Diagnostic performance of CT/MRI LI-RADS v2018 in non-cirrhotic steatotic liver disease.

OBJECTIVE: To assess the performance of computed tomography (CT)/magnetic resonance imaging (MRI) Liver Imaging Reporting and Data System (LI-RADS) among patients with non-cirrhotic steatotic liver disease (SLD). MATERIALS AND METHODS: This IRB-approved, retrospective study included 119 observations from 77 adult patients (36 women, 41 men; median 64 years) who underwent liver CT or MRI from 2010 to 2023. All patients had histopathologic evidence of SLD without cirrhosis. Three board-certified abdominal radiologists blinded to tissue diagnosis and imaging follow-up assessed observations with LI-RADS. The positive predictive value (PPV), sensitivity, specificity, accuracy, and inter-reader agreement were calculated. RESULTS: Seventy-five observations (63%) were benign and 44 (37%) were malignant. PPV for hepatocellular carcinoma (HCC) was 0-0% for LR-1, 0-0% for LR-2, 0-7% for LR-3, 11-20% for LR-4, 75-88% for LR-5, 0-8% for LR-M, and 50-75% for LR-TIV. For LR-5 in identifying HCC, sensitivity was 79-83%, specificity was 91-97%, and accuracy was 89-92%. For composite categories of LR-5, LR-M, or LR-TIV in identifying malignancy, sensitivity was 86-89%, specificity was 85-96%, and accuracy was 86-93%. The most common false positives for LR-5 were hepatocellular adenomas. Only 59-65% of HCCs showed non-peripheral washout at CT versus 67-83% at MRI, though nearly all had an enhancing capsule. PPV and accuracy of LR-5 for HCC did not differ by modality. Inter-reader agreement for major features ranged from 0.667 to 0.830 and was 0.766 for the final category. CONCLUSION: Despite challenges such as the lower prevalence of non-peripheral washout at CT and overlapping imaging features between HCC and hepatocellular adenomas, LI-RADS may serve as an effective tool in assessing focal liver lesions in SLD. CLINICAL RELEVANCE STATEMENT: LI-RADS in non-cirrhotic steatotic liver disease can effectively diagnose hepatocellular carcinoma and malignancy at computed tomography and magnetic resonance imaging, thereby guiding clinical management decisions and expediting patient care pathways. KEY POINTS: Performance of LI-RADS is unknown in non-cirrhotic patients with steatotic liver disease. LI-RADS 5 category showed a high pooled specificity of 91-97% for hepatocellular carcinoma. LI-RADS can non-invasively risk stratify focal liver observations in non-cirrhotic patients with steatotic liver disease.

Diagnostic performance of hypoechoic perinephric fat as a predictor of prediabetes and diabetes.

PURPOSE: To evaluate prevalence and predictive value of hypoechoic perinephric fat (HPF) in patients with prediabetes and diabetes compared to non-diabetics. METHODS: Of 240 patients with renal ultrasound and hemoglobin A1c (HbA1c) measurements, 114 patients had either prediabetes (HbA1c 5.7-6.4%) or diabetes (HbA1c ≥ 6.5%), and 126 patients did not. Two radiologists (blinded to diagnosis) reviewed images and discrepancies were resolved by a third. Inter-reader agreement was compared using free-marginal kappa and intraclass correlation coefficient. Fisher's exact test, Mann-Whitney test, multivariable logistic regression, and Spearman's rank correlation test with two-tailed p < 0.05 were used to determine statistical significance. RESULTS: HPF was exclusively identified in prediabetic and diabetic patients with a prevalence of 23% (vs 0%; p < 0.001). Identification of HPF had almost perfect inter-reader agreement (k = 0.94) and was statistically significant (p = 0.034) while controlling for body mass index (BMI) and estimated glomerular filtration rate in multivariable analysis. HPF had extremely high specificity and positive predictive value (100% for both) in patients with prediabetes and diabetes although it was not a sensitive finding (23% sensitivity). In patients with prediabetes and diabetes, those with HPF were statistically significantly more likely to have chronic kidney disease (CKD) (p = 0.003). There was no statistically significant difference in BMI, stages of CKD, and types of diabetes. CONCLUSION: Hypoechoic perirenal fat has almost perfect inter-reader agreement and is highly specific for and predictive of prediabetes and diabetes. Its presence may also help identify those with chronic kidney disease among prediabetic and diabetic patients.

Automated Identification and Measurement Extraction of Pancreatic Cystic Lesions from Free-Text Radiology Reports Using Natural Language Processing.

Purpose: To automatically identify a cohort of patients with pancreatic cystic lesions (PCLs) and extract PCL measurements from historical CT and MRI reports using natural language processing (NLP) and a question answering system. Materials and Methods: Institutional review board approval was obtained for this retrospective Health Insurance Portability and Accountability Act-compliant study, and the requirement to obtain informed consent was waived. A cohort of free-text CT and MRI reports generated between January 1991 and July 2019 that covered the pancreatic region were identified. A PCL identification model was developed by modifying a rule-based information extraction model; measurement extraction was performed using a state-of-the-art question answering system. The system's performance was evaluated against radiologists' annotations. Results: For this study, 430 426 free-text radiology reports from 199 783 unique patients were identified. The NLP model for identifying PCL was applied to 1000 test samples. The interobserver agreement between the model and two radiologists was almost perfect (Fleiss κ = 0.951), and the false-positive rate and true-positive rate were 3.0% and 98.2%, respectively, against consensus of radiologists' annotations as ground truths. The overall accuracy and Lin concordance correlation coefficient for measurement extraction were 0.958 and 0.874, respectively, against radiologists' annotations as ground truths. Conclusion: An NLP-based system was developed that identifies patients with PCLs and extracts measurements from a large single-institution archive of free-text radiology reports. This approach may prove valuable to study the natural history and potential risks of PCLs and can be applied to many other use cases.Keywords: Informatics, Abdomen/GI, Pancreas, Cysts, Computer Applications-General (Informatics), Named Entity Recognition Supplemental material is available for this article. © RSNA, 2022See also commentary by Horii in this issue.