Objective: The study evaluates quantitative ultrasound (QUS) texture features with machine learning (ML) to enhance the sensitivity of B-mode ultrasound (US) for the detection of fibrosis at an early stage and distinguish it from advanced fibrosis. Different ML methods were evaluated to determine the best diagnostic model. Methods: 233 B-mode images of liver lobes with early and advanced-stage fibrosis induced in a rat model were analyzed. Sixteen features describing liver texture were measured from regions of interest (ROIs) drawn on B-mode images. The texture features included a first-order statistics run length (RL) and gray-level co-occurrence matrix (GLCM). The features discriminating between early and advanced fibrosis were used to build diagnostic models with logistic regression (LR), naïve Bayes (nB), and multi-class perceptron (MLP). The diagnostic performances of the models were compared by ROC analysis using different train-test sampling approaches, including leave-one-out, 10-fold cross-validation, and varying percentage splits. METAVIR scoring was used for histological fibrosis staging of the liver. Results: 15 features showed a significant difference between the advanced and early liver fibrosis groups, p < 0.05. Among the individual features, first-order statics features led to the best classification with a sensitivity of 82.1–90.5% and a specificity of 87.1–89.8%. For the features combined, the diagnostic performances of nB and MLP were high, with the area under the ROC curve (AUC) approaching 0.95–0.96. LR also yielded high diagnostic performance (AUC = 0.91–0.92) but was lower than nB and MLP. The diagnostic variability between test-train trials, measured by the coefficient-of-variation (CV), was higher for LR (3–5%) than nB and MLP (1–2%). Conclusion: Quantitative ultrasound with machine learning differentiated early and advanced fibrosis. Ultrasound B-mode images contain a high level of information to enable accurate diagnosis with relatively straightforward machine learning methods like naïve Bayes and logistic regression. Implementing simple ML approaches with QUS features in clinical settings could reduce the user-dependent limitation of ultrasound in detecting early-stage liver fibrosis.

Machine learning for medical imaging not only requires sufficient amounts of data for training and testing but also that the data be independent. It is common to see highly interdependent data whenever there are inherent correlations between observations. This is especially to be expected for sequential imaging data taken from time series. In this study, we evaluate the use of statistical measures to test the independence of sequential ultrasound image data taken from the same case. A total of 1180 B-mode liver ultrasound images with 5903 regions of interests were analyzed. The ultrasound images were taken from two liver disease groups, fibrosis and steatosis, as well as normal cases. Computer-extracted texture features were then used to train a machine learning (ML) model for computer-aided diagnosis. The experiment resulted in high two-category diagnosis using logistic regression, with AUC of 0.928 and high performance of multicategory classification, using random forest ML, with AUC of 0.917. To evaluate the image region independence for machine learning, Jenson–Shannon (JS) divergence was used. JS distributions showed that images of normal liver were independent from each other, while the images from the two disease pathologies were not independent. To guarantee the generalizability of machine learning models, and to prevent data leakage, multiple frames of image data acquired of the same object should be tested for independence before machine learning. Such tests can be applied to real-world medical image problems to determine if images from the same subject can be used for training.

Background: Hepatocellular carcinoma (HCC) detection with B-mode and contrast-enhanced ultrasound (CUS) imaging often varies between subjects, especially in patients with background cirrhosis. Various factors contribute to this variability, including the tumor blood flow, tumor size, internal echoes, and its location in livers with diffuse fibro-cirrhotic changes. Objective: Towards improving lesion detection, this study evaluates a vasodilator, hydralazine, to enhance the visibility of HCC by reducing its blood flow relative to the surrounding liver tissue. Methods: HCC were analyzed for tumor visibility measured for B-mode, CUS, and hydralazine-augmented-contrast ultrasound (HyCUS) in an autochthonous HCC rat model. 21 tumors from 12 rats were studied. B-mode and CUS images were acquired before hydralazine injection. Rats received an intravenous hydralazine injection of 5 mg/kg,then images were acquired 20 min later. Four rats were used as controls. The difference in echo intensity of the lesion and the surrounding tissue was used to determine the visibility index (VI). Results: The visibility index for HCC was found to be significantly improved with the use of HyCUS imaging compared to traditional B-mode and CUS imaging. The visibility index for HCC was 16.5 ± 2.8 for HyCUS, compared to 5.3 ± 4.8 for B-mode and 4.1 ± 3.8 for CUS. The differences between HyCUS and the other imaging modalities were statistically significant, with p-values of 0.001 and 0.02, respectively. Additionally, when compared to control cases, HyCUS showed higher discrimination of HCC (VI = 6.4 ± 1.2) with a p-value of 0.003, while B-mode (VI = 6.7 ± 1.4, p = 0.5) and CUS (VI = 6.4 ± 1.2, p = 0.3) showed lower discrimination. Conclusion: Vascular blood flow modulation by hydralazine enhances the visibility of HCC. HyCUS offers a potential problem-solving method for detecting HCC when B-mode and CUS are unsuccessful, especially with background fibro-cirrhotic liver disease. Future evaluation of the approach in humans will determine its translatability for clinical applications.

No abstract