Development and validation of a neural network for NAFLD diagnosis

Sorino, Paolo; Campanella, Angelo J.; Mirizzi, Antonella; Franco, Isabella; Bianco, Antonella; Caruso, Maria Gabriella; Misciagna, Giovanni; Aballay, Laura Rosana; Buongiorno, Claudia; Liuzzi, Rosalba; Cisternino, Anna Maria; Notarnicola, Maria; Chiloiro, Marisa; Fallucchi, Francesca; Pascoschi, Giovanni; Osella, Alberto Rubén

doi:10.1038/s41598-021-99400-y

Cited by 19 publications

(4 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future investigations could also incorporate additional preprocessing steps ( 31 ) , stain normalization on Sirius-Red stained images ( 27 ) , and extend the model to multi-class classification. We could also consider multimodal learning, since reasonable NAFLD diagnosis performance has been reported using DL on non-imaging data ( 36 , 37 ) .…”

Section: Discussionmentioning

confidence: 99%

Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning

Naik¹,

Forlano²,

Manousou³

et al. 2023

Biol. Imaging

View full text Add to dashboard Cite

Non-alcoholic fatty liver disease (NAFLD) is now the leading cause of chronic liver disease, affecting approximately 30% of people worldwide. Histopathology reading of fibrosis patterns is crucial to diagnosing NAFLD. In particular, separating mild from severe stages corresponds to a critical transition as it correlates with clinical outcomes. Deep Learning for digitized histopathology whole-slide images (WSIs) can reduce high inter- and intra-rater variability. We demonstrate a novel solution to score fibrosis severity on a retrospective cohort of 152 Sirius-Red WSIs, with fibrosis stage annotated at slide level by an expert pathologist. We exploit multiple instance learning and multiple-inferences to address the sparsity of pathological signs. We achieved an accuracy of $ 78.98\pm 5.86\% $ , an F1 score of $ 77.99\pm 5.64\%, $ and an AUC of $ 0.87\pm 0.06 $ . These results set new state-of-the-art benchmarks for this application.

show abstract

Section: Discussionmentioning

confidence: 99%

Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning

Naik¹,

Forlano²,

Manousou³

et al. 2023

Biol. Imaging

View full text Add to dashboard Cite

show abstract

“…In clinical practice, numerous works have shown how ML or e-health tools are considered various alternatives to standard diagnostic methods [10][11][12][13] such as Magnetic Resonance Imaging (MRI), ultrasounds, etc. ML approaches are already used for NAFLD diagnosis [14,15].…”

Section: Introductionmentioning

confidence: 99%

MAFUS: a Framework to predict mortality risk in MAFLD subjects

Lofù¹,

Sorino²,

Colafiglio³

et al. 2023

Preprint

View full text Add to dashboard Cite

Metabolic (dysfunction) associated fatty liver disease (MAFLD) establishes new criteria for diagnosing fatty liver disease independent of alcohol consumption and concurrent viral hepatitis infection. However, the long-term outcome of MAFLD subjects is sparse. Few articles are focused on mortality in MAFLD subjects, and none investigate how to predict a fatal outcome. In this paper, we propose an artificial intelligence-based framework named MAFUS that physicians can use for predicting mortality in MAFLD subjects. The framework uses data from various anthropometric and biochemical sources based on Machine Learning (ML) algorithms. The framework has been tested on a state-of-the-art dataset on which five ML algorithms are trained. Support Vector Machines resulted in being the best model. Furthermore, an Explainable Artificial Intelligence (XAI) analysis has been performed to understand the SVM's diagnostic reasoning and the contribution of each feature to the prediction. The MAFUS framework is easy to apply, and the required parameters are readily available in the dataset.

show abstract

“…It has been reported that non-alcoholic fatty liver disease (NAFLD) is a clinicopathological condition that encompasses a variety of chronic liver diseases ranging from asymptomatic hepatic fat accumulation to progressive liver disease, with clinical symptoms resembling alcoholic liver disease despite the absence of excessive alcohol consumption 4 , 5 . A recent study revealed that the prevalence of NAFLD diagnosed by ultrasound was estimated to be about 25% 6 . It is estimated that either NAFLD or non-alcoholic steatohepatitis (NASH) will be the most common indication for liver transplantation by 2030 7 .…”

Section: Introductionmentioning

confidence: 99%

Prediction of decreased estimated glomerular filtration rate using liver fibrosis markers: a renal biopsy-based study

Mima

2022

Sci Rep

View full text Add to dashboard Cite

Non-alcoholic fatty liver disease is the most common chronic liver disease and is associated with chronic kidney disease. The fibrosis-4 index and non-alcoholic fatty liver disease score are widely used as non-invasive diagnostic methods for non-alcoholic fatty liver disease. However, the relationship between these markers and specific renal histopathologies in chronic kidney disease remain unclear. This study included 179 patients aged between 16 and 80 years who underwent renal biopsy. We examined the association between the fibrosis-4 index or non-alcoholic fatty liver disease score and change in estimated glomerular filtration rate 12 months after kidney biopsy for each renal histopathology. Renal histopathologies were determined by renal biopsy. Our results showed that there was a significant negative correlation between the fibrosis-4 index and estimated glomerular filtration rate. In nephrosclerosis, the non-alcoholic fatty liver disease score and estimated glomerular filtration rate tended to have a negative correlation, albeit without significance. In IgA nephropathy, both the fibrosis-4 index and non-alcoholic fatty liver disease score were significantly negatively correlated with estimated glomerular filtration rate. Furthermore, the fibrosis-4 index was not associated with urinary protein-to-creatinine ratio or renal function markers such as urinary b2 microglobulin and urinary N-acetyl-d-glucosamine. Our kidney biopsy-based study showed that the liver fibrosis markers fibrosis-4 index and non-alcoholic fatty liver disease score were negatively correlated with the estimated glomerular filtration rate in nephrosclerosis and IgA nephropathy.

show abstract

Development and validation of a neural network for NAFLD diagnosis

Cited by 19 publications

References 71 publications

Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning

Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning

MAFUS: a Framework to predict mortality risk in MAFLD subjects

Prediction of decreased estimated glomerular filtration rate using liver fibrosis markers: a renal biopsy-based study

Contact Info

Product

Resources

About