The Calculation and Evaluation of an Ultrasound-Estimated Fat Fraction in Non-Alcoholic Fatty Liver Disease and Metabolic-Associated Fatty Liver Disease

We aimed to develop a non-linear regression model that could predict the fat fraction of the liver (UEFF), similar to magnetic resonance imaging proton density fat fraction (MRI-PDFF), based on quantitative ultrasound (QUS) parameters. We measured and retrospectively collected the ultrasound attenuation coefficient (AC), backscatter-distribution coefficient (BSC-D), and liver stiffness (LS) using shear wave elastography (SWE) in 90 patients with clinically suspected non-alcoholic fatty liver disease (NAFLD), and 51 patients with clinically suspected metabolic-associated fatty liver disease (MAFLD). The MRI-PDFF was also measured in all patients within a month of the ultrasound scan. In the linear regression analysis, only AC and BSC-D showed a significant association with MRI-PDFF. Therefore, we developed prediction models using non-linear least squares analysis to estimate MRI-PDFF based on the AC and BSC-D parameters. We fitted the models on the NAFLD dataset and evaluated their performance in three-fold cross-validation repeated five times. We decided to use the model based on both parameters to calculate UEFF. The correlation between UEFF and MRI-PDFF was strong in NAFLD and very strong in MAFLD. According to a receiver operating characteristics (ROC) analysis, UEFF could differentiate between <5% vs. ≥5% and <10% vs. ≥10% MRI-PDFF steatosis with excellent, 0.97 and 0.91 area under the curve (AUC), accuracy in the NAFLD and with AUCs of 0.99 and 0.96 in the MAFLD groups. In conclusion, UEFF calculated from QUS parameters is an accurate method to quantify liver fat fraction and to diagnose ≥5% and ≥10% steatosis in both NAFLD and MAFLD. Therefore, UEFF can be an ideal non-invasive screening tool for patients with NAFLD and MAFLD risk factors.

Artificial intelligence and neural networks in radiology – Basics that all radiology residents should know

The area of Artificial Intelligence is developing at a high rate. In the medical field, an extreme amount of data is created every day. As the images and the reports are quantifiable, the field of radiology aspires to deliver better, more efficient clinical care. Artificial intelligence (AI) means the simulation of human intelligence by a system or machine. It has been developed to enable machines to “think”, which means to be able to learn, reason, predict, categorize, and solve problems concerning high amounts of data and make decisions in a more effective manner than before. Different AI methods can help radiologists with pre-screening images and identifying features. In this review, we summarize the basic concepts which are needed to understand AI. As the AI methods are expected to exceed the threshold for clinical usefulness soon, in the near future it will be inevitable to use AI in medicine.

Splenic hamartoma in a patient with peripancreatic arterial arcades: A case report

Splenic hamartoma is a rare benign vascular lesion of the spleen. A splenic mass was incidentally detected in an asymptomatic 65-year-old male during an abdominal ultrasound scan. The workup of the splenic lesion included an abdominal CT angiography (CTA), contrast-enhanced ultrasound (CEUS), and microvascular flow imaging Doppler sonography. The CT scan confirmed that the splenic mass had benign characteristics, and its contrast enhancement was similar to the spleen. The CEUS was able to rule out the possibility of hemangioma. Meanwhile, chronic compression of the celiac trunk and the filling of the splenic artery from collaterals were also detected on CTA. The imaging studies suggested a splenic hamartoma, and the diagnosis was confirmed by the result of a fine needle aspiration biopsy.

Radiomics analysis of contrast-enhanced CT scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols

Introduction

This study aimed to construct a radiomics-based machine learning (ML) model for differentiation between non-clear cell and clear cell renal cell carcinomas (ccRCC) that is robust against institutional imaging protocols and scanners.

Materials and methods

Preoperative unenhanced (UN), corticomedullary (CM), and excretory (EX) phase CT scans from 209 patients diagnosed with RCCs were retrospectively collected. After the three-dimensional segmentation, 107 radiomics features (RFs) were extracted from the tumor volumes in each contrast phase. For the ML analysis, the cases were randomly split into training and test sets with a 3:1 ratio. Highly correlated RFs were filtered out based on Pearson’s correlation coefficient (r > 0.95). Intraclass correlation coefficient analysis was used to select RFs with excellent reproducibility (ICC ≥ 0.90). The most predictive RFs were selected by the least absolute shrinkage and selection operator (LASSO). A support vector machine algorithm-based binary classifier (SVC) was constructed to predict tumor types and its performance was evaluated based-on receiver operating characteristic curve (ROC) analysis. The “Kidney Tumor Segmentation 2019” (KiTS19) publicly available dataset was used during external validation of the model. The performance of the SVC was also compared with an expert radiologist’s.

Results

The training set consisted of 121 ccRCCs and 38 non-ccRCCs, while the independent internal test set contained 40 ccRCCs and 13 non-ccRCCs. For external validation, 50 ccRCCs and 23 non-ccRCCs were identified from the KiTS19 dataset with the available UN, CM, and EX phase CTs. After filtering out the highly correlated and poorly reproducible features, the LASSO algorithm selected 10 CM phase RFs that were then used for model construction. During external validation, the SVC achieved an area under the ROC curve (AUC) value, accuracy, sensitivity, and specificity of 0.83, 0.78, 0.80, and 0.74, respectively. UN and/or EX phase RFs did not further increase the model’s performance. Meanwhile, in the same comparison, the expert radiologist achieved similar performance with an AUC of 0.77, an accuracy of 0.79, a sensitivity of 0.84, and a specificity of 0.69.

Conclusion

Radiomics analysis of CM phase CT scans combined with ML can achieve comparable performance with an expert radiologist in differentiating ccRCCs from non-ccRCCs.

CT texture analysis of abdominal lesions – Part II: Tumors of the Kidney and Pancreas

It has been proven in a few early studies that radiomic analysis offers a promising opportunity to detect or differentiate between organ lesions based on their unique texture parameters. Recently, the utilization of CT texture analysis (CTTA) has been receiving significant attention, especially for response evaluation and prognostication of different oncological diagnoses. In this review article, we discuss the unique ability of radiomics and its subfield CTTA to diagnose lesions in the pancreas and kidney. We review studies in which CTTA was used for the classification of histology grades in pancreas and kidney tumors. We also review the role of radiogenomics in the prediction of the molecular and genetic subtypes of pancreatic tumors. Furthermore, we provide a short report on recent advancements of radiomic analysis in predicting prognosis and survival of patients with pancreatic and renal cancers.

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.

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.

Thrombosed orbital varix with mild, spontaneously resolving symptoms

Orbital varices are abnormally enlarged, thin walled veins in direct connection with normal orbital vessels. Stooping, bending, coughing or straining increase the venous tension and in this way can cause symptoms, such as bulging of the eyes (proptosis), orbital pain, bleeding, intermittent double vision. Small varices are managed by observation while larger lesions may require surgery. In our case report we demonstrate the case of a 72-year-old female patient with right sided retro-orbital pressure sensation for weeks, and exophthalmos with blurred vision for 1 week. MR investigation proved the presence of a partially thrombosed orbital varix on the right side, and a smaller, non-thrombosed varix on the left side. Observation was agreed, and the symptoms resolved spontaneously after several weeks.

Orthopaedic metallic artefact reduction algorithm facilitates CT evaluation of the urinary tract after hip prosthesis

AIM

To examine the improvement in the visualisation of bladder and ureteric pathologies next to a hip prosthesis with metallic artefact reduction for orthopaedic implants (O-MAR).

MATERIALS AND METHODS

Thirty-four patients who underwent pelvic computed tomography (CT) for non-prosthesis-related causes were enrolled retrospectively. Portal venous phase scans were reconstructed both with standard iterative reconstruction (ITR) and with O-MAR. The density of the ureters and the bladder was measured at both sides in the plane of the prosthesis. A semi-quantitative score was also used to assess visibility. The R (version 3.4.1) package was used for statistical analysis.

RESULTS

The average (μ) density of the 41 prosthesis side ureters was significantly lower on ITR images (μ=-94.76±150.48 [±SD] HU) than on O-MAR images (μ=-13.40±36.37 HU; p<0.0004). The difference between the ITR and O-MAR (μ=-138.62±182.64 versus -35.55±40.21 HU; p<0.0003) was also significant at the prosthesis side of the bladder. The visibility of the prosthesis side ureters was improved: 53.7% was obscured on ITR series compared to 4.9% on O-MAR. The visibility score was also better across all levels (p<0.001) with O-MAR. In four cases (13%), the O-MAR images significantly changed the diagnosis: in two cases ureteric stones, in one case each a bladder stone and a bladder tumour were discovered.

CONCLUSIONS

O-MAR reconstruction of CT images significantly improves the visibility of the urinary tract adjacent to metallic hip implants. Thus, O-MAR is essential for detecting ureteric and bladder pathologies in patients with a hip prosthesis.

Diffusion weighted magnetic resonance imaging demonstrates tumor response following palliative embolization of a recurrent shoulder plasmacytoma

We report the palliative embolization and functional imaging follow-up of a recurrent shoulder plasmacytoma. The multiple myeloma patient complained of severe pain and discomfort, while he could not tolerate further chemotherapy. The left shoulder lesion had earlier received a high dose of irradiation. Thus, the well-vascularized lesion was embolized via feeding arteries branching off from the left subclavian artery in two sessions. The patient’s symptoms rapidly improved post-embolization and the serum free light chain ratio stabilized at a lower level. The follow-up magnetic resonance image showed increased diffusivity in previously restricted tumor foci. This has negatively correlated with the decreased fludeoxyglucose uptake on PET, suggesting post-embolization necrosis.

Cerebral iodized lipid embolization via a pulmonary arteriovenous shunt: rare complication of transcatheter arterial embolization for hepatocellular carcinoma

We report the first European case of cerebral iodized lipid embolism post transcatheter arterial embolization for hepatocellular carcinoma. Lipiodol emboli and corresponding multifocal brain ischemia were documented with computed tomography (CT) and magnetic resonance (MR) in the acutely symptomatic patient. Transcranial Doppler sonography with contrast indicated a right-to-left shunt, while on a follow-up CT scan lipiodol embolization was detected in both lungs. Dilated pulmonary vessels and thick vascular channels were seen in the vicinity of the right diaphragm suggestive of pulmonary arteriovenous shunt. The patient symptoms regressed with supportive care alone, but he died 5 months later due to hepatic failure unrelated to the procedure.

Ultrasonography in the diagnosis and monitoring of ascites in acute abdominal attacks of hereditary angioneurotic oedema

BACKGROUND

Hereditary angioneurotic oedema (HAE) is a rare cause of ascites. As acute abdominal attacks of the disease can mimic surgical emergencies, prompt and accurate diagnosis is essential. This study was undertaken to evaluate the usefulness of serial abdominal ultrasound (US) examinations.

PATIENTS AND METHODS

Seventy patients with HAE were followed up for almost a decade. All patients presenting with an acute oedematous attack underwent abdominal US, which was then repeated 24 and 48 h after appropriate therapy.

RESULTS

Twenty-two acute oedematous attacks with abdominal complaints severe enough to justify hospital admission occurred in the study population. Abdominal US performed during the attack showed oedematous thickening of the intestinal wall in 80% of cases and invariably demonstrated the presence of free peritoneal fluid in all patients. Rapid symptomatic relief achieved by treatment was accompanied by the significant regression of US abnormalities.

CONCLUSIONS

Transitory ascites demonstrated by abdominal US is a clue to the diagnosis of an acute abdominal attack of HAE. The possibility of HAE should always be considered whenever unexplained abdominal pain recurs with or without ascites.