Search

• Develop a DL-based CAD system for hepatic steatosis grading assessment. • Evaluate the performance of popular pre-trained (fine-tuned) DL schemes. • Compare performance using original and augmented image datasets with up-sampling. • Compare performance against the traditional hepatorenal index calculation. To evaluate the performance of pre-trained deep learning schemes (DLS) in hepatic steatosis (HS) grading of Non-Alcoholic Fatty Liver Disease (NAFLD) patients, using as input B-mode US images containing right kidney (RK) cortex and liver parenchyma (LP) areas indicated by an expert radiologist. A total of 112 consecutively enrolled, biopsy-validated NAFLD patients underwent a regular abdominal B-mode US examination. For each patient, a radiologist obtained a B-mode US image containing RK cortex and LP and marked a point between the RK and LP, around which a window was automatically cropped. The cropped image dataset was augmented using up-sampling, and the augmented and non-augmented datasets were sorted by HS grade. Each dataset was split into training (70%) and testing (30%), and fed separately as input to InceptionV3, MobileNetV2, ResNet50, DenseNet201, and NASNetMobile pre-trained DLS. A receiver operating characteristic (ROC) analysis of hepatorenal index (HRI) measurements by the radiologist from the same cropped images was used for comparison with the performance of the DLS. With the test data, the DLS reached 89.15 %–93.75 % accuracy when comparing HS grades S0–S1 vs. S2–S3 and 79.69 %–91.21 % accuracy for S0 vs. S1 vs. S2 vs. S3 with augmentation, and 80.45–82.73 % accuracy when comparing S0–S1 vs. S2–S3 and 59.54 %–63.64 % accuracy for S0 vs. S1 vs. S2 vs. S3 without augmentation. The performance of radiologists' HRI measurement after ROC analysis was 82 %, 91.56 %, and 96.19 % for thresholds of S ≥ S1, S ≥ S2, and S = S3, respectively. All networks achieved high performance in HS assessment. DenseNet201 with the use of augmented data seems to be the most efficient supplementary tool for NAFLD diagnosis and grading. [ABSTRACT FROM AUTHOR]

Abstract Sedimentological studies of the Upper Cretaceous–lower Eocene limestones in the western part of the Ionian basin (Araxos area) indicate that these deposits are composed of calciturbidites interbedded with breccia-microbreccia. Breccia - microbreccia deposits are structureless, display channelized geometry with calciturbiditic blocks internally to the channels. Most of the clasts were sourced from the underlying Lower Cretaceous "Vigla limestones". Calciturbidites include T a to T e Bouma sub-divisions, and are organized in cycles that form channelized deposits with a high degree of amalgamation. Statistical analysis confirms the presence of order in the sub-division sequence. The thickness of event beds in the studied section shows a lognormal statistical distribution, typical of turbidite successions. Limestone microfacies suggest deep-water deposits and reworked shelf deposits. The intense extensional tectonic activity in the Ionian basin during the Early Cretaceous, with synthetic and antithetic faults, produced active platform margins and asymmetrical grabens. In this regime, large amounts of coarse-grained material became available and accumulated in the basin. High slope gradients led to slumping. During the Late Cretaceous, the uplifted margins of the grabens caused erosion of the pre-existing deposits of the Lower Cretaceous "Vigla Formation". This event led to the accumulation of channelized microbreccia and breccia units and transport of platform deposits by turbidity currents. The Early Cretaceous to early Eocene depositional history in the Ionian Basin indicates that the regional tectonic activity, rather than the eustatic sea-level changes, was the major factor that influenced the basin evolution, suggesting a syn-rift stage being active from the Jurassic to the early Eocene. [ABSTRACT FROM AUTHOR]

Chronic Liver Disease (CLD) is considered as one of the leading causes of death worldwide today. Shear Wave Elastography (SWE) is a recently introduced technique which offers real-time elasticity imaging as well as stiffness quantification over a 2D region-of-interest (ROI). The major challenge for clinicians nowadays is the accurate and on-time estimation of liver fibrosis progress toward an efficient treatment to avoid unnecessary and costly invasive procedures. Classify CLD from SWE imaging by means of an optimized ROI selection procedure and a computer aided diagnosis system. The proposed algorithm employs a ROI selection technique (areas with no stiffness variation across-time) to quantify 32 SWE images (16 healthy and 16 with CLD). The selection procedure employs four SWE images from the same area of liver parenchyma having 5 s time distance acquired from each patient. Subsequently, the mean stiffness value of pixels having Stiffness Standard Deviation <2 across time is calculated providing the new ROI for analysis. From each final ROI, 185 textural features were computed. Stepwise multi-linear-regression analysis was utilized to avoid feature redundancy leading to a feature subset feeding a Support Vector Machine (SVM) classifier. Highest classification accuracy from the SVM-model was 94.3% with sensitivity and specificity values of 93.8% and 94.6%, respectively. Best feature combination for the SVM model comprised the Standard Deviation, Sum-Variance and Contrast features. A new automatic SWE reliability algorithm for CLD diagnosis has been developed that could prove to be of value to physicians improving the diagnostic accuracy of CLD. No disclosure. [ABSTRACT FROM AUTHOR]

Background Patients with liver steatosis and diabetes mellitus can benefit from medications like glucagon-like peptide 1 receptor agonists or sodium-glucose co-transporter 2 inhibitors, as far as both hyperglycemia and fatty liver are concerned. Studies comparing members of both these families have not yet been published. We aimed to compare the effects of Empagliflozin and Dulaglutide, focusing primarily on liver steatosis. Methodology This prospective, observational, controlled study enrolled 78 patients from two centers in Athens, Greece. Adults with type 2 diabetes mellitus (DM2) and nonalcoholic fatty liver disease were assigned to one of three groups and received either Empagliflozin or Dulaglutide or any other medical treatment deemed appropriate by their physician. The primary endpoint was the reduction in liver fat fraction, assessed using magnetic resonance imaging-proton density fat fraction. Additionally, we evaluated the proportion of patients achieving a relative reduction above 30% of their initial liver fat concentration. Results The Empagliflozin group exhibited a reduction in liver fat fraction. Furthermore, the percentage of patients with a relative reduction of liver steatosis, >30%, was significantly larger in this group, compared to the Dulaglutide and Control groups. Significant body weight reduction was observed in all three groups, but no improvement in fibrosis assessing scores was noted. Conclusions Empagliflozin is effective in improving liver steatosis, while Dulaglutide does not exhibit a similar effect. Larger studies, comparing these or related agents, are necessary, to further assess benefits in patients with DM2 and nonalcoholic fatty liver., Competing Interests: The authors have declared that no competing interests exist., (Copyright © 2024, Koullias et al.)

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., (© 2022 by the American Diabetes Association.)

Background and Aims: Liver stiffness measurements (LSMs) by 2-dimensional-shear-wave elastography (LSM 2D-SWE ) are now widely used in hepatology. However, relevant information for primary biliary cholangitis (PBC) is scant. We compare LSM 2D-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 LSM 2D-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 LSM 2D-SWE estimates., Results: Liver fibrosis stages F0-F4 were found in 4, 19, 19, 16 and 10 cases, respectively. Across stages F0-F4, the LSM 2D-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 LSM 2D-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 LSM 2D-SWE for mild, significant, severe fibrosis and cirrhosis was highly significant in all comparisons ( p <.001), with AUC 2D-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 LSM 2D-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 R 2 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.

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.

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., (© 2019 American Association of Physicists in Medicine.)

Two-dimensional shear wave elastography (2D-SWE) has proven to be efficient for the evaluation of liver fibrosis in small to moderate-sized clinical trials. We aimed at running a larger-scale meta-analysis of individual data. Centers which have worked with Aixplorer ultrasound equipment were contacted to share their data. Retrospective statistical analysis used direct and paired receiver operating characteristic and area under the receiver operating characteristic curve (AUROC) analyses, accounting for random effects. Data on both 2D-SWE and liver biopsy were available for 1,134 patients from 13 sites, as well as on successful transient elastography in 665 patients. Most patients had chronic hepatitis C (n = 379), hepatitis B (n = 400), or nonalcoholic fatty liver disease (n = 156). AUROCs of 2D-SWE in patients with hepatitis C, hepatitis B, and nonalcoholic fatty liver disease were 86.3%, 90.6%, and 85.5% for diagnosing significant fibrosis and 92.9%, 95.5%, and 91.7% for diagnosing cirrhosis, respectively. The AUROC of 2D-SWE was 0.022-0.084 (95% confidence interval) larger than the AUROC of transient elastography for diagnosing significant fibrosis (P = 0.001) and 0.003-0.034 for diagnosing cirrhosis (P = 0.022) in all patients. This difference was strongest in hepatitis B patients., Conclusion: 2D-SWE has good to excellent performance for the noninvasive staging of liver fibrosis in patients with hepatitis B; further prospective studies are needed for head-to-head comparison between 2D-SWE and other imaging modalities to establish disease-specific appropriate cutoff points for assessment of fibrosis stage. (Hepatology 2018;67:260-272)., (© 2017 The Authors. Hepatology published by Wiley Periodicals, Inc., on behalf of the American Association for the Study of Liver Diseases.)

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., (Copyright © 2017 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.)

The dielectric properties of biological tissues can contribute non-invasively to a better characterization and understanding of the structural properties and physiology of living organisms. The question we asked, is whether these induced changes are effected by an endogenous or exogenous cellular stress, and can they be detected non-invasively in the form of a dielectric response, e.g., an AC conductivity switch in the broadband frequency spectrum. This study constitutes the first methodological approach for the detection of environmental stress-induced damage in mammalian tissues by the means of broadband dielectric spectroscopy (BDS) at the frequencies of 1-10⁶ Hz. Firstly, we used non-ionizing (NIR) and ionizing radiation (IR) as a typical environmental stress. Specifically, rats were exposed to either digital enhanced cordless telecommunication (DECT) radio frequency electromagnetic radiation or to γ-radiation, respectively. The other type of stress, characterized usually by high genomic instability, was the pathophysiological state of human cancer (lung and prostate). Analyzing the results of isothermal dielectric measurements provided information on the tissues' water fraction. In most cases, our methodology proved sufficient in detecting structural changes, especially in the case of IR and malignancy. Useful specific dielectric response patterns are detected and correlated with each type of stress. Our results point towards the development of a dielectric-based methodology for better understanding and, in a relatively invasive way, the biological and structural changes effected by radiation and developing lung or prostate cancer often associated with genomic instability.

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.

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.