Clinical Value of Information Entropy Compared with Deep Learning for Ultrasound Grading of Hepatic Steatosis

Abstract

Entropy is a quantitative measure of signal uncertainty and has been widely applied to ultrasound tissue characterization. Ultrasound assessment of hepatic steatosis typically involves a backscattered statistical analysis of signals based on information entropy. Deep learning extracts features for classification without any physical assumptions or considerations in acoustics. In this study, we assessed clinical values of information entropy and deep learning in the grading of hepatic steatosis. A total of 205 participants underwent ultrasound examinations. The image raw data were used for Shannon entropy imaging and for training and testing by the pretrained VGG-16 model, which has been employed for medical data analysis. The entropy imaging and VGG-16 model predictions were compared with histological examinations. The diagnostic performances in grading hepatic steatosis were evaluated using receiver operating characteristic (ROC) curve analysis and the DeLong test. The areas under the ROC curves when using the VGG-16 model to grade mild, moderate, and severe hepatic steatosis were 0.71, 0.75, and 0.88, respectively; those for entropy imaging were 0.68, 0.85, and 0.9, respectively. Ultrasound entropy, which varies with fatty infiltration in the liver, outperformed VGG-16 in identifying participants with moderate or severe hepatic steatosis (p < 0.05). The results indicated that physics-based information entropy for backscattering statistics analysis can be recommended for ultrasound diagnosis of hepatic steatosis, providing not only improved performance in grading but also clinical interpretations of hepatic steatosis.

Accurate and generalizable quantitative scoring of liver steatosis from ultrasound images via scalable deep learning

“…Unlike attenuation imaging (ATI)[ 46 ], FibroScan, or some other reported DL solutions[ 22 , 25 , 26 ], our algorithm accepts images taken from both hepatic lobes rather than a selected area of interest in a specific location. We categorized 2D US images into six major viewpoints (Figure 2 ), which we further grouped into four view groups.…”

“…This is encouraging because, unlike CAP, our DL algorithm can be applied to many different liver viewpoints and does not require additional equipment outside of an US scanner. Our DL algorithm enjoys similar advantages in flexibility over other quantitative US techniques[ 25 , 49 ], which examines the attenuation, brightness, or echogenicity change within a small region of interest (ROI). Such restrictions may result in missing other useful information for steatosis diagnosis (for example, liver/kidney contrast and the loss of vessel walls).…”

“…This dwarfs the training set size of other works and should contribute to better model generalizability. Another important point is that most prior studies used one specific viewpoint[ 19 , 20 , 24 ] or manually defined area of interest[ 22 , 25 , 26 ], which can restrict their applicability. Like Byra et al [ 27 ], we investigated performance across different views.…”

Ultrasound Sample Entropy Imaging: A New Approach for Evaluating Hepatic Steatosis and Fibrosis

“…Initially, an algorithmic scheme based on Fourier analysis was proposed to establish the PDF of ultrasound RF data to calculate Shannon entropy [34] – [36] . The statistical histogram was then used as a less computationally complex alternative method to reconstruct the PDF of ultrasound signals, increasing the practical applicability of Shannon entropy [16] – [18] , [29] , [37] . A common problem for PDF-based entropies is that the probability distributions of ultrasound RF signals may be identical for different scattering microstructures, causing ambiguity in the physical meaning of ultrasound backscattering.…”

“…Ultrasound parametric imaging based on Shannon entropy was demonstrated to improve the accuracy of hepatic steatosis assessment compared with that of imaging based on conventional statistical distributions [16] and improved evaluations of metabolic syndrome risks among individuals with hepatic steatosis [17] . The diagnostic performance of Shannon entropy imaging in grading hepatic steatosis is also competitive compared with that of deep learning [18] .…”