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.

Microvascular flow imaging to differentiate focal hepatic lesions: the spoke-wheel pattern as a specific sign of focal nodular hyperplasia

Microvascular flow imaging (MVFI) is an advanced Doppler ultrasound technique designed to detect slow-velocity blood flow in small-caliber microvessels. This technique is capable of realtime, highly detailed visualization of tumor vessels without using a contrast agent. MVFI has been recently applied for the characterization of focal liver lesions and has revealed typical vascularity distributions in multiple types thereof. Focal nodular hyperplasia (FNH) constitutes an important differential diagnosis of malignant liver tumors. In this essay, we provide iconographic documentation of the MVFI appearance of FNH and other common solid liver lesions. Identifying the typical patterns of vascularity, including the spoke-wheel pattern with MVFI, can expedite the diagnosis, spare patients from unnecessary procedures, and save costs.

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.

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.

Tissue attenuation imaging and tissue scatter imaging for quantitative ultrasound evaluation of hepatic steatosis

We aimed to assess the feasibility of ultrasound-based tissue attenuation imaging (TAI) and tissue scatter distribution imaging (TSI) for quantification of liver steatosis in patients with nonalcoholic fatty liver disease (NAFLD). We prospectively enrolled 101 participants with suspected NAFLD. The TAI and TSI measurements of the liver were performed with a Samsung RS85 Prestige ultrasound system. Based on the magnetic resonance imaging proton density fat fraction (MRI-PDFF), patients were divided into ≤5%, 5-10%, and ≥10% of MRI-PDFF groups. We determined the correlation between TAI, TSI, and MRI-PDFF and used multiple linear regression analysis to identify any association with clinical variables. The diagnostic performance of TAI, TSI was determined based on the area under the receiver operating characteristic curve (AUC). The intraclass correlation coefficient (ICC) was calculated to assess interobserver reliability. Both TAI (rs = 0.78, P < .001) and TSI (rs = 0.68, P < .001) showed significant correlation with MRI-PDFF. TAI overperformed TSI in the detection of both ≥5% MRI-PDFF (AUC = 0.89 vs 0.87) and ≥10% (AUC = 0.93 vs 0.86). MRI-PDFF proved to be an independent predictor of TAI (β = 1.03; P < .001), while both MRI-PDFF (β = 50.9; P < .001) and liver stiffness (β = -0.86; P < .001) were independent predictors of TSI. Interobserver analysis showed excellent reproducibility of TAI (ICC = 0.95) and moderate reproducibility of TSI (ICC = 0.73). TAI and TSI could be used successfully to diagnose and estimate the severity of hepatic steatosis in routine clinical practice.

Diagnosis of focal liver lesions with deep learning-based multi-channel analysis of hepatocyte-specific contrast-enhanced magnetic resonance imaging

BACKGROUND

The nature of input data is an essential factor when training neural networks. Research concerning magnetic resonance imaging (MRI)-based diagnosis of liver tumors using deep learning has been rapidly advancing. Still, evidence to support the utilization of multi-dimensional and multi-parametric image data is lacking. Due to higher information content, three-dimensional input should presumably result in higher classification precision. Also, the differentiation between focal liver lesions (FLLs) can only be plausible with simultaneous analysis of multi-sequence MRI images.

AIM

To compare diagnostic efficiency of two-dimensional (2D) and three-dimensional (3D)-densely connected convolutional neural networks (DenseNet) for FLLs on multi-sequence MRI.

METHODS

We retrospectively collected T2-weighted, gadoxetate disodium-enhanced arterial phase, portal venous phase, and hepatobiliary phase MRI scans from patients with focal nodular hyperplasia (FNH), hepatocellular carcinomas (HCC) or liver metastases (MET). Our search identified 71 FNH, 69 HCC and 76 MET. After volume registration, the same three most representative axial slices from all sequences were combined into four-channel images to train the 2D-DenseNet264 network. Identical bounding boxes were selected on all scans and stacked into 4D volumes to train the 3D-DenseNet264 model. The test set consisted of 10-10-10 tumors. The performance of the models was compared using area under the receiver operating characteristic curve (AUROC), specificity, sensitivity, positive predictive values (PPV), negative predictive values (NPV), and f1 scores.

RESULTS

The average AUC value of the 2D model (0.98) was slightly higher than that of the 3D model (0.94). Mean PPV, sensitivity, NPV, specificity and f1 scores (0.94, 0.93, 0.97, 0.97, and 0.93) of the 2D model were also superior to metrics of the 3D model (0.84, 0.83, 0.92, 0.92, and 0.83). The classification metrics of FNH were 0.91, 1.00, 1.00, 0.95, and 0.95 using the 2D and 0.90, 0.90, 0.95, 0.95, and 0.90 using the 3D models. The 2D and 3D networks' performance in the diagnosis of HCC were 1.00, 0.80, 0.91, 1.00, and 0.89 and 0.88, 0.70, 0.86, 0.95, and 0.78, respectively; while the evaluation of MET lesions resulted in 0.91, 1.00, 1.00, 0.95, and 0.95 and 0.75, 0.90, 0.94, 0.85, and 0.82 using the 2D and 3D networks, respectively.

CONCLUSION

Both 2D and 3D-DenseNets can differentiate FNH, HCC and MET with good accuracy when trained on hepatocyte-specific contrast-enhanced multi-sequence MRI volumes.