Texture analysis of the liver at MDCT for assessing hepatic fibrosis

Post-contrast CT liver attenuation alone is superior to the liver-spleen difference for identifying moderate hepatic steatosis

OBJECTIVE

To assess the diagnostic performance of post-contrast CT for predicting moderate hepatic steatosis in an older adult cohort undergoing a uniform CT protocol, utilizing hepatic and splenic attenuation values.

MATERIALS AND METHODS

A total of 1676 adults (mean age, 68.4 ± 10.2 years; 1045M/631F) underwent a CT urothelial protocol that included unenhanced, portal venous, and 10-min delayed phases through the liver and spleen. Automated hepatosplenic segmentation for attenuation values (in HU) was performed using a validated deep-learning tool. Unenhanced liver attenuation < 40.0 HU, corresponding to > 15% MRI-based proton density fat, served as the reference standard for moderate steatosis.

RESULTS

The prevalence of moderate or severe steatosis was 12.9% (216/1676). The diagnostic performance of portal venous liver HU in predicting moderate hepatic steatosis (AUROC = 0.943) was significantly better than the liver-spleen HU difference (AUROC = 0.814) (p < 0.001). Portal venous phase liver thresholds of 80 and 90 HU had a sensitivity/specificity for moderate steatosis of 85.6%/89.6%, and 94.9%/74.7%, respectively, whereas a liver-spleen difference of -40 HU and -10 HU had a sensitivity/specificity of 43.5%/90.0% and 92.1%/52.5%, respectively. Furthermore, livers with moderate-severe steatosis demonstrated significantly less post-contrast enhancement (mean, 35.7 HU vs 47.3 HU; p < 0.001).

CONCLUSION

Moderate steatosis can be reliably diagnosed on standard portal venous phase CT using liver attenuation values alone. Consideration of splenic attenuation appears to add little value. Moderate steatosis not only has intrinsically lower pre-contrast liver attenuation values (< 40 HU), but also enhances less, typically resulting in post-contrast liver attenuation values of 80 HU or less.

CLINICAL RELEVANCE STATEMENT

Moderate steatosis can be reliably diagnosed on post-contrast CT using liver attenuation values alone. Livers with at least moderate steatosis enhance less than those with mild or no steatosis, which combines with the lower intrinsic attenuation to improve detection.

KEY POINTS

The liver-spleen attenuation difference is frequently utilized in routine practice but appears to have performance limitations. The liver-spleen attenuation difference is less effective than liver attenuation for moderate steatosis. Moderate and severe steatosis can be identified on standard portal venous phase CT using liver attenuation alone.

CT-based radiomics for predicting pathological grade in hepatocellular carcinoma

Objective

To construct and validate radiomics models for hepatocellular carcinoma (HCC) grade predictions based on contrast-enhanced CT (CECT).

Methods

Patients with pathologically confirmed HCC after surgery and underwent CECT at our institution between January 2016 and December 2020 were enrolled and randomly divided into training and validation datasets. With tumor segmentation and feature extraction, radiomic models were constructed using univariate analysis, followed by least absolute shrinkage and selection operator (LASSO) regression. In addition, combined models with clinical factors and radiomics scores (Radscore) were constructed using logistic regression. Finally, all models were evaluated using the receiver operating characteristic (ROC) curve with the area under the curve (AUC), calibration curve, and decision curve analysis (DCA).

Results

In total 242 patients were enrolled in this study, of whom 170 and 72 formed the training and validation datasets, respectively. The arterial phase and portal venous phase (AP+VP) radiomics model were evaluated as the best for predicting HCC pathological grade among all the models built in our study (AUC = 0.981 in the training dataset; AUC = 0.842 in the validation dataset) and was used to build a nomogram. Furthermore, the calibration curve and DCA indicated that the AP+VP radiomics model had a satisfactory prediction efficiency.

Conclusions

Low- and high-grade HCC can be distinguished with good diagnostic performance using a CECT-based radiomics model.

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

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

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

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

Noninvasive assessment of significant liver fibrosis in rabbits by spectral CT parameters and texture analysis

PURPOSE

Noninvasive assessment of significant liver fibrosis in rabbits by spectral CT parameters and texture analysis.

MATERIALS AND METHODS

Thirty-three rabbits were randomly divided into 27 carbon tetrachloride-induced liver fibrosis group and 6 control group. Spectral CT contrast-enhanced scan was performed in batches, and the liver fibrosis was staged according to the histopathological results. The portal venous phase spectral CT parameters [70 keV CT value, normalized iodine concentration (NIC), spectral HU curve slope (λHU)] were measured, and MaZda texture analysis was performed on 70 keV monochrome images. Three dimensionality reduction methods and four statistical methods in B11 module were used to perform discriminant analysis and calculate misclassified rate (MCR), and ten texture features under the lowest combination of MCR were statistically analyzed. Receiver operating characteristic curve (ROC) was used to calculate the diagnostic performance of spectral parameters and texture features for significant liver fibrosis. Finally, the binary logistic regression was used to further screen independent predictors and establish model.

RESULTS

A total of 23 experimental rabbits and 6 control rabbits were included, of which 16 had significant liver fibrosis. Three spectral CT parameters with significant liver fibrosis were significantly lower than those of non-significant liver fibrosis (p < 0.05), and the AUC ranged from 0.846 to 0.913. The combination analysis of mutual information (MI) and nonlinear discriminant analysis (NDA) had the lowest MCR, which with 0%. In the filtered texture features, four were statistically significant and AUC > 0.5, ranges from 0.764 to 0.875. The logistic regression model showed that Perc.90% and NIC could be used as independent predictors, the overall prediction accuracy of the model was 89.7% and the AUC was 0.976.

CONCLUSION

Spectral CT parameters and texture features have high diagnostic value for predicting significant liver fibrosis in rabbits, and the combination of the two can improve its diagnostic efficiency.

Development of a Radiomics-Based Model to Predict Graft Fibrosis in Liver Transplant Recipients: A Pilot Study

Liver Transplantation is complicated by recurrent fibrosis in 40% of recipients. We evaluated the ability of clinical and radiomic features to flag patients at risk of developing future graft fibrosis. CT scans of 254 patients at 3-6 months post-liver transplant were retrospectively analyzed. Volumetric radiomic features were extracted from the portal phase using an Artificial Intelligence-based tool (PyRadiomics). The primary endpoint was clinically significant (≥F2) graft fibrosis. A 10-fold cross-validated LASSO model using clinical and radiomic features was developed. In total, 75 patients (29.5%) developed ≥F2 fibrosis by a median of 19 (4.3-121.8) months. The maximum liver attenuation at the venous phase (a radiomic feature reflecting venous perfusion), primary etiology, donor/recipient age, recurrence of disease, brain-dead donor, tacrolimus use at 3 months, and APRI score at 3 months were predictive of ≥F2 fibrosis. The combination of radiomics and the clinical features increased the AUC to 0.811 from 0.793 for the clinical-only model (p = 0.008) and from 0.664 for the radiomics-only model (p < 0.001) to predict future ≥F2 fibrosis. This pilot study exploring the role of radiomics demonstrates that the addition of radiomic features in a clinical model increased the model's performance. Further studies are required to investigate the generalizability of this experimental tool.

A radiomics model for predicting the outcome of endovascular abdominal aortic aneurysm repair based on machine learning

OBJECTIVE

This study aimed to develop a radiomics model to predict the outcome of endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA), based on machine learning (ML) algorithms.

METHODS

We retrospectively reviewed 711 patients with infra-renal AAA who underwent elective EVAR procedures between January 2016 and December 2019 at our single center. The radiomics features of AAA were extracted using Pyradiomics. Pearson correlation analysis, analysis of variance (ANOVA), least absolute shrinkage, and selection operator (LASSO) regression were applied to determine the predictors for EVAR-related severe adverse events (SAEs). Eighty percent of patients were classified as the training set and the remaining 20 percent of patients were classified as the test set. The selected features were used to build a radiomics model in training set using different ML algorithms. The performance of each model was assessed using the area under the curve (AUC) from the receiver operating characteristic (ROC) curve in the test set.

RESULTS

A total of 493 patients were enrolled in this study, the mean follow-up time was 32 months. During the follow-up, 156 (31.6%) patients experienced EVAR-related SAEs. A total of 1223 radiomics features were extracted from each patient, of which 30 radiomics features were finally identified. The quantitative performance assessment and the ROC curves indicated that the logistics regression (LR) model had better predictive value than others, with accuracy, 0.86; AUC, 0.93; and F1 score, 0.91. The Rad-score waterfall plot showed that the overall amount of error was small both in the training set and in the test set. Calibration curve showed that the calibration degree of the training set and the test set were good (p > 0.05). Decision curve analysis (threshold 0.32) demonstrated that the model had good clinical applicability.

CONCLUSION

Our radiomics model could be used as an efficient and adjunctive tool to predict the outcome after EVAR.

Predicting endocrine function after total pancreatectomy and islet cell autotransplantation: A novel approach utilizing computed tomography texture analysis

BACKGROUND

Islet cell autotransplantation is an effective method to prevent morbidity associated with type IIIc diabetes after total pancreatectomy. However, there is no valid method to predict long-term endocrine function. Our aim was to assess computed tomography texture analysis as a strategy to predict long-term endocrine function after total pancreatectomy and islet cell autotransplantation.

METHODS

All patients undergoing total pancreatectomy and islet cell autotransplantation from 2007 to 2020 who had high-quality preoperative computed tomography imaging available for texture analysis were included. The primary outcome was optimal long-term endocrine function, defined as stable glycemic control with <10 units of insulin/day.

RESULTS

Sixty-three patients met inclusion criteria. Median yield was 6,111 islet equivalent/kg body weight. At a median follow-up of 64.2 months, 12.7% (n = 8) of patients were insulin independent and 39.7% (n = 25) demonstrated optimal endocrine function. Neither total islet equivalent nor islet equivalent/kg body weight alone were associated with optimal endocrine function. To improve endocrine function prediction, computed tomography texture analysis parameters were analyzed, identifying an association between kurtosis (odds ratio, 2.32; 95% confidence interval, 1.08-4.80; P = .02) and optimal endocrine function. Sensitivity analysis discovered a cutoff for kurtosis = 0.60, with optimal endocrine function seen in 66.7% with kurtosis ≥0.60, compared with only 26.2% with kurtosis <0.60 (P < .01). On multivariate logistic regression including islet equivalent yield, only kurtosis ≥0.60 (odds ratio, 5.61; 95% confidence interval, 1.56-20.19; P = .01) and fewer small islet equivalent (odds ratio, 1.00; 95% confidence interval, 1.00-1.00; P = .02) were associated with optimal endocrine function, with the whole model demonstrating excellent prediction of long-term endocrine function (area under the curve, 0.775).

CONCLUSION

Computed tomography texture analysis can provide qualitative data, that when used in combination with quantitative islet equivalent yield, can accurately predict long-term endocrine function after total pancreatectomy and islet cell autotransplantation.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Noninvasive staging of liver fibrosis: review of current quantitative CT and MRI-based techniques

Liver fibrosis features excessive protein accumulation in the liver interstitial space resulting from repeated tissue injury due to chronic liver disease. Liver fibrosis eventually proceeds to cirrhosis and associated complications. So, early diagnosis and staging of liver fibrosis are of vital importance for clinical treatment. Liver biopsy remains the gold standard for the diagnosing and staging of fibrosis, but it is suboptimal due to various limitations. Recently, efforts have been made to migrate toward noninvasive techniques for assessing liver fibrosis. CT is relatively easy to perform, relatively standardized for different scanners, and does not require additional hardware in liver fibrosis staging. MRI is frequently performed to characterize indeterminate liver lesions. Because it does not use ionizing radiation and features high image contrast, its role has increased in the staging of liver fibrosis. More recently, several studies on liver fibrosis staging using deep learning algorithms in CT or MRI have been proposed and have shown meaningful results. In this review, we summarize the basic concept, diagnostic performance, and advantages and limitations of each technique to noninvasively stage liver fibrosis.

Development of a classification method for mild liver fibrosis using non-contrast CT image

PURPOSE

Detection of early-stage liver fibrosis has direct clinical implications on patient management and treatment. The aim of this paper is to develop a non-invasive, cost-effective method for classifying liver disease between "non-fibrosis" (F0) and "fibrosis" (F1-F4), and to evaluate the classification performance quantitatively.

METHODS

Image data from 75 patients who underwent a simultaneous liver biopsy and non-contrast CT examination were used for this study. Non-contrast CT image texture features such as wavelet-based features, standard deviation of variance filter, and mean CT number were calculated in volumes of interest (VOIs) positioned within the liver parenchyma. In addition, a combined feature was calculated using logistic regression with L2-norm regularization to further improve fibrosis detection. Based on the final pathology from the liver biopsy, the patients were labelled either as "non-fibrosis" or "fibrosis". Receiver-operating characteristic (ROC) curve, area under the ROC curve (AUROC), specificity, sensitivity, and accuracy were determined for the algorithm to differentiate between "non-fibrosis" and "fibrosis".

RESULTS

The combined feature showed the highest classification performance with an AUROC of 0.86, compared to the wavelet-based feature (AUROC, 0.76), the standard deviation of variance filter (AUROC, 0.65), and mean CT number (AUROC, 0.84). The combined feature's specificity, sensitivity, and accuracy were 0.66, 0.88, and 0.76, respectively, showing the most promising results.

CONCLUSION

A new non-invasive and cost-effective method was developed to classify liver diseases between "non-fibrosis" (F0) and "fibrosis" (F1-F4). The proposed method makes it possible to detect liver fibrosis in asymptomatic patients using non-contrast CT images for better patient management and treatment.

Usefulness of Noncontrast MRI-Based Radiomics Combined Clinic Biomarkers in Stratification of Liver Fibrosis

PURPOSE

To develop and validate a radiomic nomogram based on texture features from out-of-phase T1W images and clinical biomarkers in prediction of liver fibrosis.

MATERIALS AND METHODS

Patients clinically diagnosed with chronic liver fibrosis who underwent liver biopsy and noncontrast MRI were enrolled. All patients were assigned to the nonsignificant fibrosis group with fibrosis stage <2 and the significant fibrosis group with stage ≥2. Texture parameters were extracted from out-of-phase T1-weighted (T1W) images and calculated using the Artificial Intelligent Kit (AK). Boruta and LASSO regressions were used for feature selection and a multivariable logistic regression was used for construction of a combinational model integrating radiomics and clinical biomarkers. The performance of the models was assessed by using the receiver operator curve (ROC) and decision curve.

RESULTS

ROC analysis of the radiomics model that included the most discriminative features showed AUCs of the training and test groups were 0.80 and 0.78. A combinational model integrating RADscore and fibrosis 4 index was established. ROC analysis of the training and test groups showed good to excellent performance with AUC of 0.93 and 0.86. Decision curves showed the combinational model added more net benefit than radiomic and clinical models alone.

CONCLUSIONS

The study presents a combinational model that incorporates RADscore and clinical biomarkers, which is promising in classification of liver fibrosis.

A New SteatoScore in the Evaluation of Non-Alcoholic Liver Disease in Oncologic Patients

Purpose

The aims of this study were to evaluate the reproducibility of a new multi-parametric steatoscore (new SteatoScore) in oncologic patients with non-alcoholic fatty liver disease (NAFLD) and to compare it with computed tomography (CT).

Materials and Methods

Fifty-one (31 men, 20 women) oncologic patients, with a mean age and weight of 63.9 years and 78.33 kg, respectively, were retrospectively enrolled in the study. Patients underwent ultrasound (US) and computed tomography (CT) examinations as part of their oncologic follow-up protocol. US examinations were performed by using a 3.5-MHz convex probe. During the US examination, three standardized clips were obtained in each patient. Two operators performed all measurements, one of whom repeated the processing twice in 1 year. Hepatic/renal ratio (HR), attenuation rate (AR), diaphragm visualization (DV), hepatic/portal vein ratio (HPV), and portal vein wall visualization (PVW) were acquired and calculated by using Matlab and inserted in a multi-parametric algorithm called new SteatoScore. On unenhanced CT scan, hepatic attenuation (HA), liver-spleen difference (L-S), and liver/spleen ratio (L/S) were measured by placement of a region of interest (ROI) within liver and spleen parenchyma, avoiding areas with vessels and biliary ducts.

Results

The intra-observer variability was greater than the inter-observer one, with intraclass correlation coefficient (ICC) values of 0.94 and 0.97, respectively. Correlation between single US and CT parameters provided an agreement in no case exceeding 50%. New SteatoScore showed high reproducibility, and high coefficient of correlation with L-S (R = −0.64; p < 0.0001) and L/S (R = −0.62; p < 0.0001) at CT.

Conclusion

New SteatoScore has a high reproducibility and shows a good correlation with unenhanced CT in evaluation of oncologic patients with NAFLD.

Effects of slice thickness on CT radiomics features and models for staging liver fibrosis caused by chronic liver disease

OBJECTIVES

To investigate the effects of slice thickness on CT radiomics features and models for staging liver fibrosis.

METHODS

A total of 108 pathologically confirmed liver fibrosis patients from a single center were retrospectively collected and divided into different groups. Both thick (5- or 7-mm) and thin slices (1.3- or 2-mm) were analyzed. A fivefold cross-validation with 100 repeats was conducted. The minimum redundancy-maximum relevance algorithm was used to reduce the radiomics features, and the top 10 ranking features were included for further analysis for each loop. The random forest was used for model establishment. The models with median AUC were selected for the assessment of the discriminative performance for both datasets. Mutual features selected by the models with AUC > 0.8 were searched and considered as the most predictive ones.

RESULTS

A total of 162 and 643 radiomics features with excellent reliability were selected from thick- and thin-slice datasets, respectively. The overall discriminative performance of the 500 AUCs from the thin-slice dataset was better than the thick slice. The median AUC values of the thick-sliced datasets were significantly lower than those of the thin-sliced datasets (0.78 and 0.90 for differentiating F1 vs. F2-4, 0.72 and 0.85 for differentiating F1-2 vs. F3-4, both P = 0.03). For differentiating F1-3 vs. F4, no significant difference was found (0.85 vs 0.94, P = 0.15). Six mutual predictive features across all the datasets were found.

CONCLUSIONS

The radiomics features extracted from thin-slice images and their corresponding models were better and more stable for staging liver fibrosis.

Value-added Opportunistic CT Screening: State of the Art

Opportunistic CT screening leverages robust imaging data embedded within abdominal and thoracic scans that are generally unrelated to the specific clinical indication and have heretofore gone largely unused. This incidental imaging information may prove beneficial to patients in terms of wellness, prevention, risk profiling, and presymptomatic detection of relevant disease. The growing interest in CT-based opportunistic screening relates to a confluence of factors: the objective and generalizable nature of CT-based body composition measures, the emergence of fully automated explainable AI solutions, the sheer volume of body CT scans performed, and the increasing emphasis on precision medicine and value-added initiatives. With a systematic approach to body composition and other useful CT markers, initial evidence suggests that their ability to help radiologists assess biologic age and predict future adverse cardiometabolic events rivals even the best available clinical reference standards. Emerging data suggest that standalone "intended" CT screening over an unorganized opportunistic approach may be justified, especially when combined with established cancer screening. This review will discuss the current status of opportunistic CT screening, including specific body composition markers and the various disease processes that may be impacted. The remaining hurdles to widespread clinical adoption include generalization to more diverse patient populations, disparate technical settings, and reimbursement.

Value of Histogram of Gray-Scale Ultrasound Image in Differential Diagnosis of Small Triple Negative Breast Invasive Ductal Carcinoma and Fibroadenoma

Objective

To investigate the value of gray-scale ultrasound (US) image histogram in the differential diagnosis between small (≤2.00 cm), oval, or round triple negative breast invasive ductal carcinoma (TN-IDC) and fibroadenoma (FA).

Methods

Fifty-five cases of triple negative breast invasive ductal carcinoma (TN-IDC group) and 57 cases of breast fibroadenoma (FA group) confirmed by pathology in Hubei cancer hospital from September 2017 to September 2021 were analyzed retrospectively. The gray-scale US images were analyzed by histogram analysis method, from which some parameters (including mean, variance, skewness, kurtosis and 1st, 10th, 50th, 90th and 99th percentile) can be obtained. Intraclass correlation coefficient (ICC) was used to evaluate the inter observer reliability of histogram parameters. Histogram parameters between the TN-IDC and FA groups were compared using independent Student’s t-test or Mann-Whitney U-test, respectively. In addition, the receiver operating characteristic (ROC) curve analysis was used for the significant parameters to calculate the differential diagnosis efficiency.

Results

All the histogram parameters showed excellent inter-reader consistency, with the ICC values ranged from 0.883 to 0.999. The mean value, 1st, 10th, 50th, 90th and 99th percentiles of TN-IDC group were significantly lower than those of FA group (P < 0.05). The area under ROC curve (AUC) values of mean and n percentiles were from 0.807 to 0.848. However, there were no significant differences in variance, skewness and kurtosis between the two groups (P > 0.05).

Conclusion

Histogram analysis of gray-scale US images can well distinguish small, oval, or round TN-IDC from FA.

CT-based radiomics model for preoperative prediction of hepatic encephalopathy after transjugular intrahepatic portosystemic shunt

OBJECTIVE

To develop and evaluate a machine learning-based CT radiomics model for the prediction of hepatic encephalopathy (HE) after transjugular intrahepatic portosystemic shunt (TIPS).

METHODS

A total of 106 patients who underwent TIPS placement were consecutively enrolled in this retrospective study. Regions of interest (ROIs) were drawn on unenhanced, arterial phase, and portal venous phase CT images, and radiomics features were extracted, respectively. A radiomics model was established to predict the occurrence of HE after TIPS by using random forest algorithm and 10-fold cross-validation. Receiver operating characteristic (ROC) curves were performed to validate the capability of the radiomics model and clinical model on the training, test and original data sets, respectively.

RESULTS

The radiomics model showed favorable discriminatory ability in the training cohort with an area under the curve (AUC) of 0.899 (95% CI, 0.848 to 0.951), while in the test cohort, it was confirmed with an AUC of 0.887 (95% CI, 0.760 to 1.00). After applying this model to original data set, it had an AUC of 0.955 (95% CI, 0.896 to 1.00). A clinical model was also built with an AUC of 0.649 (95% CI, 0.530 to 0.767) in the original data set, and a Delong test demonstrated its relative lower efficiency when compared with the radiomics model (p < 0.05).

CONCLUSION

Machine learning-based CT radiomics model performed better than traditional clinical parameter-based models in the prediction of post-TIPS HE.

ADVANCES IN KNOWLEDGE

Radiomics model for the prediction of post-TIPS HE was built based on feature extraction from routine acquired pre-operative CT images and feature selection by random forest algorithm, which showed satisfied performance and proved the advantages of machine learning in this field.

Combining Hepatic and Splenic CT Radiomic Features Improves Radiomic Analysis Performance for Liver Fibrosis Staging

Background: The exact focus of computed tomography (CT)-based artificial intelligence techniques when staging liver fibrosis is still not exactly known. This study aimed to determine both the added value of splenic information to hepatic information, and the correlation between important radiomic features and information exploited by deep learning models for liver fibrosis staging by CT-based radiomics. Methods: The study design is retrospective. Radiomic features were extracted from both liver and spleen on portal venous phase CT images of 252 consecutive patients with histologically proven liver fibrosis stages between 2006 and 2018. The radiomics analyses for liver fibrosis staging were done by hepatic and hepatic–splenic features, respectively. The most predictive radiomic features were automatically selected by machine learning models. Results: When using splenic–hepatic features in the CT-based radiomics analysis, the average accuracy rates for significant fibrosis, advanced fibrosis, and cirrhosis were 88%, 82%, and 86%, and area under the receiver operating characteristic curves (AUCs) were 0.92, 0.81, and 0.85. The AUC of hepatic–splenic-based radiomics analysis with the ensemble classifier was 7% larger than that of hepatic-based analysis (p < 0.05). The most important features selected by machine learning models included both hepatic and splenic features, and they were consistent with the location maps indicating the focus of deep learning when predicting liver fibrosis stage. Conclusions: Adding CT-based splenic radiomic features to hepatic radiomic features increases radiomics analysis performance for liver fibrosis staging. The most important features of the radiomics analysis were consistent with the information exploited by deep learning.

Texture analysis imaging "what a clinical radiologist needs to know"

Texture analysis has arisen as a tool to explore the amount of data contained in images that cannot be explored by humans visually. Radiomics is a method that extracts a large number of features from radiographic medical images using data-characterisation algorithms. These features, termed radiomic features, have the potential to uncover disease characteristics. The goal of both radiomics and texture analysis is to go beyond size or human-eye based semantic descriptors, to enable the non-invasive extraction of quantitative radiological data to correlate them with clinical outcomes or pathological characteristics. In the latest years there has been a flourishing sub-field of radiology where texture analysis and radiomics have been used in many settings. It is difficult for the clinical radiologist to cope with such amount of data in all the different radiological sub-fields and to identify the most significant papers. The aim of this review is to provide a tool to better understand the basic principles underlining texture analysis and radiological data mining and a summary of the most significant papers of the latest years.

CT radiomics nomogram for the preoperative prediction of severe post-hepatectomy liver failure in patients with huge (≥ 10 cm) hepatocellular carcinoma

Background

This study aimed to establish a radiomics-based nomogram for predicting severe (grade B or C) post-hepatectomy liver failure (PHLF) in patients with huge (≥ 10 cm) hepatocellular carcinoma (HCC).

Methods

One hundred eighty-six patients with huge HCC (training dataset, n = 131 and test dataset, n = 55) that underwent curative hepatic resection were included in this study. The least absolute shrinkage and selection operator (LASSO) approach was applied to develop a radiomics signature for grade B or C PHLF prediction using the training dataset. A multivariable logistic regression model was used by incorporating radiomics signature and other clinical predictors to establish a radiomics nomogram. Decision tree analysis was performed to stratify the risk for severe PHLF.

Results

The radiomics signature consisting of nine features predicted severe PHLF with AUCs of 0.766 and 0.745 for the training and test datasets. The radiomics nomogram was generated by integrating the radiomics signature, the extent of resection and the model for end-stage liver disease (MELD) score. The nomogram exhibited satisfactory discrimination ability, with AUCs of 0.842 and 0.863 for the training and test datasets, respectively. Based on decision tree analysis, patients were divided into three risk classes: low-risk patients with radiomics score < -0.247 and MELD score < 10 or radiomics score ≥ − 0.247 but underwent partial resections; intermediate-risk patients with radiomics score < − 0.247 but MELD score ≥10; high-risk patients with radiomics score ≥ − 0.247 and underwent extended resections.

Conclusions

The radiomics nomogram could predict severe PHLF in huge HCC patients. A decision tree may be useful in surgical decision-making for huge HCC hepatectomy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12957-021-02459-0.

A Combination Model of Radiomics Features and Clinical Biomarkers as a Nomogram to Differentiate Nonadvanced From Advanced Liver Fibrosis: A Retrospective Study

RATIONALE AND OBJECTIVES

To develop and validate a combination model of radiomics features and clinical biomarkers to differentiate nonadvanced from advanced liver fibrosis.

MATERIALS AND METHODS

One hundred and eight consecutive patients with pathologically diagnosed liver fibrosis were randomly placed in a training or a test cohort at a ratio of 2:1. For each patient, 1674 radiomics features extracted from portal venous phase CT images were reduced by using minimum redundancy and maximum relevant. The optimal features identified were incorporated into the radiomics model. Eight clinical markers were evaluated. Integrated with clinical independent risk factors, a combination model was built. A nomogram was also established from the model. The performance of the models was assessed. Finally, a decision curve analysis was performed to estimate the clinical usefulness of the nomogram.

RESULTS

The radiomics model established using five features achieved a promising level of discrimination between nonadvanced and advanced liver fibrosis. The combination model incorporated the radiomics signature with two clinical biomarkers and showed good calibration and discrimination. The training and testing cohort results of the radiomics model were area under curve values 0.864 and 0.772, accuracy 77.8% and 77.8%, sensitivity 86.7% and 73.1%, and specificity 71.4% and 90.0%, respectively. For the combination model, the training and testing cohort results were area under curve values 0.915 and 0.897, accuracy 83.3% and 86.1%, sensitivity 86% and 80.6%, and specificity 82.6% and 92.3%, respectively. The decision curve indicated the nomogram has potential in clinical application.

CONCLUSION

This combination model provides a promising approach for differentiating non-advanced from advanced liver fibrosis.

Current Status of Radiomics and Deep Learning in Liver Imaging

ABSTRACT

Artificial intelligence is poised to revolutionize medical image. It takes advantage of the high-dimensional quantitative features present in medical images that may not be fully appreciated by humans. Artificial intelligence has the potential to facilitate automatic organ segmentation, disease detection and characterization, and prediction of disease recurrence. This article reviews the current status of artificial intelligence in liver imaging and reviews the opportunities and challenges in clinical implementation.

Virtual Biopsy for Diagnosis of Chemotherapy-Associated Liver Injuries and Steatohepatitis: A Combined Radiomic and Clinical Model in Patients with Colorectal Liver Metastases

Non-invasive diagnosis of chemotherapy-associated liver injuries (CALI) is still an unmet need. The present study aims to elucidate the contribution of radiomics to the diagnosis of sinusoidal dilatation (SinDil), nodular regenerative hyperplasia (NRH), and non-alcoholic steatohepatitis (NASH). Patients undergoing hepatectomy for colorectal metastases after chemotherapy (January 2018-February 2020) were retrospectively analyzed. Radiomic features were extracted from a standardized volume of non-tumoral liver parenchyma outlined in the portal phase of preoperative post-chemotherapy computed tomography. Seventy-eight patients were analyzed: 25 had grade 2-3 SinDil, 27 NRH, and 14 NASH. Three radiomic fingerprints independently predicted SinDil: GLRLM_f3 (OR = 12.25), NGLDM_f1 (OR = 7.77), and GLZLM_f2 (OR = 0.53). Combining clinical, laboratory, and radiomic data, the predictive model had accuracy = 82%, sensitivity = 64%, and specificity = 91% (AUC = 0.87 vs. AUC = 0.77 of the model without radiomics). Three radiomic parameters predicted NRH: conventional_HUQ2 (OR = 0.76), GLZLM_f2 (OR = 0.05), and GLZLM_f3 (OR = 7.97). The combined clinical/laboratory/radiomic model had accuracy = 85%, sensitivity = 81%, and specificity = 86% (AUC = 0.91 vs. AUC = 0.85 without radiomics). NASH was predicted by conventional_HUQ2 (OR = 0.79) with accuracy = 91%, sensitivity = 86%, and specificity = 92% (AUC = 0.93 vs. AUC = 0.83 without radiomics). In the validation set, accuracy was 72%, 71%, and 91% for SinDil, NRH, and NASH. Radiomic analysis of liver parenchyma may provide a signature that, in combination with clinical and laboratory data, improves the diagnosis of CALI.

CT texture analysis of abdominal lesions – Part I.: Liver lesions

Artificial Intelligence and the use of radiomics analysis have been of great interest in the last decade in the field of imaging. CT texture analysis (CTTA) is a new and emerging field in radiomics, which seems promising in the assessment and diagnosis of both focal and diffuse liver lesions. The utilization of CTTA has only been receiving great attention recently, especially for response evaluation and prognostication of different oncological diagnoses. Radiomics, combined with machine learning techniques, offers a promising opportunity to accurately detect or differentiate between focal liver lesions based on their unique texture parameters. In this review article, we discuss the unique ability of radiomics in the diagnostics and prognostication of both focal and diffuse liver lesions. We also provide a brief review of radiogenomics and summarize its potential role of in the non-invasive diagnosis of malignant liver tumors.

Liver segmental volume and attenuation ratio (LSVAR) on portal venous CT scans improves the detection of clinically significant liver fibrosis compared to liver segmental volume ratio (LSVR)

Background

The aim of this proof-of-concept study was to show that the liver segmental volume and attenuation ratio (LSVAR) improves the detection of significant liver fibrosis on portal venous CT scans by adding the liver vein to cava attenuation (LVCA) to the liver segmental volume ratio (LSVR).

Material and methods

Patients who underwent portal venous phase abdominal CT scans and MR elastography (reference standard) within 3 months between 02/2016 and 05/2017 were included. The LSVAR was calculated on portal venous CT scans as LSVR*LVCA, while the LSVR represented the volume ratio between Couinaud segments I-III and IV-VIII, and the LVCA represented the density of the liver veins compared to the density in the vena cava. The LSVAR and LSVR were compared between patients with and without significantly elevated liver stiffness (based on a cutoff value of 3.5 kPa) using the Mann–Whitney U test and ROC curve analysis.

Results

The LSVR and LSVAR allowed significant differentiation between patients with (n = 19) and without (n = 122) significantly elevated liver stiffness (p < 0.001). However, the LSVAR showed a higher area under the curve (AUC = 0.96) than the LSVR (AUC = 0.74). The optimal cutoff value was 0.34 for the LSVR, which detected clinically increased liver stiffness with a sensitivity of 53% and a specificity of 88%. With a cutoff value of 0.67 for the LSVAR, the sensitivity increased to 95% while maintaining a specificity of 89%.

Conclusion

The LSVAR improves the detection of significant liver fibrosis on portal venous CT scans compared to the LSVR.

Liver Fibrosis Assessment

Early diagnosis of hepatic fibrosis (HF) is pivotal for management to cease progression to cirrhosis and hepatocellular carcinoma. HF is the telltale sign of chronic liver disease, and confirmed by liver biopsy, which is an invasive technique and inclined to sampling errors. The morphologic parameters of cirrhosis are assessed on conventional imaging such as on ultrasound (US), computed tomography (CT) and magnetic resonance imaging (MRI). Newer imaging modalities such as magnetic resonance elastography and US elastography are reliable and accurate. More research studies on novel imaging modalities such as MRI with diffusion weighted imaging, enhancement by hepatobiliary contrast agents, and CT using perfusion are essential for earlier diagnosis, surveillance and accurate management. The purpose of this article is to discuss non-invasive CT, MRI, and US imaging modalities for diagnosis and stratify HF.

Opportunistic Screening at Abdominal CT: Use of Automated Body Composition Biomarkers for Added Cardiometabolic Value

Abdominal CT is a frequently performed imaging examination for a wide variety of clinical indications. In addition to the immediate reason for scanning, each CT examination contains robust additional data on body composition that generally go unused in routine clinical practice. There is now growing interest in harnessing this additional information. Prime examples of cardiometabolic information include measurement of bone mineral density for osteoporosis screening, quantification of aortic calcium for assessment of cardiovascular risk, quantification of visceral fat for evaluation of metabolic syndrome, assessment of muscle bulk and density for diagnosis of sarcopenia, and quantification of liver fat for assessment of hepatic steatosis. All of these relevant biometric measures can now be fully automated through the use of artificial intelligence algorithms, which provide rapid and objective assessment and allow large-scale population-based screening. Initial investigations into these measures of body composition have demonstrated promising performance for prediction of future adverse events that matches or exceeds the best available clinical prediction models, particularly when these CT-based measures are used in combination. In this review, the concept of CT-based opportunistic screening is discussed, and an overview of the various automated biomarkers that can be derived from essentially all abdominal CT examinations is provided, drawing heavily on the authors' experience. As radiology transitions from a volume-based to a value-based practice, opportunistic screening represents a promising example of adding value to services that are already provided. If the potentially high added value of these objective CT-based automated measures is ultimately confirmed in subsequent investigations, this opportunistic screening approach could be considered for intentional CT-based screening. ^©RSNA, 2021.

The utility of two-dimensional shear wave elastography and texture analysis for monitoring liver fibrosis in rat model

BACKGROUND

Liver fibrosis is a common pathological change caused by a variety of etiologies. Early diagnosis and timely treatment can reverse or delay disease progression and improve the prognosis. This study aimed to assess the potential utility of two-dimensional shear wave elastography and texture analysis in dynamic monitoring of the progression of liver fibrosis in rat model.

METHODS

Twenty rats were divided into control group (n = 4) and experimental groups (n = 4 per group) with carbon tetrachloride administration for 2, 3, 4, and 6 weeks. The liver stiffness measurement was performed by two-dimensional shear wave elastography, while the optimal texture analysis subsets to distinguish fibrosis stage were generated by MaZda. The results of elastography and texture analysis were validated through comparing with histopathology.

RESULTS

Liver stiffness measurement was 6.09 ± 0.31 kPa in the control group and 7.10 ± 0.41 kPa, 7.80 ± 0.93 kPa, 8.64 ± 0.93 kPa, 9.91 ± 1.13 kPa in the carbon tetrachloride induced groups for 2, 3, 4, 6 weeks, respectively (P < 0.05). By texture analysis, histogram and co-occurrence matrix had the most frequency texture parameters in staging liver fibrosis. Receiver operating characteristic curve of liver elasticity showed that the sensitivity and specificity were 95.0% and 92.5% to discriminate liver fibrosis and non-fibrosis, respectively. In texture analysis, five optimal parameters were selected to classify liver fibrosis and non-fibrosis.

CONCLUSIONS

Two-dimensional shear wave elastography showed potential applications for noninvasive monitoring of the progression of hepatic fibrosis, even in mild fibrosis. Texture analysis can further extract and quantify the texture features in ultrasonic image, which was a supplementary to further visual information and acquired high diagnostic accuracy for severe fibrosis.

Utility of Multiparametric CT for Identification of High-Risk NAFLD

OBJECTIVE. The purpose of this study was to evaluate the utility of laboratory and CT metrics in identifying patients with high-risk nonalcoholic fatty liver disease (NAFLD). MATERIALS AND METHODS. Patients with biopsy-proven NAFLD who underwent CT within 1 year of biopsy were included. Histopathologic review was performed by an experienced gastrointestinal pathologist to determine steatosis, inflammation, and fibrosis. The presence of any lobular inflammation and hepatocyte ballooning was categorized as nonalcoholic steatohepatitis (NASH). Patients with NAFLD and advanced fibrosis (stage F3 or higher) were categorized as having high-risk NAFLD. Aspartate transaminase to platelet ratio index and Fibrosis-4 (FIB-4) laboratory scores were calculated. CT metrics included hepatic attenuation, liver segmental volume ratio (LSVR), splenic volume, liver surface nodularity score, and selected texture features. In addition, two readers subjectively assessed the presence of NASH (present or not present) and fibrosis (stages F0-F4). RESULTS. A total of 186 patients with NAFLD (mean age, 49 years; 74 men and 112 women) were included. Of these, 87 (47%) had NASH and 112 (60%) had moderate to severe steatosis. A total of 51 patients were classified as fibrosis stage F0, 42 as F1, 23 as F2, 37 as F3, and 33 as F4. Additionally, 70 (38%) had advanced fibrosis (stage F3 or F4) and were considered to have high-risk NAFLD. FIB-4 score correlated with fibrosis (ROC AUC of 0.75 for identifying high-risk NAFLD). Of the individual CT parameters, LSVR and splenic volume performed best (AUC of 0.69 for both for detecting high-risk NAFLD). Subjective reader assessment performed best among all parameters (AUCs of 0.78 for reader 1 and 0.79 for reader 2 for detecting high-risk NAFLD). FIB-4 and subjective scores were complementary (combined AUC of 0.82 for detecting high-risk NAFLD). For NASH assessment, FIB-4 performed best (AUC of 0.68), whereas the AUCs were less than 0.60 for all individual CT features and subjective assessments. CONCLUSION. FIB-4 and multiple CT findings can identify patients with high-risk NAFLD (advanced fibrosis or cirrhosis). However, the presence of NASH is elusive on CT.

CT texture analysis in histological classification of epithelial ovarian carcinoma

OBJECTIVES

The study aimed to compare the ability of morphological and texture features derived from contrast-enhanced CT in histological subtyping of epithelial ovarian carcinoma (EOC).

METHODS

Consecutive 205 patients with newly diagnosed EOC who underwent contrast-enhanced CT were included and dichotomised into high-grade serous carcinoma (HGSC) and non-HGSC. Clinical information including age and cancer antigen 125 (CA-125) was documented. The pre-treatment images were analysed using commercial software, TexRAD, by two independent radiologists. Eight qualitative CT morphological features were evaluated, and 36 CT texture features at 6 spatial scale factors (SSFs) were extracted per patient. Features' reduction was based on kappa score, intra-class correlation coefficient (ICC), univariate ROC analysis and Pearson's correlation test. Texture features with ICC ≥ 0.8 were compared by histological subtypes. Patients were randomly divided into training and testing sets by 8:2. Two random forest classifiers were determined and compared: model 1 incorporating selected morphological and clinical features and model 2 incorporating selected texture and clinical features.

RESULTS

HGSC showed specifically higher texture features than non-HGSC (p < 0.05). Both models performed highly in predicting histological subtypes of EOC (model 1: AUC 0.891 and model 2: AUC 0.937), and no statistical significance was found between the two models (p = 0.464).

CONCLUSION

CT texture analysis provides objective and quantitative metrics on tumour characteristics with HGSC demonstrating specifically high texture features. The model incorporating texture analysis could classify histology subtypes of EOC with high accuracy and performed as well as morphological features.

KEY POINTS

• A number of CT morphological and texture features showed good inter- and intra-observer agreements. • High-grade serous ovarian carcinoma showed specifically higher CT texture features than non-high-grade serous ovarian carcinoma. • CT texture analysis could differentiate histological subtypes of epithelial ovarian carcinoma with high accuracy.

Texture Analysis of Gray-Scale Ultrasound Images for Staging of Hepatic Fibrosis

Purpose

Materials and Methods

Results

Conclusion

Noninvasive Assessment of Liver Parenchyma Using Gray-Scale Ultrasound-Based Histogram Analysis in Patients With Chronic Hepatitis B Infection

The aims of this study were to examine the alterations of liver echo-intensity histogram parameters in chronic hepatitis B (CHB) patients and to assess the potential role of histogram parameters in the evaluation of hepatic fibrosis. A total of 52 patients with CHB who underwent liver biopsies were included in the study. The control group consisted of 30 healthy individuals. Histogram parameters were obtained from histogram analysis of gray-scale ultrasound images of both groups. The histogram parameters of the groups were compared. The association of histogram parameters with the grading and staging of histological activity index (HAI) in patients with CHB were evaluated. The patient group had statistically significant lower skewness, kurtosis, and higher variance, mean, 50th, and 90th percentile values compared with control group. When patients with CHB were divided into subgroups according to HAI stage, there was the increasing trend in skewness values and decreasing trend in kurtosis values across subgroups. The first percentile values showed negative correlation with HAI staging in patients with CHB. Ultrasound is a fast, inexpensive, and reproducible imaging method; histogram analysis of gray-scale ultrasound images may provide useful information for evaluation of hepatic fibrosis in CHB patients.

Prediction of liver regeneration in recipients after living-donor liver transplantation in using preoperative CT texture analysis and clinical features

PURPOSE

The aim of the study is to predict the rate of liver regeneration in recipients after living-donor liver transplantation using preoperative CT texture and shape analysis of the future graft.

METHODS

102 donor-recipient pairs who underwent living-donor liver transplantation using right lobe grafts were retrospectively included. We semi-automatically segmented the future graft from preoperative CT. The volume of the future graft (LV_pre) was measured, and texture and shape analyses were performed. The graft liver was segmented from postoperative follow-up CT and the volume of the graft (LV_post) was measured. The regeneration index was defined by the following equation: [(LV_post-LV_pre)/LV_pre] × 100(%). We performed a stepwise, multivariate linear regression analysis to investigate the association between clinical, texture and shape parameters and the RI and to make the best-fit predictive model.

RESULTS

The mean regeneration index was 47.5 ± 38.6%. In univariate analysis, the volume of the future graft, energy, effective diameter, surface area, sphericity, roundness_m, compactness1, and grey-level co-occurrence matrix contrast as well as several clinical parameters were significantly associated with the regeneration index (p < 0.05). The best-fit predictive model for the regeneration index made by multivariate analysis was as follows: Regeneration index (%) = 127.020-0.367 × effective diameter - 1.827 × roundness_m + 47.371 × recipient body surface area (m²) + 12.041 × log(recipient white blood cell count) (× 10³/μL)+ 18.034 (if the donor was female).

CONCLUSION

The effective diameter and roundness_m of the future graft were associated with liver regeneration. Preoperative CT texture analysis of future grafts can be useful for predicting liver regeneration in recipients after living-donor liver transplantation.

Imaging biomarkers of diffuse liver disease: current status

We are happy to introduce this special issue of Abdominal Radiology on "diffuse liver disease". We have invited imaging experts to discuss various topics pertaining to diffuse liver disease, covering a vast array of imaging techniques including ultrasound (US), CT, MRI and new molecular imaging agents. Below, we briefly discussed the current status, limitations, and future directions of imaging biomarkers of diffuse liver disease.

Three-dimensional CT texture analysis of anatomic liver segments can differentiate between low-grade and high-grade fibrosis

Background

CT texture analysis (CTTA) has been successfully used to assess tissue heterogeneity in multiple diseases. The purpose of this work is to demonstrate the value of three-dimensional CTTA in the evaluation of diffuse liver disease. We aimed to develop CTTA based prediction models, which can be used for staging of fibrosis in different anatomic liver segments irrespective of variations in scanning parameters.

Methods

We retrospectively collected CT scans of thirty-two chronic hepatitis patients with liver fibrosis. The CT examinations were performed on either a 16- or a 64-slice scanner. Altogether 354 anatomic liver segments were manually highlighted on portal venous phase images, and 1117 three-dimensional texture parameters were calculated from each segment. The segments were divided between groups of low-grade and high-grade fibrosis using shear-wave elastography. The highly-correlated features (Pearson r > 0.95) were filtered out, and the remaining 453 features were normalized and used in a classification with k-means and hierarchical cluster analysis. The segments were split between the train and test sets in equal proportion (analysis I) or based on the scanner type (analysis II) into 64-slice train 16-slice validation cohorts for machine learning classification, and a subset of highly prognostic features was selected with recursive feature elimination.

Results

A classification with k-means and hierarchical cluster analysis divided segments into four main clusters. The average CT density was significantly higher in cluster-4 (110 HU ± SD = 10.1HU) compared to the other clusters (c1: 96.1 HU ± SD = 11.3HU; p < 0.0001; c2: 90.8 HU ± SD = 16.8HU; p < 0.0001; c3: 93.1 HU ± SD = 17.5HU; p < 0.0001); but there was no difference in liver stiffness or scanner type among the clusters. The optimized random forest classifier was able to distinguish between low-grade and high-grade fibrosis with excellent cross-validated accuracy in both the first and second analysis (AUC = 0.90, CI = 0.85–0.95 vs. AUC = 0.88, CI = 0.84–0.91). The final support vector machine model achieved an excellent prediction rate in the second analysis (AUC = 0.91, CI = 0.88–0.94) and an acceptable prediction rate in the first analysis (AUC = 0.76, CI = 0.67–0.84).

Conclusions

In conclusion, CTTA-based models can be successfully applied to differentiate high-grade from low-grade fibrosis irrespective of the imaging platform. Thus, CTTA may be useful in the non-invasive prognostication of patients with chronic liver disease.

Diagnostic advances of artificial intelligence and radiomics in gastroenterology

Traditional medical imaging, including ultrasound, computed tomography, magnetic resonance imaging, or positron emission tomography, remains widely used diagnostic modalities for gastrointestinal diseases at present. These modalities are used to assess changes in morphology, attenuation, signal intensity, and enhancement characteristics. Gastrointestinal tumors, especially malignant tumors, are commonly seen in clinical practice with an increasing number of deaths each year. Because the imaging manifestations of different diseases usually overlap, accurate early diagnosis of tumor lesions, noninvasive and effective evaluation of tumor staging, and prediction of prognosis remain challenging. Fortunately, traditional medical images contain a great deal of important information that cannot be recognized by human eyes but can be extracted by artificial intelligence (AI) technology, which can quantitatively assess the heterogeneity of lesions and provide valuable information, including therapeutic effects and patient prognosis. With the development of computer technology, the combination of medical imaging and AI technology is considered to represent a promising field in medical image analysis. This new emerging field is called “radiomics”, which makes big data mining and extraction from medical imagery possible and can help clinicians make effective decisions and develop personalized treatment plans. Recently, AI and radiomics have been gradually applied to lesion detection, qualitative and quantitative diagnosis, histopathological grading and staging of tumors, therapeutic efficacy assessment, and prognosis evaluation. In this minireview, we briefly introduce the basic principles and technology of radiomics. Then, we review the research and application of AI and radiomics in gastrointestinal diseases, especially diagnostic advancements of radiomics in the differential diagnosis, treatment option, assessment of therapeutic efficacy, and prognosis evaluation of esophageal, gastric, hepatic, pancreatic, and colorectal diseases.

Feasibility of computed tomography texture analysis of hepatic fibrosis using dual-energy spectral detector computed tomography

PURPOSE

To evaluate feasibility of computer tomography texture analysis (CTTA) at different energy level using dual-energy spectral detector CT for liver fibrosis.

MATERIALS AND METHODS

Eighty-seven patients who underwent a spectral CT examination and had a reference standard of liver fibrosis (histopathologic findings, n = 61, or clinical findings for normal, n = 26) were included. Mean gray-level intensity, mean number of positive pixels (MPP), entropy, skewness, and kurtosis using commercially available software (TexRAD) were compared at different energy levels. Optimal CTTA parameter cutoffs to diagnose liver fibrosis were evaluated. CTTA parameters at different energy levels correlated with liver fibrosis. The association of CTTA parameters with energy level was evaluated.

RESULTS

Mean gray-level intensity, skewness, kurtosis, and entropy showed significant differences between patients with and without clinically significant hepatic fibrosis (P < 0.05). Mean gray-level intensity at 50 keV was significantly positively correlated with liver fibrosis (ρ = 0.502, P < 0.001). To diagnose stages F2-F4, entropy and mean gray-level intensity at low keV level showed the largest area under the curve (AUC; 0.79 and 0.79). Estimated marginal means (EMMs) of mean gray-level intensity showed prominent differences at low energy levels.

CONCLUSION

CTTA parameters from different keV levels demonstrated meaningful accuracy for diagnosis of liver fibrosis or clinically significant hepatic fibrosis.

Deep residual nets model for staging liver fibrosis on plain CT images

PURPOSE

The early diagnosis of liver fibrosis is crucial for the prevention of liver cirrhosis and liver cancer. As gold standard for staging liver fibrosis, liver biopsy is an invasive procedure that carries the risk of serious complications. The aim of this study was to evaluate the performance of the residual neural network (ResNet), a non-invasive methods, for staging liver fibrosis using plain CT images.

METHODS

This retrospective study involved 347 patients subjected to liver CT scanning and liver biopsy. For each patient, we selected three axial images adjacent to the puncture location in the eighth or ninth inter-space on the right side. After processing and enhancement (rotation, translation, and amplification), these images were used as input data for the ResNet model. The model used a fivefold cross-validation method. In each fold, the images of approximately 80% of the total sample size (278 patients) were used for training the ResNet model, the other 20% (69 patients) were used for testing the trained network, with the liver biopsy pathology results as gold standard. The proportion of patients in each fibrosis stage was equal for training and test groups. The final result was the mean of the fivefold cross-validation in the test group. The performance of the ResNet model was evaluated for the test group by receiver operating characteristic (ROC) analysis.

RESULTS

For the ResNet model, the area under the ROC curve (AUC) for assessing cirrhosis (F4), advanced fibrosis (F3 or higher), significant fibrosis (F2 or higher), and mild fibrosis (F1 or higher) was 0.97, 0.94, 0.90, and 0.91, respectively.

CONCLUSIONS

The ResNet model analysis of plain CT images exhibited high diagnostic efficiency for liver fibrosis staging. As a convenient, fast, and economical non-invasive diagnostic method, the ResNet model can be used to assist radiologists and clinicians in liver fibrosis evaluations.

A Nomogram Model of Radiomics and Satellite Sign Number as Imaging Predictor for Intracranial Hematoma Expansion

Background

We aimed to construct and validate a nomogram model based on the combination of radiomic features and satellite sign number for predicting intracerebral hematoma expansion.

Methods

A total of 129 patients from two institutions were enrolled in this study. The preprocessed initial CT images were used for radiomic feature extraction. The ANOVA-Kruskal–Wallis test and least absolute shrinkage and selection operator regression were applied to identify candidate radiomic features and construct the Radscore. A nomogram model was developed by integrating the Radscore with a satellite sign number. The discrimination performance of the proposed model was evaluated by receiver operating characteristic (ROC) analysis, and the predictive accuracy was assessed via a calibration curve. Decision curve analysis (DCA) and Kaplan–Meier (KM) survival analysis were performed to evaluate the clinical value of the model.

Results

Four optimal features were ultimately selected and contributed to the Radscore construction. A positive correlation was observed between the satellite sign number and Radscore (Pearson’s r: 0.451). The nomogram model showed the best performance with high area under the curves in both training cohort (0.881, sensitivity: 0.973; specificity: 0.787) and external validation cohort (0.857, sensitivity: 0.950; specificity: 0.766). The calibration curve, DCA, and KM analysis indicated the high accuracy and clinical usefulness of the nomogram model for hematoma expansion prediction.

Conclusion

A nomogram model of integrated radiomic signature and satellite sign number based on noncontrast CT images could serve as a reliable and convenient measurement of hematoma expansion prediction.

Equilibrium CT Texture Analysis for the Evaluation of Hepatic Fibrosis: Preliminary Evaluation against Histopathology and Extracellular Volume Fraction

Background: Evaluate equilibrium contrast-enhanced CT (EQ-CT) texture analysis (EQ-CTTA) against histologically-quantified fibrosis, serum-based enhanced liver fibrosis panel (ELF) and imaging-based extracellular volume fraction (ECV) in chronic hepatitis. Methods: This study was a re-analysis of image data from a previous prospective study. Pre- and equilibrium-phase post-IV contrast CT datasets were collected from patients with chronic hepatitis with contemporaneous liver biopsy and serum ELF measurement between April 2011 and July 2013. Biopsy samples were analysed to derive collagen proportionate area (CPA). EQ-CTTA was performed with a filtration histogram technique using texture analysis software, with texture quantification using statistical and histogram-based metrics (mean, skewness, standard deviation, entropy, etc.). Association between pre-contrast and EQ-CTTA against CPA, ECV and ELF was evaluated using Spearman’s rank correlation coefficient (r_s). Results: Complete datasets collected in 29 patients (16 male; 13 female), mean age (range): 49 (22–66 years). Liver ECV, CPA and ELF had a median (interquartile range) of 0.26 (0.24–0.29); 5.0 (3.0–13.7) and 9.71 (8.39–10.92). Difference in segment VII hepatic CTTA (medium texture scale) between EQ-CT and pre-contrast images was significantly and positively associated with ELF score (mean: r_s = 0.69, p < 0.001; skewness: r_s = 0.57, p = 0.007). Significant negative associations were observed between pre-contrast and EQ-CT whole hepatic CTTA (coarse texture scale) with CPA (pre-contrast, SD: r_s = −0.66, p < 0.001) and ECV (EQ-CT, entropy: r_s = −0.58, p = 0.006). Conclusions: Hepatic EQ-CTTA demonstrates significant association with validated markers of liver fibrosis, suggesting a role in non-invasive quantification of severity in diffuse fibrosis.

Diagnostic accuracy of texture analysis and machine learning for quantification of liver fibrosis in MRI: correlation with MR elastography and histopathology

OBJECTIVES

To compare the diagnostic accuracy of texture analysis (TA)-derived parameters combined with machine learning (ML) of non-contrast-enhanced T1w and T2w fat-saturated (fs) images with MR elastography (MRE) for liver fibrosis quantification.

METHODS

In this IRB-approved prospective study, liver MRIs of participants with suspected chronic liver disease who underwent liver biopsy between August 2015 and May 2018 were analyzed. Two readers blinded to clinical and histopathological findings performed TA. The participants were categorized into no or low-stage (0-2) and high-stage (3-4) fibrosis groups. Confusion matrices were calculated using a support vector machine combined with principal component analysis. The diagnostic accuracy of ML-based TA of liver fibrosis and MRE was assessed by area under the receiver operating characteristic curves (AUC). Histopathology served as reference standard.

RESULTS

A total of 62 consecutive participants (40 men; mean age ± standard deviation, 48 ± 13 years) were included. The accuracy of TA and ML on T1w was 85.7% (95% confidence interval [CI] 63.7-97.0) and 61.9% (95% CI 38.4-81.9) on T2w fs for classification of liver fibrosis into low-stage and high-stage fibrosis. The AUC for TA on T1w was similar to MRE (0.82 [95% CI 0.59-0.95] vs. 0.92 [95% CI 0.71-0.99], p = 0.41), while the AUC for T2w fs was significantly lower compared to MRE (0.57 [95% CI 0.34-0.78] vs. 0.92 [95% CI 0.71-0.99], p = 0.008).

CONCLUSION

Our results suggest that liver fibrosis can be quantified with TA-derived parameters of T1w when combined with a ML algorithm with similar accuracy compared to MRE.

KEY POINTS

• Liver fibrosis can be categorized into low-stage fibrosis (0-2) and high-stage fibrosis (3-4) using texture analysis-derived parameters of T1-weighted images with a machine learning approach. • For the differentiation of low-stage fibrosis and high-stage fibrosis, the diagnostic accuracy of texture analysis on T1-weighted images combined with a machine learning algorithm is similar compared to MR elastography.

Radiomics based on artificial intelligence in liver diseases: where we are?

Radiomics uses computers to extract a large amount of information from different types of images, form various quantifiable features, and select relevant features using artificial-intelligence algorithms to build models, in order to predict the outcomes of clinical problems (such as diagnosis, treatment, prognosis, etc.). The study of liver diseases by radiomics will contribute to early diagnosis and treatment of liver diseases and improve survival and cure rates of liver diseases. This field is currently in the ascendant and may have great development in the future. Therefore, we summarize the progress of current research in this article and then point out the related deficiencies and the direction of future research.

Radiomics and Deep Learning: Hepatic Applications

Radiomics and deep learning have recently gained attention in the imaging assessment of various liver diseases. Recent research has demonstrated the potential utility of radiomics and deep learning in staging liver fibroses, detecting portal hypertension, characterizing focal hepatic lesions, prognosticating malignant hepatic tumors, and segmenting the liver and liver tumors. In this review, we outline the basic technical aspects of radiomics and deep learning and summarize recent investigations of the application of these techniques in liver disease.

5-Fluorouracil induced liver toxicity in patients with colorectal cancer: role of computed tomography texture analysis as a potential biomarker

PURPOSE

To assess if CT texture analysis (TA) can serve as a biomarker of liver toxicity in patients with colorectal cancer treated with 5-fluorouracil (5-FU)-based chemotherapy.

METHODS

In this IRB-approved, HIPAA-compliant retrospective study, patients with colorectal cancer treated with 5-FU-based regimens during 2008-2010 were identified from institutional electronic database. Total 43 patients (23 women; mean age 56 years) with normal baseline liver function tests (LFTs), availability of baseline (pre-chemotherapy) and first follow-up CT (median 1.7 months, interquartile range (IQR) 1.5-2.5) performed during chemotherapy were included. Two single-slice ROI of right and left liver lobe were obtained on baseline and first follow-up CT for TA. Texture features [mean, entropy, kurtosis, skewness, mean of positive pixel, standard deviation (SD)] were extracted using a commercially available software (TexRAD; Feedback Medical Ltd, Cambridge, UK). Changes in texture parameters between baseline and follow-up CT were evaluated with Wilcoxon signed-rank test for patients with and without LFT elevation during chemotherapy.

RESULTS

Patients with LFT elevation (n = 34; 79%) showed significantly different mean, entropy, skewness, and SD (p values range 0.007-0.047) between baseline and first follow-up CT. No significant changes in features were observed in patients without LFT elevation (n = 9; 21%). In 19 patients (56%), first follow-up CT was performed before elevation of LFTs was observed.

CONCLUSIONS

This proof-of-concept study shows that there are early changes in liver texture on first follow-up CT in patients with LFT elevation during 5-FU-based chemotherapy for colorectal cancer. In more than 50% of cases, these changes occur before LFT elevation becomes evident on blood tests.

Current Imaging Techniques for Noninvasive Staging of Hepatic Fibrosis

OBJECTIVE. The purpose of this article is to discuss quantitative methods of CT, MRI, and ultrasound (US) for noninvasive staging of hepatic fibrosis. Hepatic fibrosis is the hallmark of chronic liver disease (CLD), and staging by random liver biopsy is invasive and prone to sampling errors and subjectivity. Several noninvasive quantitative imaging methods are under development or in clinical use. The accuracy, precision, technical aspects, advantages, and disadvantages of each method are discussed. CONCLUSION. The most promising methods are the liver surface nodularity score using CT and measurement of liver stiffness using MR elastography or US elastography.

Predicting malignant potential of subsolid nodules: can radiomics preempt longitudinal follow up CT?

Background

To assess if radiomics can differentiate benign and malignant subsolid lung nodules (SSNs) on baseline or follow up chest CT examinations. If radiomics can differentiate between benign and malignant subsolid lung nodules, the clinical implications are shorter follow up CT imaging and early recognition of lung adenocarcinoma on imaging.

Materials and methods

The IRB approved retrospective study included 36 patients (mean age 69 ± 8 years; 5 males, 31 females) with 108 SSNs (31benign, 77 malignant) who underwent follow up chest CT for evaluation of indeterminate SSN. All SSNs were identified on both baseline and follow up chest CT. DICOM CT images were deidentified and exported into the open access 3D Slicer software (version 4.7) to obtain radiomic features. Logistic regression analyses and receiver operating characteristic (ROC) curves for various quantitative parameters were generated with SPSS statistical software.

Results

Only 2/92 radiomic features (cluster shade and surface volume ratio) enabled differentiation between malignant and benign SSN on baseline chest CT (P = 0.01 and 0.03) with moderate accuracy [AUC 0.624 (0.505–0.743)]. On follow-up CT, 52/92 radiomic features were significantly different between benign and malignant SSN (P: 0.04 - < 0.0001) with improved accuracy [AUC: 0.708 (0.605–0.811), P = 0.04 - < 0.0001]. Radiomics of benign SSN were stable over time, whereas 63/92 radiomic features of malignant SSNs changed significantly between the baseline and follow up chest CT (P: 0.04 - < 0.0001).

Conclusions

Temporal changes in radiomic features of subsolid lung nodules favor malignant etiology over benign. The change in radiomics features of subsolid lung nodules can allow shorter follow up CT imaging and early recognition of lung adenocarcinoma on imaging. Radiomic features have limited application in differentiating benign and early malignant SSN on baseline chest CT.

Diagnostic value of MR-based texture analysis for the assessment of hepatic fibrosis in patients with nonalcoholic fatty liver disease (NAFLD)

PURPOSE

To investigate the performance of MR-based texture analysis (TA) for the assessment of hepatic fibrosis in patients with nonalcoholic fatty liver disease (NAFLD).

METHODS

Fifty-four adult patients (33 females, 21 males, mean age 49.8 ± 13.5 years) with biopsy-proven NAFLD were enrolled and underwent MR imaging on a 1.5 T system. TA parameters were extracted on axial noncontrast 3D-GRE T1W images (slice thickness = 4.6 mm) using a commercially available research software (TexRAD). Receiver operating curves (ROC), areas under the ROC (AUROC) and 95% confidence intervals (CI) were calculated to assess the accuracy of each TA parameter for the diagnosis of significant (F ≥ 2) and advanced fibrosis (F ≥ 3). The correlation between TA and histopathological features of nonalcoholic steatohepatitis (NASH) was tested calculating the Spearman's rank correlation coefficient (ρ).

RESULTS

Thirty-seven (68%) subjects had significant fibrosis and 20 (37%) had advanced fibrosis. The TA parameters with the best performance were standard deviation (SD) and entropy, respectively, with AUROC 0.755 (95% CI 0.619-0.862, p ≤ 0.0002) and 0.769 (95% CI 0.634-0.873, p < 0.0001) for significant fibrosis and AUROC 0.746 (95% CI 0.609-0.854, p ≤ 0.0004) and 0.754 (95% CI 0.618-0.861, p ≤ 0.0002) for advanced fibrosis. SD and entropy demonstrated a moderate correlation with the degree of fibrosis (ρ = 0.457 and 0.480; p < 0.01). No significant correlation was found between TA parameters and other histopathological features of NASH.

CONCLUSIONS

Entropy and SD extracted on T1-weighted MR images have fair accuracy for the diagnosis of significant and advanced hepatic fibrosis in patients with NAFLD.