhosis. Methods: This retrospective study compared MR-derived radiomic features between patients with cirrhosis undergoing hepatocellular carcinoma screening and patients without cirrhosis undergoing intraductal papillary mucinous neoplasm surveillance between 2015 and 2018 using the same imaging protocol. Secondary analyses stratified the cirrhosis cohort by liver disease severity using clinical compensation/decompensation and Model for End-Stage Liver Disease (MELD). Results: Of 167 patients, 90 had cirrhosis with 68.9% compensated and median MELD 8. Combined liver and spleen radiomic features generated an AUC 0.94 for detecting cirrhosis, with shape and texture components contributing more than size. Discrimination of cirrhosis remained high after stratification by liver disease severity. Conclusions: MR-based liver and spleen radiomic features had high accuracy in identifying cirrhosis, after stratification by clinical compensation/decompensation and MELD. Shape and texture features performed better than size features. These findings will inform radiomic-based applications for cirrhosis diagnosis and severity.

Radiomics: a primer on high-throughput image phenotyping

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

Clinical application of deep learning and radiomics in hepatic disease imaging: a systematic scoping review

OBJECTIVE

Artificial intelligence (AI) has begun to play a pivotal role in hepatic imaging. This systematic scoping review summarizes the latest progress of AI in evaluating hepatic diseases based on computed tomography (CT) and magnetic resonance (MR) imaging.

METHODS

We searched PubMed and Web of Science for publications, using terms related to deep learning, radiomics, imaging methods (CT or MR), and the liver. Two reviewers independently selected articles and extracted data from each eligible article. The Quality Assessment of Diagnostic Accuracy Studies-AI (QUADAS-AI) tool was used to assess the risk of bias and concerns regarding applicability.

RESULTS

The screening identified 45 high-quality publications from 235 candidates, including 8 on diffuse liver diseases and 37 on focal liver lesions. Nine studies used deep learning and 36 studies used radiomics. All 45 studies were rated as low risk of bias in patient selection and workflow, but 36 (80%) were rated as high risk of bias in the index test because they lacked external validation. In terms of concerns regarding applicability, all 45 studies were rated as low concerns. These studies demonstrated that deep learning and radiomics can evaluate liver fibrosis, cirrhosis, portal hypertension, and a series of complications caused by cirrhosis, predict the prognosis of malignant hepatic tumors, and differentiate focal hepatic lesions.

CONCLUSIONS

The latest studies have shown that deep learning and radiomics based on hepatic CT and MR imaging have potential application value in the diagnosis, treatment evaluation, and prognosis prediction of common liver diseases. The AI methods may become useful tools to support clinical decision-making in the future.

ADVANCES IN KNOWLEDGE

Deep learning and radiomics have shown their potential in the diagnosis, treatment evaluation, and prognosis prediction of a series of common diffuse liver diseases and focal liver lesions.