Detecting liver fibrosis using a machine learning‐based approach to the quantification of the heart‐induced deformation in tagged MR images

Abstract

Liver disease causes millions of deaths per year worldwide, and approximately half of these cases are due to cirrhosis, which is an advanced stage of liver fibrosis that can be accompanied by liver failure and portal hypertension. Early detection of liver fibrosis helps in improving its treatment and prevents its progression to cirrhosis. In this work, we present a novel noninvasive method to detect liver fibrosis from tagged MRI images using a machine learning‐based approach. Specifically, coronal and sagittal tagged MRI imaging are analyzed separately to capture cardiac‐induced deformation of the liver. The liver is manually delineated and a novel image feature, namely, the histogram of the peak strain (HPS) value, is computed from the segmented liver region and is used to classify the liver as being either normal or fibrotic. Classification is achieved using a support vector machine algorithm. The in vivo study included 15 healthy volunteers (10 males; age range 30–45 years) and 22 patients (15 males; age range 25–50 years) with liver fibrosis verified and graded by transient elastography, and 10 patients only had a liver biopsy and were diagnosed with a score of F3‐F4. The proposed method demonstrates the usefulness and efficiency of extracting the HPS features from the sagittal slices for patients with moderate fibrosis. Cross‐validation of the method showed an accuracy of 83.7% (specificity = 86.6%, sensitivity = 81.8%).

Registered Trials of Artificial Intelligence Conducted on Chronic Liver Disease: A Cross-Sectional Study on ClinicalTrials.gov

“…For example, ultrasound-based MLA is more accurate in detecting steatosis, hepatic fibrosis, and localized liver lesions [9][10][11]. Several studies have demonstrated the efficiency of support vector machine (SVM) models based on magnetic resonance (MR) images and convolutional neural network (CNN) models based on computed tomography (CT) images in predicting and staging liver fibrosis [12][13][14]. Other investigators have demonstrated in previous studies that SVM models based on digital pathology images may detect steatosis and assess the degree of liver fibrosis [15,16].…”

Artificial intelligence in gastroenterology: A state-of-the-art review

“…Forty-two studies developed models addressing detection of steatosis, fibrosis, or cirrhosis based on clinical data, shear-wave elastography, CT or MRI scans, histopathology, or genetics. Of these, 27 studies developed models to detect, quantify, or predict steatosis, fibrosis, or cirrhosis[ 202 , 209 - 234 ]. Forlano et al [ 215 ] developed a ML-based model for quantification of steatosis, inflammation, ballooning, and fibrosis using biopsies from patients with NAFLD.…”

Application of Artificial Intelligence in Chronic Liver Diseases: A Systematic Review and Meta-analysis

“…Eventually, a total of 78 articles were included in the qualitative analysis, of which 17 were included in the quantitative analysis (15 studies on liver brosis and 2 studies on NAFLD). There were 11 studies integrating AI with imaging modalities, i.e., ultrasonography (21)(22)(23)(24)(25) , elastography (26,27) , computed tomography (CT) (28,29) and magnetic resonance imaging (MRI) (30,31) , to facilitate the diagnosis of liver brosis and NAFLD. The other 6 studies developed AI models using clinical and laboratory data, such as the presence of other underlying diseases or ascites, liver chemistry tests, and platelet and white blood cell counts, to predict liver brosis stages (32)(33)(34)(35)(36)(37) .…”

“…The other 6 studies developed AI models using clinical and laboratory data, such as the presence of other underlying diseases or ascites, liver chemistry tests, and platelet and white blood cell counts, to predict liver brosis stages (32)(33)(34)(35)(36)(37) . Regarding the types of AI, 6 studies used convolutional neural networks (CNNs) (21,23,(27)(28)(29)31) , 5 studies used arti cial neural networks (ANNs) (24,25,(34)(35)(36) , 5 studies used multiple AI models (22,26,32,33,37) and 1 study used a support vector machine (SVM) (30) . The study characteristics, sensitivity, speci city, prevalence, validation methods and other extracted data from the included studies are shown in Table 1.…”

“…(Supplemental table 2) There were 8 studies investigating the performance of AI-assisted systems for the diagnosis of signi cant brosis (≥ F2). (21,22,26,27,29,31,35,37) Four studies used CNNs as AI models (22,27,28,30) , 1 study utilized an ANN (35) , and the other 3 studies used multiple AI models. (22,26,37) In this group, the AI models were integrated into ultrasonography in 2 studies (21,22) , elastography in 2 studies (26,27) , CT in 1 study (29) , MRI in 1 study (31) , and clinical and laboratory parameters in 2 studies.…”