A radiomics-based interpretable model to predict the pathological grade of pancreatic neuroendocrine tumors

OBJECTIVES

To develop a computed tomography (CT) radiomics-based interpretable machine learning (ML) model to predict the pathological grade of pancreatic neuroendocrine tumors (pNETs) in a non-invasive manner.

METHODS

Patients with pNETs who underwent contrast-enhanced abdominal CT between 2010 and 2022 were included in this retrospective study. Radiomics features were extracted, and five radiomics-based ML models, namely logistic regression (LR), random forest (RF), support vector machine (SVM), XGBoost, and GaussianNB, were developed. The performance of these models was evaluated using a time-independent testing set, and metrics such as sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC) were calculated. The accuracy of the radiomics model was compared to that of needle biopsy. The Shapley Additive Explanation (SHAP) tool and the correlation between radiomics and biological features were employed to explore the interpretability of the model.

RESULTS

A total of 122 patients (mean age: 50 ± 14 years; 53 male) were included in the training set, whereas 100 patients (mean age: 48 ± 13 years; 50 male) were included in the testing set. The AUCs for LR, SVM, RF, XGBoost, and GaussianNB were 0.758, 0.742, 0.779, 0.744, and 0.745, respectively, with corresponding accuracies of 73.0%, 70.0%, 77.0%, 71.9%, and 72.9%. The SHAP tool identified two features of the venous phase as the most significant, which showed significant differences among the Ki-67 index or mitotic count subgroups (p < 0.001).

CONCLUSIONS

An interpretable radiomics-based RF model can effectively differentiate between G1 and G2/3 of pNETs, demonstrating favorable interpretability.

CLINICAL RELEVANCE STATEMENT

The radiomics-based interpretable model developed in this study has significant clinical relevance as it offers a non-invasive method for assessing the pathological grade of pancreatic neuroendocrine tumors and holds promise as an important complementary tool to traditional tissue biopsy.

KEY POINTS

• A radiomics-based interpretable model was developed to predict the pathological grade of pNETs and compared with preoperative needle biopsy in terms of accuracy. • The model, based on CT radiomics, demonstrated favorable interpretability. • The radiomics model holds potential as a valuable complementary technique to preoperative needle biopsy; however, it should not be considered a replacement for biopsy.

Spectral CT - a new supplementary method for preoperative assessment of pathological grades of esophageal squamous cell carcinoma

BACKGROUND

Spectral CT imaging parameters have been reported to be useful in the differentiation of pathological grades in different malignancies. This study aims to investigate the value of spectral CT in the quantitative assessment of esophageal squamous cell carcinoma (ESCC) with different degrees of differentiation.

METHODS

There were 191 patients with proven ESCC who underwent enhanced spectral CT from June 2018 to March 2020 retrospectively enrolled. These patients were divided into three groups based on pathological results: well differentiated ESCC, moderately differentiated ESCC, and poorly differentiated ESCC. Virtual monoenergetic 40 keV-equivalent image (VMI40keV), iodine concentration (IC), water concentration (WC), effective atomic number (Eff-Z), and the slope of the spectral curve(λHU) of the arterial phase (AP) and venous phase (VP) were measured or calculated. The quantitative parameters of the three groups were compared by using one-way ANOVA and pairwise comparisons were performed with LSD. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic performance of these parameters in poorly differentiated groups and non-poorly differentiated groups.

RESULTS

There were significant differences in VMI40keV, IC, Eff-Z, and λHU in AP and VP among the three groups (all p < 0.05) except for WC (p > 0.05). The VMI40keV, IC, Eff-Z, and λHU in the poorly differentiated group were significantly higher than those in the other groups both in AP and VP (all p < 0.05). In the ROC analysis, IC performed the best in the identification of the poorly differentiated group and non-poorly differentiated group in VP (AUC = 0.729, Sensitivity = 0.829, and Specificity = 0.569 under the threshold of 21.08 mg/ml).

CONCLUSIONS

Quantitative parameters of spectral CT could offer supplemental information for the preoperative differential diagnosis of ESCC with different degrees of differentiation.

Preoperative determination of pathological grades of primary single HCC: development and validation of a scoring model

PURPOSE

This study aimed to establish a reliable diagnostic score model for the preoperative determination of pathological grade in HCC based on gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) enhanced MRI and biochemical indicators.

METHODS

In this retrospective study, we analyzed 139 patients with HCC who underwent Gd-EOB-DTPA MRI between 2014 and 2020, including an establishment cohort of 76 patients and a validation cohort of 63 patients. Based on the imaging features demonstrated on Gd-EOB-DTPA MRI images and biochemical indicators of the establishment cohort, a scoring model based on logistic regression was developed, and compared with postoperative pathological findings in terms of effective determination of pathological grade. The validity of the scoring model was assessed by ROC curves and an independent external validation cohort.

RESULTS

Three parameters related to pathological grades were identified, including maximum diameter of the tumor, peritumoral hypointensity in the hepatobiliary phase, and [alkaline phosphatase (U/L) + gamma glutamyl transpeptidase (U/L)]/ lymphocyte count (× 10⁹/L) (AGLR) ratios. Based on these three parameters, a scoring model was developed. ROC curve showed that a score of > 5 was set as the threshold for determining pathological grades with accuracy, sensitivity, specificity, PPV, and NPV of 89.5%, 75.0%, 95.1%, 85.7%, and 90.7%, respectively.

CONCLUSION

The study provided the groundwork for a promising and easily implementable scoring model for preoperative determination of HCC pathological grades, for which further validation should be pursued.

The application value of multi-parameter cystoscope in improving the accuracy of preoperative bladder cancer grading

Purpose

To develop and validate a preoperative cystoscopic-based predictive model for predicting postoperative high-grade bladder cancer (BCa), which could be used to guide the surgical selection and postoperative treatment strategies.

Materials and methods

We retrospectively recruited 366 patients with cystoscopy biopsy for pathology and morphology evaluation between October 2010 and January 2021. A binary logistic regression model was used to assess the risk factors for postoperative high-grade BCa. Diagnostic performance was analyzed by plotting receiver operating characteristic curve and calculating area under the curve (AUC), sensitivity, specificity. From January 2021 to July 2021, we collected 105 BCa prospectively to validate the model's accuracy.

Results

A total of 366 individuals who underwent transurethral resection of bladder tumor (TURBT) or radical cystectomy following cystoscopy biopsy were included for analysis. 261 (71.3%) had a biopsy pathology grade that was consistent with postoperative pathology grade. We discovered five cystoscopic parameters, including tumor diameter, site, non-pedicled, high-grade biopsy pathology, morphology, were associated with high-grade BCa. The established multi-parameter logistic regression model (“JSPH” model) revealed AUC was 0.917 (P < 0.001). Sensitivity and specificity were 86.2% and 84.0%, respectively. And the consistency of pre- and post-operative high-grade pathology was improved from biopsy-based 70.5% to JSPH model-based 85.2%. In a 105-patients prospective validation cohort, the consistency of pre- and post-operative high-grade pathology was increased from 63.1 to 84.2% after incorporation into JSPH model for prediction.

Conclusion

The cystoscopic parameters based “JSPH model” is accurate at predicting postoperative pathological high-grade tumors prior to operations.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12894-022-01054-z.

Utility of Newly Proposed Grading System From International Association for the Study of Lung Cancer for Invasive Lung Adenocarcinoma

Introduction

The International Association for the Study of Lung Cancer proposed a new grading criteria for invasive adenocarcinoma. However, its utility has not been validated.

Methods

Patients who underwent complete resection of lung adenocarcinoma were included in this study. Then, they were divided into the following three groups on the basis of the criteria recently proposed by the International Association for the Study of Lung Cancer: grade 1, lepidic predominant tumor, with less than 20% of high-grade patterns; grade 2, acinar or papillary predominant tumor, with less than 20% of high-grade patterns; and grade 3, any tumor with greater than or equal to 20% of high-grade patterns.

Results

Recurrence-free survival (RFS) was significantly different among the proposed grades (p < 0.001). The RFS of patients upgrading from current grade 2 (papillary or acinar predominant tumor) to proposed grade 3 (5-y RFS, 65.2%) was significantly worse than that of patients with proposed grade 2 (77.1%, hazard ratio = 1.882, 95% confidence interval: 1.236–2.866) but not significantly different from that of patients with grade 3 in both the current (micropapillary or solid predominant tumor) and proposed criteria (53.2%, hazard ratio = 0.761, 95% confidence interval: 0.456–1.269). Among patients with pathologic stage 0 or I, RFS was well stratified by the new grading system (p < 0.001) but not among patients with stage II or III (p = 0.334). In the multivariable analysis, the new grading was not a predictive factor of RFS.

Conclusions

Although the proposed grading system well stratified RFS in patients with pathologic stage 0 or I lung adenocarcinoma, there is room for improvement.

Integrating multiparametric MRI radiomics features and the Vesical Imaging-Reporting and Data System (VI-RADS) for bladder cancer grading

PURPOSE

Pathological grade is important for the treatment selection and outcome prediction in bladder cancer (BCa). We aimed to construct a radiomics-clinical nomogram to preoperatively differentiate high-grade BCa from low-grade BCa.

METHODS

A total of 185 BCa patients who received multiparametric MRI (mpMRI) before surgery between August 2014 and April 2020 were enrolled in our study. Radiomics features were extracted from the largest tumor located on dynamic contrast-enhancement and T2WI images. After feature selection, the synthetic minority over-sampling technique (SMOTE) was performed to balance the minority group (low-grade group). Radiomics signatures were constructed in the training set and assessed in the validation set. Univariable and multivariable logistic regression were applied to build a nomogram.

RESULTS

The radiomics signature generated by the least absolute shrinkage and selection operator model achieved the optimal performance for BCa grading in both the SMOTE-balanced training [accuracy: 93.2%, area under the curve (AUC): 0.961] and validation sets (accuracy: 89.9%, AUC: 0.952). A radiomics-clinical nomogram incorporating the radiomics signature and the Vesical Imaging-Reporting and Data System (VI-RADS) score had novel calibration and discrimination both in the training (AUC: 0.956) and validation sets (AUC: 0.958). Decision curve analysis presented the clinical utility of the nomogram for decision-making.

CONCLUSIONS

The mpMRI-based radiomics signature had the potential to preoperatively predict the pathological grade of BCa. The proposed nomogram combining the radiomics signature with the VI-RADS score improved the diagnostic power, which may aid in clinical decision-making.

Preoperative Pathological Grading of Hepatocellular Carcinoma Using Ultrasomics of Contrast-Enhanced Ultrasound

RATIONALE AND OBJECTIVES

To develop an ultrasomics model for preoperative pathological grading of hepatocellular carcinoma (HCC) using contrast-enhanced ultrasound (CEUS).

MATERIAL AND METHODS

A total of 235 HCCs were retrospectively enrolled, including 65 high-grade and 170 low-grade HCCs. Representative images of four-phase CEUS were selected from the baseline sonography, arterial, portal venous, and delayed phase images. Tumor ultrasomics features were automatically extracted using Ultrasomics-Platform software. Models were built via the classifier support vector machine, including an ultrasomics model using the ultrasomics features, a clinical model using the clinical factors, and a combined model using them both. Model performances were tested in the independent validation cohort considering efficiency and clinical usefulness.

RESULTS

A total of 1502 features were extracted from each image. After the reproducibility test and dimensionality reduction, 25 ultrasomics features and 3 clinical factors were selected to build the models. In the validation cohort, the combined model showed the best predictive power, with an area under the curve value of 0.785 (95% confidence interval [CI] 0.662-0.909), compared to the ultrasomics model of 0.720 (95% CI 0.576-0.864) and the clinical model of 0.665 (95% CI 0.537-0.793). Decision curve analysis suggested that the combined model was clinically useful, with a corresponding net benefit of 0.760 compared to the other two models.

CONCLUSION

We presented an ultrasomics-clinical model based on multiphase CEUS imaging and clinical factors, which showed potential value for the preoperative discrimination of HCC pathological grades.

High DPP4 expression predicts poor prognosis in patients with low-grade glioma

Dipeptidyl peptidase-IV (DPP4) plays a key role in tumor development; however, its role in glioma pathogenesis has not been determined. Here, we aimed to investigate the expression pattern of DPP4 and explore the association between expression and patient prognosis in glioma. DPP4 levels were investigated using qRT-PCR, immunohistochemistry and western blot in a rat model of glioma and also in patient samples. The relationship between DPP4 levels, WHO pathological grade gliomas, and isocitrate dehydrogenase 1 and 2 (IDH1/2) status was assessed in patient samples. Our data indicated that DPP4 levels were markedly increased in a rat model of glioma (p < 0.05, p < 0.01) and aslo in patient samples. Furthermore, the elevation of DPP4 levels in the samples obtained from pateints was associated with the pathogical grade of glioma and the IDH1/2 status (p < 0.01, p < 0.001). High DPP4 levels decreased the survival probability of patients with low-grade glioma (LGG). The data from patient samples showed that DPP4 expression increased with the pathological grade. Increased expression of DPP4 could be a promising index for determining the prognosis of glioma.

Intraoperative contrast-enhanced ultrasound for cerebral glioma resection and the relationship between microvascular perfusion and microvessel density

We analyzed the relationship between quantitative CEUS parameters and microvessel density (MVD) of different pathologic grades of cerebral gliomas. ICEUS was performed in 49 patients with cerebral gliomas. The enhancement characteristics of cerebral gliomas were observed before and after tumor resection. The number of microvessels was counted by immunostaining with anti-CD34. Differences in these quantitative parameters in cerebral gliomas were compared and subjected to a correlation analysis with MVD. The assessment of iCEUS parameters and tumor MVD showed that cerebral gliomas of different pathological grades had different characteristics. The time-to-peak (Tmax) was significantly shorter, the peak intensity (PI) and MVD were significantly higher in high-grade cerebral gliomas than in low-grade cerebral gliomas (p < 0.05). According to the immunostaining, PI was positively (r = 0.637) correlated with MVD and Tmax was negatively (r = -0.845) correlated with MVD. ICEUS could provid dynamic and continuous real-time imaging and quantitative data analysis of different pathological grades of cerebral gliomas, the quantitiative CEUS parameters were closely related to the MVD, and be helpful in understanding the cerebral gliomas grade and refining surgical strategy.

Choroid plexus tumours on MRI: similarities and distinctions in different grades

Background

The therapeutic planning varies for different grades of choroid plexus tumours (CPTs). The aim of this study was to define the similarities and distinctions among MRIs for different grades of CPTs, providing more guidance for clinical decisions.

Methods

We reviewed the MRI findings in 35 patients with CPT verified by surgical pathology, including 18 choroid plexus papillomas (CPPs, grade I), 11 atypical choroid plexus papillomas (aCPPs, grade II), and 6 choroid plexus carcinomas (CPCs, grade III). Nonparametric testing based on ranks was performed to evaluate the association of pathological grade with MRI findings.

Results

Among the 35 CPTs, 29 were located in the ventricular system. The tumours were generally slightly hypo- or isointense on T1WI, slightly hyper- or isointense on T2WI, and moderately or strongly enhanced in post-contrast imaging. Twenty cases were accompanied by hydrocephalus. The median tumour longest diameters of CPPs, aCPPs, and CPCs were 28.6, 44.6, and 60.6 mm, respectively. Four cases were purely cystic, 6 were papillary, 10 were lobulated, and 2 were irregular. Three cases had necrosis. The median oedema diameters of CPPs, aCPPs, and CPCs were 0, 0, and 24.1 mm, respectively. The grades of CPTs were statistically associated with tumour longest diameter (r_s = 0.68, P < 0.001), internal morphology (χ² = 10.32, P = 0.016), necrosis (Z = 2.27, P = 0.023), and oedema diameter (r_s = 0.72, P < 0.001).

Conclusion

CPTs typically appeared as intraventricular papillary or lobulated lesions, often accompanied by hydrocephalus. Larger tumour, irregular or fuzzy internal morphology, presentation of necrosis and wide-ranging peritumoural oedema might increase the likelihood of malignancy.

A clinicopathological study of parotid carcinoma: 18-year review of 171 patients at a single institution

BACKGROUND

This study investigated the clinical outcomes of patients with parotid carcinoma at a single institution during an 18-year period, with the focus on diagnosis, treatment, and survival.

METHODS

The subjects were 171 patients with parotid carcinoma treated at our department during the 18-year period from September 1999 to August 2017. There were 19 patients in stage I, 65 patients in stage II, 22 patients in stage III, and 65 patients in stage IV. The symptoms, preoperative diagnosis, node metastasis, survival rate, prognostic factors, and immunohistological findings were investigated.

RESULTS

Preoperative diagnosis of the histological grade by fine-needle aspiration cytology was only possible in 34% of the patients, while the histological grade was correctly determined by frozen section biopsy in 72%. The overall frequency of lymph node metastasis was 29%, with 59% in patients with high-grade carcinoma and only 6% in those with low-/intermediate-grade tumors. The disease-specific 5-year survival rate was 100% for patients in stage I, 95.2% in stage II, 70.4% in stage III, and 45.1% in stage IV. Multivariate analysis showed that the pathological grade was the most important prognostic factor. Immunohistological investigation showed patients with HER-2 or androgen receptor-positive tumors had a significantly worse prognosis.

CONCLUSIONS

Although a high-grade tumor is the most important prognostic factor, preoperative diagnosis of the grade was not always accurate. Since advanced cancer has a poor prognosis with a limited response to surgery and radiation therapy, development of new treatment strategies, such as molecular-targeting therapies directed against HER-2 and AR, is required.

Histogram analysis of diffusion kurtosis imaging derived maps may distinguish between low and high grade gliomas before surgery

OBJECTIVE

To investigate the value of histogram analysis of diffusion kurtosis imaging (DKI) maps in the evaluation of glioma grading.

METHODS

A total of 39 glioma patients who underwent preoperative magnetic resonance imaging (MRI) were classified into low-grade (13 cases) and high-grade (26 cases) glioma groups. Parametric DKI maps were derived, and histogram metrics between low- and high-grade gliomas were analysed. The optimum diagnostic thresholds of the parameters, area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were achieved using a receiver operating characteristic (ROC).

RESULT

Significant differences were observed not only in 12 metrics of histogram DKI parameters (P<0.05), but also in mean diffusivity (MD) and mean kurtosis (MK) values, including age as a covariate (F=19.127, P<0.001 and F=20.894, P<0.001, respectively), between low- and high-grade gliomas. Mean MK was the best independent predictor of differentiating glioma grades (B=18.934, 22.237 adjusted for age, P<0.05). The partial correlation coefficient between fractional anisotropy (FA) and kurtosis fractional anisotropy (KFA) was 0.675 (P<0.001). The AUC of the mean MK, sensitivity, and specificity were 0.925, 88.5% and 84.6%, respectively.

CONCLUSIONS

DKI parameters can effectively distinguish between low- and high-grade gliomas. Mean MK is the best independent predictor of differentiating glioma grades.

KEY POINTS

• DKI is a new and important method. • DKI can provide additional information on microstructural architecture. • Histogram analysis of DKI may be more effective in glioma grading.

Correlation of dual-source computed tomography/dual-energy imaging with pathological grading of lung adenocarcinoma and its clinical value

Objective:

To explore the correlation of dual-source computed tomography (DSCT)/dual-energy imaging with pathological grading of lung adenocarcinoma.

Methods:

A total of 47 patients with lung adenocarcinoma were selected. Tissues were histopathologically confirmed by routine DSCT scanning and dual-energy enhanced scanning. Arterial-phase and venous-phase iodine distribution images and single-energy images at 40-190 keV were obtained. The region of interest was outlined to obtain CT values. The iodine concentrations of each tumor in two phases were recorded to calculate normalized iodine concentrations (NICs).

Results:

The maximum diameter and minimum diameter of tumors in low differentiation (LD) group were significantly higher than those of high differentiation (HD) group (P<0.05). In LD group, 70.8% of margins were lobulated, which significantly exceeded that of HD group (30.4%) (P<0.05). Besides, 26.1% of patients in HD group were complicated with ground-glass opacity, which was significantly higher than that of LD group (4.2%) (P<0.05). In venous phase, there were significant differences between the two groups at low energy levels (40-70 keV) (P<0.05). At high energy levels (80-190 keV), the CT values of LD group were slightly higher than those of HD group. In arterial and venous phases, NICs of HD group were lower than those of LD group (P>0.05).

Conclusion:

HD and LD groups could be predictably distinguished by single-energy images at low energy levels (40-70 keV) in the venous phase. Quantitative analysis of NIC in the venous phase is also valuable for predicting the pathological grade of lung adenocarcinoma.

Recurrence of vocal fold leukoplakia after carbon dioxide laser therapy

This work aims to analyze the recurrence of vocal fold leukoplakia after carbon dioxide (CO₂) laser resection. In this retrospective study, all patients undergoing CO₂ laser resection of vocal fold leukoplakia were followed up for at least 2 years. Recurrence was diagnosed as any presence of leukoplakia in the vocal cord subsequent to previous successful complete resection. A total of 326 patients with complete resection of vocal fold leukoplakia and follow-up subsequent surveillance laryngoscopy were studied. The recurrence rate, the recurrence time, and risk factors were evaluated. Of these, 52 (16.0%) patients experienced recurrence with a mean follow-up time of 50.5 ± 15.4 months. The mean time to recurrence was 16.2 ± 14.1 months. Univariate analysis showed that the size of lesion (P < 0.001, Pearson χ ² test; P < 0.001, log-rank test) and the pathological grade (P = 0.025, Pearson χ ² test; P = 0.028, log-rank test) were significantly related to recurrence. The size of lesion was an independent prognostic factor for recurrence using multivariate analysis (P = 0.001, logistic regression; P = 0.001, Cox proportional hazards model). Considering the possible recurrence of vocal fold leukoplakia, long-term follow-up is required after CO₂ laser resection. In conclusion, the size of lesion combined with the pathological grade are important risk factors that predict vocal fold leukoplakia recurrence.

Measurement of the hepatitis B core-related antigen is valuable for predicting the pathological status of liver tissues in chronic hepatitis B patients

The objective of this study was to evaluate the validities of serum hepatitis B core-related antigen (HBcrAg) for predicting the pathological status of liver tissues of chronic hepatitis B (CHB). A total of 205 Chinese patients with CHB, including 121 HBeAg-positive and 84 HBeAg-negative patients, were enrolled in this study. In HBeAg-positive patients, AUCs of serum HBcrAg for predicting severe necro-inflammation and advanced fibrosis were greater than 0.70; using serum HBcrAg<=4.81×10(4)kUmL(-1) and <=2.45×10(4)kUmL(-1) as cutoffs, the sensitivities, specificities, accuracies for predicting severe necro-inflammation and advanced fbrosis were 0.697, 0.716, 0.711 and 0.818, 0.778, 0.785, respectively. In HBeAg-negative patients, the AUCs of serum HBcrAg for predicting significant necro-inflammation and significant fibrosis were greater than 0.70; using serum HBcrAg>=1.70×10(2)kUmL(-1) and >=4.02kUmL(-1) as cutoffs, the sensitivities, specificities, accuracies for predicting significant necro-inflammation and significant fibrosis were 0.929, 0.964, 0.952 and 1.000, 1.000, 1.000, respectively. These results indicated favorable performances of serum HBcrAg for predicting severe necro-inflammation and advanced fibrosis in HBeAg-positive patients and significant necro-inflammation and significant fibrosis in negative patients.

Value of controlled attenuation parameter in diagnosing nonalcoholic fatty liver disease

AIM: To assess the value of controlled attenuation parameter (CAP) in diagnosing nonalcoholic fatty liver disease (NAFLD).

METHODS: From January 2012 to March 2015, 146 NAFLD patients diagnosed by biopsy were enrolled in this study. CAP measurement was conducted by Fibroscan in all patients. The relationships between CAP and body mass index (BMI), aspartate transaminase (ALT), blood lipids and hepatic steatosis were analyzed, and the area under the receiver operating characteristic curve (AUC) was used to determine the diagnostic accuracy of CAP for NAFLD.

RESULTS: A total of 146 patients were recruited, including 58 patients with NAFLD alone and 88 patients with NAFLD and chronic hepatitis B (CHB). CAP was found to be positively correlated with BMI (r = 0.54, P < 0.05) and hepatic steatosis (r = 0.848, P < 0.05), while there was no relationship between CAP and ALT, AST, blood lipid, liver inflammation grade or fibrosis stage. The cut-offs for the CAP values in patients with hepatic steatosis vs mild steatosis, mild steatosis vs moderate steatosis, moderate steatosis vs severe steatosis were 252.50 dB/m, 281.50 dB/m, and 326.50 dB/m, respectively, with AUROC of 0.818, 0.917 and 0.789, respectively.

CONCLUSION: Controlled attenuation parameter appears to be a promising tool for diagnosing NAFLD.