Speed of sound index for liver steatosis estimation: a reliability study in normal subjects.

PURPOSE Non-alcoholic fatty liver disease (NAFLD) is the most widespread type of chronic liver disease in the Western countries. Ultrasound (US) is widely used for NAFLD staging. The Resona 7 US system (Mindray Bio-Medical Electronics Co., Ltd.) includes an image optimization and speed of ultrasound-related feature, Sound Speed Index (SSI). SSI is applied in a region of interest (ROI) that could potentially aid in tissue characterization. The purpose of this study is to evaluate the reliability of SSI on various examination parameters on normal subjects. METHODS Twenty normal subjects were examined by two radiologists performing SSI measurements in the liver in different ROI depths and sizes. Intraclass correlation coefficient (ICC) was calculated to measure intra- and inter-observer variability and inter-ROI variability. RESULTS For all ROIs and both radiologists, the mean inter-observer ICC was 0.62 and the mean intraobserver ICC was 0.52 and 0.79. The mean SSI values for all ROIs and examiners were in the range 1528.79-1540.16 m/s. CONCLUSION The results indicate that SSI can lead to reliable measurements on normal subjects, independent of ROI size but dependent on ROI placement. More studies processing NAFLD patients, utilizing reference methods of liver fat quantification either for reliability or correlation with SSI, should be performed to further investigate the relevance of the SSI as a potential biomarker in clinical practice for liver steatosis grading.

Comparison of Visual Transient Elastography, Vibration Controlled Transient Elastography, Shear Wave Elastography and Sound Touch Elastography in Chronic liver Disease assessment using liver biopsy as 'Gold Standard'.

PURPOSE: Chronic liver disease (CLD) is considered one of the main causes of death. Ultrasound Elastography (USE) is a CLD assessment imaging method. This study aims to evaluate a recently introduced commercial alternative of USE, Visual Transient Elastography (ViTE), and to compare it with three established USE methods, Vibration Controlled Transient Elastography (VCTE), Shear Wave Elastography (SWE) and Sound Touch Elastography (STE), using Liver Biopsy (LB) as 'Gold Standard'. METHOD: 152 consecutive subjects underwent a liver ViTE, VCTE, SWE and STE examination. A Receiver Operator Characteristic (ROC) analysis was performed on the measured stiffness values of each method. An inter- intra-observer analysis was also performed. RESULTS: The ViTE, VCTE, SWE and STE ROC analysis resulted in an AUC of 0.9481, 0.9900, 0.9621 and 0.9683 for F ≥ F1, 0.9698, 0.9767, 0.9931 and 0.9834 for F ≥ F2, 0.9846, 0.9651, 0.9835 and 0.9763 for F ≥ F3, and 0.9524, 0.9645, 0.9656, and 0.9509 for F = F4, respectively. ICC scores were 0.98 for Inter-observer and 0.97 for Intra-observer variability analysis. CONCLUSION: ViTE performance in CLD stage differentiation is comparable to the performance of VCTE, SWE and STE.

Noninvasive, Blood-Based Biomarkers as Screening Tools for Hepatic Fibrosis in People With Type 2 Diabetes.

Nonalcoholic fatty liver disease (NAFLD) is dramatically increasing in parallel with the pandemic of type 2 diabetes. Here, the authors aimed to assess the performance of the most commonly used noninvasive, blood-based biomarkers for liver fibrosis (FibroTest, NAFLD fibrosis score, BARD score, and FIB-4 Index) in subjects with type 2 diabetes. Liver stiffness measurement was estimated by two-dimensional shear wave elastography. Finally, the authors assessed the diagnostic role of ActiTest and NashTest 2 in liver fibrosis in the examined population.

Liver Ultrasound Attenuation: An Ultrasound Attenuation Index for Liver Steatosis Assessment.

OBJECTIVES: Nonalcoholic fatty liver disease (NAFLD) is the most widespread chronic liver disease type in the Western countries. Ultrasound (US) is used for NAFLD and hepatic steatosis (HS) grading. The most popular US method for NAFLD assessment is the hepatorenal index (HRI), but because of its limitations, other noninvasive methods have been developed. The Resona 7 US system has recently incorporated an US attenuation-related quantitative feature, liver ultrasound attenuation (LiSA), for HS estimation. The purpose of this study is to compare LiSA's and HRI's performance on NAFLD assessment. METHODS: A total of 159 NAFLD patients having a magnetic resonance imaging-proton density fat fraction (MRI-PDFF) examination were examined by 2 radiologists, who performed LiSA and HRI measurements in the liver. Correlation of LiSA's and HRI's measurements with MRI-PDFF values was calculated through Pearson correlation coefficient (PCC). To further investigate the performance of LiSA and HRI, optimum cutoffs, provided by the literature, were used to correspond HS grades to MRI-PDFF results. Moreover, a receiver operating characteristic (ROC) analysis on LiSA measurements and steatosis grades was performed. RESULTS: Magnetic resonance imaging-PDFF was better correlated with LiSA (PCC = 0.80) than HRI (PCC = 0.67). Receiver operating characteristic analysis showed better performance range for LiSA (77.8%-91.8%) than for HRI (72.8%-85.4%) on all HS grades for all studies used for corresponding MRI-PDFF values to HS grades. CONCLUSIONS: The results indicate that LiSA is more accurate than HRI in HS differentiation and can lead to more accurate grading of HS on NAFLD patients.

A deep-learning-based prediction model for the biodistribution of 90 Y microspheres in liver radioembolization.

BACKGROUND: Radioembolization with 90 Y microspheres is a treatment approach for liver cancer. Currently, employed dosimetric calculations exhibit low accuracy, lacking consideration of individual patient, and tissue characteristics. PURPOSE: The purpose of the present study was to employ deep learning (DL) algorithms to differentiate patterns of pretreatment distribution of 99m Tc-macroaggregated albumin on SPECT/CT and post-treatment distribution of 90 Y microspheres on PET/CT and to accurately predict how the 90 Y-microspheres will be distributed in the liver tissue by radioembolization therapy. METHODS: Data for 19 patients with liver cancer (10 with hepatocellular carcinoma, 5 with intrahepatic cholangiocarcinoma, 4 with liver metastases) who underwent radioembolization with 90 Y microspheres were used for the DL training. We developed a 3D voxel-based variation of the Pix2Pix model, which is a special type of conditional GANs designed to perform image-to-image translation. SPECT and CT scans along with the clinical target volume for each patient were used as inputs, as were their corresponding post-treatment PET scans. The real and predicted absorbed PET doses for the tumor and the whole liver area were compared. Our model was evaluated using the leave-one-out method, and the dose calculations were measured using a tissue-specific dose voxel kernel. RESULTS: The comparison of the real and predicted PET/CT scans showed an average absorbed dose difference of 5.42% ± 19.31% and 0.44% ± 1.64% for the tumor and the liver area, respectively. The average absorbed dose differences were 7.98 ± 31.39 Gy and 0.03 ± 0.25 Gy for the tumor and the non-tumor liver parenchyma, respectively. Our model had a general tendency to underpredict the dosimetric results; the largest differences were noticed in one case, where the model underestimated the dose to the tumor area by 56.75% or 72.82 Gy. CONCLUSIONS: The proposed deep-learning-based pretreatment planning method for liver radioembolization accurately predicted 90 Y microsphere biodistribution. Its combination with a rapid and accurate 3D dosimetry method will render it clinically suitable and could improve patient-specific pretreatment planning.

Liver stiffness measurements by 2-dimensional shear wave elastography compared to histological and ultrasound parameters in primary biliary cholangitis.

BACKGROUND AND AIMS: Liver stiffness measurements (LSMs) by 2-dimensional-shear-wave elastography (LSM2D-SWE) are now widely used in hepatology. However, relevant information for primary biliary cholangitis (PBC) is scant. We compare LSM2D-SWE with liver biopsy (LB) in a cohort of PBC patients in Greece. METHODS: Data of 68 LBs from 53 PBC patients were retrospectively analyzed and fibrosis stage was compared to LSM2D-SWE. Forty-six patients (86.8%) were females and at the time of LBx median (IQR) age was 62.6 (53.2-72.1). Demographic, UDCA treatment, histological and B-mode ultrasound data were tested for their influence on LSM2D-SWE estimates. RESULTS: Liver fibrosis stages F0-F4 were found in 4, 19, 19, 16 and 10 cases, respectively. Across stages F0-F4, the LSM2D-SWE was 5.6 (5.1-6.1), 7.0 (5.8-7.7), 9.1 (7.3-11.5), 10.8 (9.9-12.2) and 14.5 (11.9-25.7) kPa, respectively, with highly significant difference (p<.001). The LSM2D-SWE differed also significantly between F0 vs. F1 (p=.027), F1 vs. F2 (p=.005) and F3 vs. F4 (p=.017). The discriminatory ability of LSM2D-SWE for mild, significant, severe fibrosis and cirrhosis was highly significant in all comparisons (p<.001), with AUC2D-SWE 95.3%, 87.4%, 85.3% and 95.3% and accuracy 89.7%, 85.3%, 80.9% and 86.8%, respectively. Among 21 parameters tested, significant predictors of LSM2D-SWE by multiple linear regression were fibrosis stage, portal inflammation and parenchymal heterogeneity. The portal inflammation grade accounted for 32.2% of LSM variation with adjusted R2 0.428. CONCLUSIONS: In patients with PBC, LSM measurements by 2D-SWE can reliably discriminate between mild, significant, severe fibrosis and cirrhosis. Measurements are significantly affected by portal inflammation grade.

Deep learning networks on chronic liver disease assessment with fine-tuning of shear wave elastography image sequences.

Chronic liver disease (CLD) is currently one of the major causes of death worldwide. If not treated, it may lead to cirrhosis, hepatic carcinoma and death. Ultrasound (US) shear wave elastography (SWE) is a relatively new, popular, non-invasive technique among radiologists. Although many studies have been published validating the SWE technique either in a clinical setting, or by applying machine learning on SWE elastograms, minimal work has been done on comparing the performance of popular pre-trained deep learning networks on CLD assessment. Currently available literature reports suggest technical advancements on specific deep learning structures, with specific inputs and usually on a limited CLD fibrosis stage class group, with limited comparison on competitive deep learning schemes fed with different input types. The aim of the present study is to compare some popular deep learning pre-trained networks using temporally stable and full elastograms, with or without augmentation as well as propose suitable deep learning schemes for CLD diagnosis and progress assessment. 200 liver biopsy validated patients with CLD, underwent US SWE examination. Four images from the same liver area were saved to extract elastograms and processed to exclude areas that were temporally unstable. Then, full and temporally stable masked elastograms for each patient were separately fed into GoogLeNet, AlexNet, VGG16, ResNet50 and DenseNet201 with and without augmentation. The networks were tested for differentiation of CLD stages in seven classification schemes over 30 repetitions using liver biopsy as the reference. All networks achieved maximum mean accuracies ranging from 87.2%-97.4% and area under the receiver operating characteristic curves (AUCs) ranging from 0.979-0.990 while the radiologists had AUCs ranging from 0.800-0.870. ResNet50 and DenseNet201 had better average performance than the other networks. The use of the temporal stability mask led to improved performance on about 50% of inputs and network combinations while augmentation led to lower performance for all networks. These findings can provide potential networks with higher accuracy and better setting in the CLD diagnosis and progress assessment. A larger data set would help identify the best network and settings for CLD assessment in clinical practice.

2D perfusion DSA with an open-source, semi-automated, color-coded software for the quantification of foot perfusion following infrapopliteal angioplasty: a feasibility study.

BACKGROUND: Foot perfusion has been recently implemented as a new tool for optimizing outcomes of peripheral endovascular procedures. A custom-made, two-dimensional perfusion digital subtraction angiography (PDSA) algorithm has been implemented to quantify outcomes of endovascular treatment of critical limb ischemia (CLI), assist intra-procedural decision-making, and enhance clinical outcomes. METHODS: The study was approved by the Hospital's Ethics Committee. This prospective, single-center study included seven consecutive patients scheduled to undergo infrapopliteal endovascular treatment of CLI. Perfusion blood volume (PBV), mean transit time (MTT), and perfusion blood flow (PBF) maps were extracted by analyzing time-intensity curves and signal intensity on the perfused vessel mask. Mean values calculated from user-specified regions of interest (ROIs) on perfusion maps were employed to evaluate pre- and post-endovascular treatment condition. Measurements were performed immediately after final PDSA. RESULTS: In total, five patients (aged 54 ± 16 years, mean ± standard deviation) were analyzed, as two patients were excluded due to significant motion artifacts. Post-procedural MTT presented a mean decrease of 19.1% for all patients and increased only in 1 of 5 patients, demonstrating in 4/5 patients an increase in tissue perfusion after revascularization. Overall mean PBF and PBV values were also analogously increased following revascularization (446% and 69.5% mean, respectively) and in the majority of selected ROIs (13/15 and 12/15 ROIs, respectively). CONCLUSIONS: Quantification of infrapopliteal angioplasty outcomes using this newly proposed, custom-made, intra-procedural PDSA algorithm was performed using PBV, MTT, and PBF maps. Further studies are required to determine its role in peripheral endovascular procedures ( ClinicalTrials.gov Identifier: NCT04356092).

Comparison of Sound Touch Elastography, Shear Wave Elastography and Vibration-Controlled Transient Elastography in Chronic Liver Disease Assessment using Liver Biopsy as the "Reference Standard".

Chronic liver disease (CLD) is currently a major cause of death. Ultrasound elastography (USE) is an imaging method that has been developed for CLD assessment. Our aim in the study described here was to evaluate and compare a new commercial variant of USE, sound touch elastography (STE), with already established USE methods, shear wave elastography (SWE) and vibration-controlled transient elastography (VCTE), using liver biopsy as the "reference standard." For our study, 139 consecutive patients underwent standard liver STE, SWE and VCTE examinations with the corresponding ultrasound devices. A receiver operator characteristic (ROC) curve analysis was performed on the stiffness values measured with each method. ROC analysis revealed, for SWE, STE and VCTE, areas under the ROC curve of 0.9397, 0.9224 and 0.9348 for fibrosis stage (F), F ≥ F1; 0.9481, 0.9346 and 0.9415 for F ≥ F2; 0.9623, 0.9591 and 0.9631 for F ≥ F3; and 0.9581, 0.9541 and 0.9632 for F = F4, respectively. In conclusion, STE performs similarly to SWE and VCTE in CLD stage differentiation.

Temporal stability assessment in shear wave elasticity images validated by deep learning neural network for chronic liver disease fibrosis stage assessment.

PURPOSE: To automatically detect and isolate areas of low and high stiffness temporal stability in shear wave elastography (SWE) image sequences and define their impact in chronic liver disease (CLD) diagnosis improvement by means of clinical examination study and deep learning algorithm employing convolutional neural networks (CNNs). MATERIALS AND METHODS: Two hundred SWE image sequences from 88 healthy individuals (F0 fibrosis stage) and 112 CLD patients (46 with mild fibrosis (F1), 16 with significant fibrosis (F2), 22 with severe fibrosis (F3), and 28 with cirrhosis (F4)) were analyzed to detect temporal stiffness stability between frames. An inverse Red, Green, Blue (RGB) colormap-to-stiffness process was performed for each image sequence, followed by a wavelet transform and fuzzy c-means clustering algorithm. This resulted in a binary mask depicting areas of high and low stiffness temporal stability. The mask was then applied to the first image of the SWE sequence, and the derived, masked SWE image was used to estimate its impact in standard clinical examination and CNN classification. Regarding the impact of the masked SWE image in clinical examination, one measurement by two radiologists was performed in each SWE image and two in the corresponding masked image measuring areas with high and low stiffness temporal stability. Then, stiffness stability parameters, interobserver variability evaluation and diagnostic performance by means of ROC analysis were assessed. The masked and unmasked sets of SWE images were fed into a CNN scheme for comparison. RESULTS: The clinical impact evaluation study showed that the masked SWE images decreased the interobserver variability of the radiologists' measurements in the high stiffness temporal stability areas (interclass correlation coefficient (ICC) = 0.92) compared to the corresponding unmasked ones (ICC = 0.76). In terms of diagnostic accuracy, measurements in the high-stability areas of the masked SWE images (area-under-the-curve (AUC) ranging from 0.800 to 0.851) performed similarly to those in the unmasked SWE images (AUC ranging from 0.805 to 0.893). Regarding the measurements in the low stiffness temporal stability areas of the masked SWE images, results for interobserver variability (ICC = 0.63) and diagnostic accuracy (AUC ranging from 0.622 to 0.791) were poor. Regarding the CNN classification, the masked SWE images showed improved accuracy (ranging from 82.5% to 95.5%) compared to the unmasked ones (ranging from 79.5% to 93.2%) for various CLD stage combinations. CONCLUSION: Our detection algorithm excludes unreliable areas in SWE images, reduces interobserver variability, and augments CNN's accuracy scores for many combinations of fibrosis stages.

A Machine-Learning Algorithm Toward Color Analysis for Chronic Liver Disease Classification, Employing Ultrasound Shear Wave Elastography.

The purpose of the present study was to employ a computer-aided diagnosis system that classifies chronic liver disease (CLD) using ultrasound shear wave elastography (SWE) imaging, with a stiffness value-clustering and machine-learning algorithm. A clinical data set of 126 patients (56 healthy controls, 70 with CLD) was analyzed. First, an RGB-to-stiffness inverse mapping technique was employed. A five-cluster segmentation was then performed associating corresponding different-color regions with certain stiffness value ranges acquired from the SWE manufacturer-provided color bar. Subsequently, 35 features (7 for each cluster), indicative of physical characteristics existing within the SWE image, were extracted. A stepwise regression analysis toward feature reduction was used to derive a reduced feature subset that was fed into the support vector machine classification algorithm to classify CLD from healthy cases. The highest accuracy in classification of healthy to CLD subject discrimination from the support vector machine model was 87.3% with sensitivity and specificity values of 93.5% and 81.2%, respectively. Receiver operating characteristic curve analysis gave an area under the curve value of 0.87 (confidence interval: 0.77-0.92). A machine-learning algorithm that quantifies color information in terms of stiffness values from SWE images and discriminates CLD from healthy cases is introduced. New objective parameters and criteria for CLD diagnosis employing SWE images provided by the present study can be considered an important step toward color-based interpretation, and could assist radiologists' diagnostic performance on a daily basis after being installed in a PC and employed retrospectively, immediately after the examination.

Focal liver lesions segmentation and classification in nonenhanced T2-weighted MRI.

PURPOSE: To automatically segment and classify focal liver lesions (FLLs) on nonenhanced T2-weighted magnetic resonance imaging (MRI) scans using a computer-aided diagnosis (CAD) algorithm. METHODS: 71 FLLs (30 benign lesions, 19 hepatocellular carcinomas, and 22 metastases) on T2-weighted MRI scans were delineated by the proposed CAD scheme. The FLL segmentation procedure involved wavelet multiscale analysis to extract accurate edge information and mean intensity values for consecutive edges computed using horizontal and vertical analysis that were fed into the subsequent fuzzy C-means algorithm for final FLL border extraction. Texture information for each extracted lesion was derived using 42 first- and second-order textural features from grayscale value histogram, co-occurrence, and run-length matrices. Twelve morphological features were also extracted to capture any shape differentiation between classes. Feature selection was performed with stepwise multilinear regression analysis that led to a reduced feature subset. A multiclass Probabilistic Neural Network (PNN) classifier was then designed and used for lesion classification. PNN model evaluation was performed using the leave-one-out (LOO) method and receiver operating characteristic (ROC) curve analysis. RESULTS: The mean overlap between the automatically segmented FLLs and the manual segmentations performed by radiologists was 0.91 ± 0.12. The highest classification accuracies in the PNN model for the benign, hepatocellular carcinoma, and metastatic FLLs were 94.1%, 91.4%, and 94.1%, respectively, with sensitivity/specificity values of 90%/97.3%, 89.5%/92.2%, and 90.9%/95.6% respectively. The overall classification accuracy for the proposed system was 90.1%. CONCLUSIONS: Our diagnostic system using sophisticated FLL segmentation and classification algorithms is a powerful tool for routine clinical MRI-based liver evaluation and can be a supplement to contrast-enhanced MRI to prevent unnecessary invasive procedures.

A new computer aided diagnosis system for evaluation of chronic liver disease with ultrasound shear wave elastography imaging.

PURPOSE: Classify chronic liver disease (CLD) from ultrasound shear-wave elastography (SWE) imaging by means of a computer aided diagnosis (CAD) system. METHODS: The proposed algorithm employs an inverse mapping technique (red-green-blue to stiffness) to quantify 85 SWE images (54 healthy and 31 with CLD). Texture analysis is then applied involving the automatic calculation of 330 first and second order textural features from every transformed stiffness value map to determine functional features that characterize liver elasticity and describe liver condition for all available stages. Consequently, a stepwise regression analysis feature selection procedure is utilized toward a reduced feature subset that is fed into the support vector machines (SVMs) classification algorithm in the design of the CAD system. RESULTS: With regard to the mapping procedure accuracy, the stiffness map values had an average difference of 0.01 ± 0.001 kPa compared to the quantification results derived from the color-box provided by the built-in software of the ultrasound system. Highest classification accuracy from the SVM model was 87.0% with sensitivity and specificity values of 83.3% and 89.1%, respectively. Receiver operating characteristic curves analysis gave an area under the curve value of 0.85 with [0.77-0.89] confidence interval. CONCLUSIONS: The proposed CAD system employing color to stiffness mapping and classification algorithms offered superior results, comparing the already published clinical studies. It could prove to be of value to physicians improving the diagnostic accuracy of CLD and can be employed as a second opinion tool for avoiding unnecessary invasive procedures.

A new automated quantification algorithm for the detection and evaluation of focal liver lesions with contrast-enhanced ultrasound.

PURPOSE: Detect and classify focal liver lesions (FLLs) from contrast-enhanced ultrasound (CEUS) imaging by means of an automated quantification algorithm. METHODS: The proposed algorithm employs a sophisticated segmentation method to detect and contour focal lesions from 52 CEUS video sequences (30 benign and 22 malignant). Lesion detection involves wavelet transform zero crossings utilization as an initialization step to the Markov random field model toward the lesion contour extraction. After FLL detection across frames, time intensity curve (TIC) is computed which provides the contrast agents' behavior at all vascular phases with respect to adjacent parenchyma for each patient. From each TIC, eight features were automatically calculated and employed into the support vector machines (SVMs) classification algorithm in the design of the image analysis model. RESULTS: With regard to FLLs detection accuracy, all lesions detected had an average overlap value of 0.89 ± 0.16 with manual segmentations for all CEUS frame-subsets included in the study. Highest classification accuracy from the SVM model was 90.3%, misdiagnosing three benign and two malignant FLLs with sensitivity and specificity values of 93.1% and 86.9%, respectively. CONCLUSIONS: The proposed quantification system that employs FLLs detection and classification algorithms may be of value to physicians as a second opinion tool for avoiding unnecessary invasive procedures.