scholarly journals Cascaded Deep Learning Neural Network for Automated Liver Steatosis Diagnosis Using Ultrasound Images

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5304
Author(s):  
Se-Yeol Rhyou ◽  
Jae-Chern Yoo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Liver Steatosis ◽  
Semantic Segmentation ◽  
Speckle Noise ◽  
Ultrasound Images ◽  
Deep Learning Neural Network

Diagnosing liver steatosis is an essential precaution for detecting hepatocirrhosis and liver cancer in the early stages. However, automatic diagnosis of liver steatosis from ultrasound (US) images remains challenging due to poor visual quality from various origins, such as speckle noise and blurring. In this paper, we propose a fully automated liver steatosis prediction model using three deep learning neural networks. As a result, liver steatosis can be automatically detected with high accuracy and precision. First, transfer learning is used for semantically segmenting the liver and kidney (L-K) on parasagittal US images, and then cropping the L-K area from the original US images. The second neural network also involves semantic segmentation by checking the presence of a ring that is typically located around the kidney and cropping of the L-K area from the original US images. These cropped L-K areas are inputted to the final neural network, SteatosisNet, in order to grade the severity of fatty liver disease. The experimental results demonstrate that the proposed model can predict fatty liver disease with the sensitivity of 99.78%, specificity of 100%, PPV of 100%, NPV of 99.83%, and diagnostic accuracy of 99.91%, which is comparable to the common results annotated by medical experts.

Deep Learning Techniques of Fatty Liver Using Multi-view Ultrasound Images scanned by Different Scanners (Preprint)

2021 ◽  
Author(s):  
Taewoo Kim ◽  
Dong Hyun Lee ◽  
Eun-Kee Park ◽  
Sanghun Choi
Keyword(s):  
Deep Learning ◽  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Normal Subjects ◽  
Ultrasound Images ◽  
Learning Techniques ◽  
Fat Fraction ◽  
The Right ◽  
Deep Learning Model

BACKGROUND Fat fraction values obtained from magnetic resonance images (MRI) can be used to obtain an accurate diagnosis of fatty liver diseases. However, MRI is expensive and cannot be performed for everyone. OBJECTIVE In this study, we aim to develop multi-view ultrasound image-based convolutional deep learning models to detect fatty liver disease and yield fat fraction values. METHODS We extracted 90 (the right intercostal view) and 90 (the right intercostal view containing the right renal cortex) ultrasound images from 39 fatty liver subjects (MRI-PDFF ≥ 5%) and 51 normal subjects (MRI-PDFF < 5%) containing MRI-PDFF values from Good Gang-An Hospital. We combined liver and kidney-liver (CLKL) images to train the deep learning models, and developed classification and regression models based on VGG19 to classify fatty liver disease and yield fat fraction values. We employed the data augmentation techniques such as flip and rotation to prevent the deep learning model from overfitting. We determined the deep learning model with performance metrics such as accuracy, sensitivity, specificity, and coefficient of determination (R2). RESULTS In demographic information, all metrics such as age and sex were similar between the two groups, i.e., fatty liver disease and normal subjects. In classification, model trained on CLKL images achieved 80.1% accuracy, 86.2% precision, and 80.5% specificity to detect fatty liver disease. In regression, the predicted fat fraction values of the regression model trained on CLKL images correlated with MRI-proton density fat fraction (MRI-PDFF) values (R2, 0.633), indicating that the predicted fat fraction values were moderately estimated. CONCLUSIONS With deep learning techniques and multi-view ultrasound images, it is potentially possible to replace MRI-PDFF values with deep learning predictions for detecting fatty liver disease and estimating fat fraction values.

Non-Invasive Approaches to Estimate Liver Steatosis and Stiffness in Children with Non-Alcoholic Fatty Liver Disease

2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Toshifumi Yodoshi ◽  
Sarah Orkin ◽  
Andrew T. Trout ◽  
Ana Catalina Arce-Clachar ◽  
Kristin Bramlage ◽  
...  
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Liver Steatosis ◽  
Alcoholic Fatty Liver ◽  
Non Invasive ◽  
Alcoholic Fatty Liver Disease

Relationship of serum vaspin, nafld fibrosis score to ultrasonographic detection and quantification of steatosis in nonalcoholic fatty liver disease patients

QJM ◽  
2021 ◽  
Vol 114 (Supplement_1) ◽  
Author(s):  
Essam Mohamed Byoumy ◽  
Moataz Mohamed Sayed ◽  
Shereen Abo Baker Abd El-Rahman ◽  
Sara Abd Elkader Al-Nakib ◽  
Mohamed Magdy Salama ◽  
...  
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Liver Steatosis ◽  
Control Group ◽  
P Value ◽  
Fibrosis Score ◽  
Alcoholic Fatty Liver ◽  
Nafld Fibrosis Score ◽  
Detection And Quantification

Abstract Background Ectopic hepatic lipid accumulation is closely related to the development of insulin resistance, which is regarded as one of the most significant risk factors of non-alcoholic fatty liver disease (NAFLD). The aim of the study was to evaluate and validate the diagnostic value of serum vaspin, NAFLD Fibrosis Score and sonograghic parameters in detection and quantification of liver steatosis and determining further need for liver biopsy or other means to establish NAFLD diagnosis. Methods This study was carried out on 60 patients having bright liver in ultrasonography and 30 healthy persons as controls. The subjects were divided into the following groups; group A: 30 age and sex matched healthy volunteers (control group), group B: 20 patients with fatty liver grade I, group C: 20 patients with fatty liver grade II and group D: 20 patients with fatty liver grade III. Results serum vaspine levels and NAFLD fibrosis score, were significantly higher in patients than in controls with p-value:&lt;0.001. There was a significant positive correlation between NAFLD fibrosis score and serum vaspin and ultrasonographic findngs of NAFLD with p-value: &lt;0.001. Conclusion Vaspin seem to be the most suitable non-invasive biomarker in predicting both intrahepatic lipid contents in NAFLD group.

scholarly journals A novel model for predicting fatty liver disease by means of an artificial neural network

2020 ◽  
Author(s):  
Yi-Shu Chen ◽  
Dan Chen ◽  
Chao Shen ◽  
Ming Chen ◽  
Chao-Hui Jin ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Liver Disease ◽  
Diagnostic Accuracy ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Health Check ◽  
Ann Model ◽  
Artificial Neural ◽  
Input Variables

Abstract Background The artificial neural network (ANN) emerged recently as a potent diagnostic tool, especially for complicated systemic diseases. This study aimed to establish a diagnostic model for the recognition of fatty liver disease (FLD) by virtue of the ANN. Methods A total of 7,396 pairs of gender- and age-matched subjects who underwent health check-ups at the First Affiliated Hospital, College of Medicine, Zhejiang University (Hangzhou, China) were enrolled to establish the ANN model. Indices available in health check-up reports were utilized as potential input variables. The performance of our model was evaluated through a receiver-operating characteristic (ROC) curve analysis. Other outcome measures included diagnostic accuracy, sensitivity, specificity, Cohen’s k coefficient, Brier score, and Hosmer-Lemeshow test. The Fatty Liver Index (FLI) and the Hepatic Steatosis Index (HSI), retrained using our training-group data with its original designated input variables, were used as comparisons in the capability of FLD diagnosis. Results Eight variables (age, gender, body mass index, alanine aminotransferase, aspartate aminotransferase, uric acid, total triglyceride, and fasting plasma glucose) were eventually adopted as input nodes of the ANN model. By applying a cut-off point of 0.51, the area under ROC curves of our ANN model in predicting FLD in the testing group was 0.908 [95% confidence interval (CI), 0.901–0.915]—significantly higher (P &lt; 0.05) than that of the FLI model (0.881, 95% CI, 0.872–0.891) and that of the HSI model (0.885; 95% CI, 0.877–0.893). Our ANN model exhibited higher diagnostic accuracy, better concordance with ultrasonography results, and superior capability of calibration than the FLI model and the HSI model. Conclusions Our ANN system showed good capability in the diagnosis of FLD. It is anticipated that our ANN model will be of both clinical and epidemiological use in the future.

scholarly journals Sex Dimorphism of Nonalcoholic Fatty Liver Disease (NAFLD) in Pparg-Null Mice

2021 ◽  
Vol 22 (18) ◽  
pp. 9969
Author(s):  
Mariano Schiffrin ◽  
Carine Winkler ◽  
Laure Quignodon ◽  
Aurélien Naldi ◽  
Martin Trötzmüller ◽  
...  
Keyword(s):  
Gene Expression ◽  
Liver Disease ◽  
Fatty Liver ◽  
Nonalcoholic Fatty Liver Disease ◽  
Fatty Liver Disease ◽  
Molecular Mechanisms ◽  
Liver Steatosis ◽  
Whole Body ◽  
Sex Dimorphism ◽  
Nonalcoholic Fatty Liver

Men with nonalcoholic fatty liver disease (NAFLD) are more exposed to nonalcoholic steatohepatitis (NASH) and liver fibrosis than women. However, the underlying molecular mechanisms of NALFD sex dimorphism are unclear. We combined gene expression, histological and lipidomic analyses to systematically compare male and female liver steatosis. We characterized hepatosteatosis in three independent mouse models of NAFLD, ob/ob and lipodystrophic fat-specific (PpargFΔ/Δ) and whole-body PPARγ-null (PpargΔ/Δ) mice. We identified a clear sex dimorphism occurring only in PpargΔ/Δ mice, with females showing macro- and microvesicular hepatosteatosis throughout their entire life, while males had fewer lipid droplets starting from 20 weeks. This sex dimorphism in hepatosteatosis was lost in gonadectomized PpargΔ/Δ mice. Lipidomics revealed hepatic accumulation of short and highly saturated TGs in females, while TGs were enriched in long and unsaturated hydrocarbon chains in males. Strikingly, sex-biased genes were particularly perturbed in both sexes, affecting lipid metabolism, drug metabolism, inflammatory and cellular stress response pathways. Most importantly, we found that the expression of key sex-biased genes was severely affected in all the NAFLD models we tested. Thus, hepatosteatosis strongly affects hepatic sex-biased gene expression. With NAFLD increasing in prevalence, this emphasizes the urgent need to specifically address the consequences of this deregulation in humans.

Sign in / Sign up

Export Citation Format

Share Document