Assessment of liver fibrosis in chronic hepatitis B via multimodal data

Scaling-law mechanical marker for liver fibrosis diagnosis and drug screening through machine learning

Studies of cell and tissue mechanics have shown that significant changes in cell and tissue mechanics during lesions and cancers are observed, which provides new mechanical markers for disease diagnosis based on machine learning. However, due to the lack of effective mechanic markers, only elastic modulus and iconographic features are currently used as markers, which greatly limits the application of cell and tissue mechanics in disease diagnosis. Here, we develop a liver pathological state classifier through a support vector machine method, based on high dimensional viscoelastic mechanical data. Accurate diagnosis and grading of hepatic fibrosis facilitates early detection and treatment and may provide an assessment tool for drug development. To this end, we used the viscoelastic parameters obtained from the analysis of creep responses of liver tissues by a self-similar hierarchical model and built a liver state classifier based on machine learning. Using this classifier, we implemented a fast classification of healthy, diseased, and mesenchymal stem cells (MSCs)-treated fibrotic live tissues, and our results showed that the classification accuracy of healthy and diseased livers can reach 0.99, and the classification accuracy of the three liver tissues mixed also reached 0.82. Finally, we provide screening methods for markers in the context of massive data as well as high-dimensional viscoelastic variables based on feature ablation for drug development and accurate grading of liver fibrosis. We propose a novel classifier that uses the dynamical mechanical variables as input markers, which can identify healthy, diseased, and post-treatment liver tissues.

Simultaneous grading diagnosis of liver fibrosis, inflammation, and steatosis using multimodal quantitative ultrasound and artificial intelligence framework

Noninvasive, accurate, and simultaneous grading of liver fibrosis, inflammation, and steatosis is valuable for reversing the progression and improving the prognosis quality of chronic liver diseases (CLDs). In this study, we established an artificial intelligence framework for simultaneous grading diagnosis of these three pathological types through fusing multimodal tissue characterization parameters dug by quantitative ultrasound methods derived from ultrasound radiofrequency signals, B-mode images, shear wave elastography images, and clinical ultrasound systems, using the liver biopsy results as the classification criteria. One hundred forty-two patients diagnosed with CLD were enrolled in this study. The results show that for the classification of fibrosis grade ≥ F1, ≥ F2, ≥ F3, and F4, the highest AUCs were respectively 0.69, 0.82, 0.84, and 0.88 with single clinical indicator alone, and were 0.81, 0.83, 0.89, and 0.91 with the proposed method. For the classification of inflammation grade ≥ A2 and A3, the highest AUCs were respectively 0.66 and 0.76 with single clinical indicator alone and were 0.80 and 0.93 with the proposed method. For the classification of steatosis grade ≥ S1 and ≥ S2, the highest AUCs were respectively 0.71 and 0.90 with single clinical indicator alone and were 0.75 and 0.92 with the proposed method. The proposed method can effectively improve the grading diagnosis performance compared with the present clinical indicators and has potential applications for noninvasive, accurate, and simultaneous diagnosis of CLDs.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

Multiparametric Quantitative US Examination of Liver Fibrosis: A Feature-engineering and Machine-learning Based Analysis

Quantitative ultrasound (QUS), which is commonly used to extract quantitative features from the ultrasound radiofrequency (RF) data or the RF envelope signals for tissue characterization, is becoming a promising technique for noninvasive assessments of liver fibrosis. However, the number of feature variables examined and finally used in the existing QUS methods is typically small, to some extent limiting the diagnostic performance. Therefore, this paper devises a new multiparametric QUS (MP-QUS) method which enables the extraction of a large number of feature variables from US RF signals and allows for the use of feature-engineering and machinelearning based algorithms for liver fibrosis assessment. In the MP-QUS, eighty-four feature variables were extracted from multiple QUS parametric maps derived from the RF signals and the envelope data. Afterwards, feature reduction and selection were performed in turn to remove the feature redundancy and identify the best combination of features in the reduced feature set. Finally, a variety of machine-learning algorithms were tested for classifying liver fibrosis with the selected features, based on the results of which the optimal classifier was established and used for final classification. The performance of the proposed MPQUS method for staging liver fibrosis was evaluated on an animal model, with histologic examination as the reference standard. The mean accuracy, sensitivity, specificity and area under the receiver-operating-characteristic curve achieved by MP-QUS are respectively 83.38%, 86.04%, 80.82% and 0.891 for recognizing significant liver fibrosis, and 85.50%, 88.92%, 85.24% and 0.924 for diagnosing liver cirrhosis. The proposed MP-QUS method paves a way for its future extension to assess liver fibrosis in human subjects.

An intracellular diamine oxidase triggered hyperpolarized 129Xe magnetic resonance biosensor

Here, a novel method was developed for suppressing 129Xe signals in cucurbit[6]uril (CB6) until the trigger is activated by a specific enzyme. Due to its noncovalent interactions with amino-groups and CB6, putrescine dihydrochloride (Put) was chosen for blocking interactions between 129Xe and CB6. Upon adding diamine oxidase (DAO), Put was released from CB6 and a 129Xe@CB6 Hyper-CEST signal emerged. This proposed 129Xe biosensor was then tested in small intestinal villus epithelial cells.