Classification and staging of chronic liver disease from multimodal data

Open challenges and opportunities in federated foundation models towards biomedical healthcare

This survey explores the transformative impact of foundation models (FMs) in artificial intelligence, focusing on their integration with federated learning (FL) in biomedical research. Foundation models such as ChatGPT, LLaMa, and CLIP, which are trained on vast datasets through methods including unsupervised pretraining, self-supervised learning, instructed fine-tuning, and reinforcement learning from human feedback, represent significant advancements in machine learning. These models, with their ability to generate coherent text and realistic images, are crucial for biomedical applications that require processing diverse data forms such as clinical reports, diagnostic images, and multimodal patient interactions. The incorporation of FL with these sophisticated models presents a promising strategy to harness their analytical power while safeguarding the privacy of sensitive medical data. This approach not only enhances the capabilities of FMs in medical diagnostics and personalized treatment but also addresses critical concerns about data privacy and security in healthcare. This survey reviews the current applications of FMs in federated settings, underscores the challenges, and identifies future research directions including scaling FMs, managing data diversity, and enhancing communication efficiency within FL frameworks. The objective is to encourage further research into the combined potential of FMs and FL, laying the groundwork for healthcare innovations.

A multi-modal deep neural network for multi-class liver cancer diagnosis

Liver disease is a potentially asymptomatic clinical entity that may progress to patient death. This study proposes a multi-modal deep neural network for multi-class malignant liver diagnosis. In parallel with the portal venous computed tomography (CT) scans, pathology data is utilized to prognosticate primary liver cancer variants and metastasis. The processed CT scans are fed to the deep dilated convolution neural network to explore salient features. The residual connections are further added to address vanishing gradient problems. Correspondingly, five pathological features are learned using a wide and deep network that gives a benefit of memorization with generalization. The down-scaled hierarchical features from CT scan and pathology data are concatenated to pass through fully connected layers for classification between liver cancer variants. In addition, the transfer learning of pre-trained deep dilated convolution layers assists in handling insufficient and imbalanced dataset issues. The fine-tuned network can predict three-class liver cancer variants with an average accuracy of 96.06% and an Area Under Curve (AUC) of 0.832. To the best of our knowledge, this is the first study to classify liver cancer variants by integrating pathology and image data, hence following the medical perspective of malignant liver diagnosis. The comparative analysis on the benchmark dataset shows that the proposed multi-modal neural network outperformed most of the liver diagnostic studies and is comparable to others.

Imaging-Based Staging of Hepatic Fibrosis in Patients with Hepatitis B: A Dynamic Radiomics Model Based on Gd-EOB-DTPA-Enhanced MRI

Accurate grading of liver fibrosis can effectively assess the severity of liver disease and help doctors make an appropriate diagnosis. This study aimed to perform the automatic staging of hepatic fibrosis on patients with hepatitis B, who underwent gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging with dynamic radiomics analysis. The proposed dynamic radiomics model combined imaging features from multi-phase dynamic contrast-enhanced (DCE) images and time-domain information. Imaging features were extracted from the deep learning-based segmented liver volume, and time-domain features were further explored to analyze the variation in features during contrast enhancement. Model construction and evaluation were based on a 132-case data set. The proposed model achieved remarkable performance in significant fibrosis (fibrosis stage S1 vs. S2-S4; accuracy (ACC) = 0.875, area under the curve (AUC) = 0.867), advanced fibrosis (S1-S2 vs. S3-S4; ACC = 0.825, AUC = 0.874), and cirrhosis (S1-S3 vs. S4; ACC = 0.850, AUC = 0.900) classifications in the test set. It was more dominant compared with the conventional single-phase or multi-phase DCE-based radiomics models, normalized liver enhancement, and some serological indicators. Time-domain features were found to play an important role in the classification models. The dynamic radiomics model can be applied for highly accurate automatic hepatic fibrosis staging.

Impact of chronic liver disease upon admission on COVID-19 in-hospital mortality: Findings from COVOCA study

BACKGROUND

Italy has been the first Western country to be heavily affected by the spread of SARS-COV-2 infection and among the pioneers of the clinical management of pandemic. To improve the outcome, identification of patients at the highest risk seems mandatory.

OBJECTIVES

Aim of this study is to identify comorbidities and clinical conditions upon admission associated with in-hospital mortality in several COVID Centers in Campania Region (Italy).

METHODS

COVOCA is a multicentre retrospective observational cohort study, which involved 18 COVID Centers throughout Campania Region, Italy. Data were collected from patients who completed their hospitalization between March-June 2020. The endpoint was in-hospital mortality, assessed either from data at discharge or death certificate, whilst all exposure variables were collected at hospital admission.

RESULTS

Among 618 COVID-19 hospitalized patients included in the study, 143 in-hospital mortality events were recorded, with a cumulative incidence of about 23%. At multivariable logistic analysis, male sex (OR 2.63, 95%CI 1.42-4.90; p = 0.001), Chronic Liver Disease (OR 5.88, 95%CI 2.39-14.46; p<0.001) and malignancies (OR 2.62, 95%CI 1.21-5.68; p = 0.015) disclosed an independent association with a poor prognosis, Glasgow Coma Scale (GCS) and Respiratory Severity Scale allowed to identify at higher mortality risk. Sensitivity analysis further enhanced these findings.

CONCLUSION

Mortality of patients hospitalized for COVID-19 appears strongly affected by both clinical conditions on admission and comorbidities. Originally, we observed a very poor outcome in subjects with a chronic liver disease, alongside with an increase of hepatic damage.

Preliminary Study of Chronic Liver Classification on Ultrasound Images Using an Ensemble Model

Chronic liver diseases are fifth leading cause of fatality in developing countries. Their early diagnosis is extremely important for timely treatment and salvage life. To examine abnormalities of liver, ultrasound imaging is the most frequently used modality. However, the visual differentiation between chronic liver and cirrhosis, and presence of heptocellular carcinomas (HCC) evolved over cirrhotic liver is difficult, as they appear almost similar in ultrasound images. In this paper, to deal with this difficult visualization problem, a method has been developed for classifying four liver stages, that is, normal, chronic, cirrhosis, and HCC evolved over cirrhosis. The method is formulated with selected set of "handcrafted" texture features obtained after hierarchal feature fusion. These multiresolution and higher order features, which are able to characterize echotexture and roughness of liver surface, are extracted by using ranklet, gray-level difference matrix and gray-level co-occurrence matrix methods. Thereafter, these features are applied on proposed ensemble classifier that is designed with voting algorithm in conjunction with three classifiers, namely, k-nearest neighbor (k-NN), support vector machine (SVM), and rotation forest. The experiments are conducted to evaluate the (a) effectiveness of "handcrafted" texture features, (b) performance of proposed ensemble model, (c) effectiveness of proposed ensemble strategy, (d) performance of different classifiers, and (e) performance of proposed ensemble model based on Convolutional Neural Networks (CNN) features to differentiate four liver stages. These experiments are carried out on database of 754 segmented regions of interest formed by clinically acquired ultrasound images. The results show that classification accuracy of 96.6% is obtained by use of proposed classifier model.

Staging of Fatty Liver Diseases Based on Hierarchical Classification and Feature Fusion for Back-Scan-Converted Ultrasound Images

Fatty liver disease is progressive and may not cause any symptoms at early stages. This disease is potentially fatal and can cause liver cancer in severe stages. Therefore, diagnosing and staging fatty liver disease in early stages is necessary. In this paper, a novel method is presented to classify normal and fatty liver, as well as discriminate three stages of fatty liver in ultrasound images. This study is performed with 129 subjects including 28 normal, 47 steatosis, 42 fibrosis, and 12 cirrhosis images. The proposed approach uses back-scan conversion of ultrasound sector images and is based on a hierarchical classification. The proposed algorithm is performed in two parts. The first part selects the optimum regions of interest from the focal zone of the back-scan-converted ultrasound images. In the second part, discrimination between normal and fatty liver is performed and then steatosis, fibrosis, and cirrhosis are classified in a hierarchical basis. The wavelet packet transform and gray-level co-occurrence matrix are used to obtain a number of statistical features. A support vector machine classifier is used to discriminate between normal and fatty liver, and stage fatty cases. The results of the proposed scheme clearly illustrate the efficiency of this system with overall accuracy of 94.91% and also specificity of more than 90%.

Automated detection of coarctation of aorta in neonates from two-dimensional echocardiograms

Coarctation of aorta (CoA) is a critical congenital heart defect (CCHD) that requires accurate and immediate diagnosis and treatment. Current newborn screening methods to detect CoA lack both in sensitivity and specificity, and when suspected in a newborn, it must be confirmed using specialized imaging and expert diagnosis, both of which are usually unavailable at tertiary birthing centers. We explore the feasibility of applying machine learning methods to reliably determine the presence of this difficult-to-diagnose cardiac abnormality from ultrasound image data. We propose a framework that uses deep learning-based machine learning methods for fully automated detection of CoA from two-dimensional ultrasound clinical data acquired in the parasternal long axis view, the apical four chamber view, and the suprasternal notch view. On a validation set consisting of 26 CoA and 64 normal patients our algorithm achieved a total error rate of 12.9% (11.5% false-negative error and 13.6% false-positive error) when combining decisions of classifiers over three standard echocardiographic view planes. This compares favorably with published results that combine clinical assessments with pulse oximetry to detect CoA (71% sensitivity).

Computer-aided Characterization and Diagnosis of Diffuse Liver Diseases Based on Ultrasound Imaging: A Review

Diffuse liver diseases, such as hepatitis, fatty liver, and cirrhosis, are becoming a leading cause of fatality and disability all over the world. Early detection and diagnosis of these diseases is extremely important to save lives and improve effectiveness of treatment. Ultrasound imaging, a noninvasive diagnostic technique, is the most commonly used modality for examining liver abnormalities. However, the accuracy of ultrasound-based diagnosis depends highly on expertise of radiologists. Computer-aided diagnosis systems based on ultrasound imaging assist in fast diagnosis, provide a reliable "second opinion" for experts, and act as an effective tool to measure response of treatment on patients undergoing clinical trials. In this review, we first describe appearance of liver abnormalities in ultrasound images and state the practical issues encountered in characterization of diffuse liver diseases that can be addressed by software algorithms. We then discuss computer-aided diagnosis in general with features and classifiers relevant to diffuse liver diseases. In later sections of this paper, we review the published studies and describe the key findings of those studies. A concise tabular summary comparing image database, features extraction, feature selection, and classification algorithms presented in the published studies is also exhibited. Finally, we conclude with a summary of key findings and directions for further improvements in the areas of accuracy and objectiveness of computer-aided diagnosis.

Primary biliary cirrhosis degree assessment by acoustic radiation force impulse imaging and hepatic fibrosis indicators

AIM: To evaluate the assessment of primary biliary cirrhosis degree by acoustic radiation force impulse imaging (ARFI) and hepatic fibrosis indicators.

METHODS: One hundred and twenty patients who developed liver cirrhosis secondary to primary biliary cirrhosis were selected as the observation group, with the degree of patient liver cirrhosis graded by Child-Pugh (CP) score. Sixty healthy individuals were selected as the control group. The four indicators of hepatic fibrosis were detected in all research objects, including hyaluronic acid (HA), laminin (LN), type III collagen (PC III), and type IV collagen (IV-C). The liver parenchyma hardness value (LS) was then measured by ARFI technique. LS and the four indicators of liver fibrosis (HA, LN, PC III, and IV-C) were observed in different grade CP scores. The diagnostic value of LS and the four indicators of liver fibrosis in determining liver cirrhosis degree with PBC, whether used alone or in combination, were analyzed by receiver operating characteristic (ROC) curve.

RESULTS: LS and the four indicators of liver fibrosis within the three classes (A, B, and C) of CP scores in the observation group were higher than in the control group, with C class > B class > A class; the differences were statistically significant (P < 0.01). Although AUC values of LS within the three classes of CP scores were higher than in the four indicators of liver fibrosis, sensitivity and specificity were unstable. The ROC curves of LS combined with the four indicators of liver fibrosis revealed that: AUC and sensitivity in all indicators combined in the A class of CP score were higher than in LS alone, albeit with slightly decreased specificity; AUC and specificity in all indicators combined in the B class of CP score were higher than in LS alone, with unchanged sensitivity; AUC values (0.967), sensitivity (97.4%), and specificity (90%) of all indicators combined in the C class of CP score were higher than in LS alone (0.936, 92.1%, 83.3%).

CONCLUSION: The diagnostic value of PBC cirrhosis degree in liver cirrhosis degree assessment by ARFI combined with the four indicators of serum liver fibrosis is of satisfactory effectiveness and has important clinical application value.

Optimal linear combination of ARFI, transient elastography and APRI for the assessment of fibrosis in chronic hepatitis B

BACKGROUND & AIMS

Accurate assessment of liver fibrosis in patients with chronic hepatitis B (CHB) is necessary not only to predict the long-term clinical course but also to determine an appropriate antiviral therapy scheme. Several noninvasive approaches - serum markers and elastography - have been proposed as alternatives for the histopathological analysis of liver biopsies. The aim of this study was to evaluate two ultrasound elastography methods (ARFI and TE) and one biochemical test (APRI), as well as their optimal linear combination, in the assessment of liver fibrosis in CHB.

METHODS

Ninety five patients with CHB and 16 volunteers underwent ARFI, TE and APRI; and liver fibrosis was staged in the patients by a liver biopsy. An optimal linear combination of the three methods was developed, and its diagnostic performance was evaluated by a 10-fold cross-validation.

RESULTS

The accuracy of the linear combination was 83.86% and 91.88% for significant fibrosis (≥F2) and cirrhosis (F4), respectively, higher than those obtained for ARFI (83.50%, 88.76%), TE (75.27%, 87.61%) and APRI (73.29% and 81.67%). The combination also increased the sensitivity and the negative predictive values for the diagnosis of significant fibrosis and cirrhosis.

CONCLUSIONS

The optimal linear combination algorithm is effective for noninvasive staging of liver fibrosis in CHB. However, linear combination has its own limitations; nonlinear methods may eventually reveal even clearer diagnostic results.

Prediction of periventricular leukomalacia occurrence in neonates after heart surgery

This paper is concerned with predicting the occurrence of periventricular leukomalacia (PVL) using vital and blood gas data which are collected over a period of 12 h after the neonatal cardiac surgery. A data mining approach has been employed to generate a set of rules for classification of subjects as healthy or PVL affected. In view of the fact that blood gas and vital data have different sampling rates, in this study we have divided the data into two categories: 1) high resolution (vital), and 2) low resolution (blood gas), and designed a separate classifier based on each data category. The developed algorithm is composed of several stages; first, a feature pool has been extracted from each data category and the extracted features have been ranked based on the data reliability and their mutual information content with the output. An optimal feature subset with the highest discriminative capability has been formed using simultaneous maximization of the class separability measure and mutual information of a set. Two separate decision trees (DTs) have been developed for the classification purpose and more importantly to discover hidden relationships that exist among the data to help us better understand PVL pathophysiology. The DT result shows that high amplitude 20 min variations and low sample entropy in the vital data and the defined out of range index as well as maximum rate of change in blood gas data are important factors for PVL prediction. Low sample entropy represents lack of variability in hemodynamic measurement, and constant blood pressure with small fluctuations is an important indicator of PVL occurrence. Finally, using the different time frames of data collection, we show that the first 6 h of data contain sufficient information for PVL occurrence prediction.