Performance of Ultrasound Techniques and the Potential of Artificial Intelligence in the Evaluation of Hepatocellular Carcinoma and Non-Alcoholic Fatty Liver Disease

Characterizing Sentinel Lymph Node Status in Breast Cancer Patients Using a Deep-Learning Model Compared With Radiologists' Analysis of Grayscale Ultrasound and Lymphosonography

ABSTRACT

The objective of the study was to use a deep learning model to differentiate between benign and malignant sentinel lymph nodes (SLNs) in patients with breast cancer compared to radiologists' assessments.Seventy-nine women with breast cancer were enrolled and underwent lymphosonography and contrast-enhanced ultrasound (CEUS) examination after subcutaneous injection of ultrasound contrast agent around their tumor to identify SLNs. Google AutoML was used to develop image classification model. Grayscale and CEUS images acquired during the ultrasound examination were uploaded with a data distribution of 80% for training/20% for testing. The performance metric used was area under precision/recall curve (AuPRC). In addition, 3 radiologists assessed SLNs as normal or abnormal based on a clinical established classification. Two-hundred seventeen SLNs were divided in 2 for model development; model 1 included all SLNs and model 2 had an equal number of benign and malignant SLNs. Validation results model 1 AuPRC 0.84 (grayscale)/0.91 (CEUS) and model 2 AuPRC 0.91 (grayscale)/0.87 (CEUS). The comparison between artificial intelligence (AI) and readers' showed statistical significant differences between all models and ultrasound modes; model 1 grayscale AI versus readers, P = 0.047, and model 1 CEUS AI versus readers, P < 0.001. Model 2 r grayscale AI versus readers, P = 0.032, and model 2 CEUS AI versus readers, P = 0.041.The interreader agreement overall result showed κ values of 0.20 for grayscale and 0.17 for CEUS.In conclusion, AutoML showed improved diagnostic performance in balance volume datasets. Radiologist performance was not influenced by the dataset's distribution.

Epidemiology, pathophysiology and clinical aspects of Hepatocellular Carcinoma in MAFLD patients

Hepatocellular carcinoma (HCC) is undergoing a transformative shift, with metabolic-associated fatty liver disease (MAFLD) emerging as a dominant etiology. Diagnostic criteria for MAFLD involve hepatic steatosis and metabolic dysregulation. Globally, MAFLD prevalence stands at 38.77%, significantly linked to the escalating rates of obesity. Epidemiological data indicate a dynamic shift in the major etiologies of hepatocellular carcinoma (HCC), transitioning from viral to metabolic liver diseases. Besides the degree of liver fibrosis, several modifiable lifestyle risk factors, such as type 2 diabetes, obesity, alcohol use, smoking, and HBV, HCV infection contribute to the pathogenesis of HCC. Moreover  gut microbiota and genetic variants may contribute to HCC development.The pathophysiological link between MAFLD and HCC involves metabolic dysregulation, impairing glucose and lipid metabolism, inflammation and oxidative stress. Silent presentation poses challenges in early MAFLD-HCC diagnosis. Imaging, biopsy, and AI-assisted techniques aid diagnosis, while HCC surveillance in non-cirrhotic MAFLD patients remains debated.ITA.LI.CA. group proposes a survival-based algorithm for treatment based on Barcelona clinic liver cancer (BCLC) algorithm. Liver resection, transplantation, ablation, and locoregional therapies are applied based on the disease stage. Systemic treatments is promising, with initial immunotherapy results indicating a less favorable response in MAFLD-related HCC.Adopting lifestyle interventions and chemopreventive measures with medications, including aspirin, metformin, and statins, constitute promising approaches for the primary prevention of HCC.Prognosis is influenced by multiple factors, with MAFLD-HCC associated with prolonged survival. Emerging diagnostic biomarkers and epigenomic markers, show promising results for early HCC detection in the MAFLD population.

Artificial intelligence-based diagnosis of standard endoscopic ultrasonography scanning sites in the biliopancreatic system: a multicenter retrospective study

BACKGROUND

There are challenges for beginners to identify standard biliopancreatic system anatomical sites on endoscopic ultrasonography (EUS) images. Therefore, the authors aimed to develop a convolutional neural network (CNN)-based model to identify standard biliopancreatic system anatomical sites on EUS images.

METHODS

The standard anatomical structures of the gastric and duodenal regions observed by EUS was divided into 14 sites. The authors used 6230 EUS images with standard anatomical sites selected from 1812 patients to train the CNN model, and then tested its diagnostic performance both in internal and external validations. Internal validation set tests were performed on 1569 EUS images of 47 patients from two centers. Externally validated datasets were retrospectively collected from 16 centers, and finally 131 patients with 85 322 EUS images were included. In the external validation, all EUS images were read by CNN model, beginners, and experts, respectively. The final decision made by the experts was considered as the gold standard, and the diagnostic performance between CNN model and beginners were compared.

RESULTS

In the internal test cohort, the accuracy of CNN model was 92.1-100.0% for 14 standard anatomical sites. In the external test cohort, the sensitivity and specificity of CNN model were 89.45-99.92% and 93.35-99.79%, respectively. Compared with beginners, CNN model had higher sensitivity and specificity for 11 sites, and was in good agreement with the experts (Kappa values 0.84-0.98).

CONCLUSIONS

The authors developed a CNN-based model to automatically identify standard anatomical sites on EUS images with excellent diagnostic performance, which may serve as a potentially powerful auxiliary tool in future clinical practice.

Application of artificial intelligence techniques for non-alcoholic fatty liver disease diagnosis: A systematic review (2005-2023)

BACKGROUND AND OBJECTIVES

Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is important to distinguish the pathological stages of NAFLD: steatosis, steatohepatitis, and liver fibrosis, which are definitively diagnosed on invasive biopsy. Non-invasive ultrasound (US) imaging, including US elastography technique, and clinical parameters can be used to diagnose and grade NAFLD and its complications. Artificial intelligence (AI) is increasingly being harnessed for developing NAFLD diagnostic models based on clinical, biomarker, or imaging data. In this work, we systemically reviewed the literature for AI-enabled NAFLD diagnostic models based on US (including elastography) and clinical (including serological) data.

METHODS

We performed a comprehensive search on Google Scholar, Scopus, and PubMed search engines for articles published between January 2005 and June 2023 related to AI models for NAFLD diagnosis based on US and/or clinical parameters using the following search terms: "non-alcoholic fatty liver disease", "non-alcoholic steatohepatitis", "deep learning", "machine learning", "artificial intelligence", "ultrasound imaging", "sonography", "clinical information".

RESULTS

We reviewed 64 published models that used either US (including elastography) or clinical data input to detect the presence of NAFLD, non-alcoholic steatohepatitis, and/or fibrosis, and in some cases, the severity of steatosis, inflammation, and/or fibrosis as well. The performances of the published models were summarized, and stratified by data input and algorithms used, which could be broadly divided into machine and deep learning approaches.

CONCLUSION

AI models based on US imaging and clinical data can reliably detect NAFLD and its complications, thereby reducing diagnostic costs and the need for invasive liver biopsy. The models offer advantages of efficiency, accuracy, and accessibility, and serve as virtual assistants for specialists to accelerate disease diagnosis and reduce treatment costs for patients and healthcare systems.

Comparison of Gray-scale Inversion to Improve Detection of Pulmonary Nodules on Chest X-rays Between Radiologists and a Deep Convolutional Neural Network

Detection of pulmonary nodules on chest x-rays is an important task for radiologists. Previous studies have shown improved detection rates using gray-scale inversion. The purpose of our study was to compare the efficacy of gray-scale inversion in improving the detection of pulmonary nodules on chest x-rays for radiologists and machine learning models (ML). We created a mixed dataset consisting of 60, 2-view (posteroanterior view - PA and lateral view) chest x-rays with computed tomography confirmed nodule(s) and 62 normal chest x-rays. Twenty percent of the cases were separated for a testing dataset (24 total images). Data augmentation through mirroring and transfer learning was used for the remaining cases (784 total images) for supervised training of 4 ML models (grayscale PA, grayscale lateral, gray-scale inversion PA, and gray-scale inversion lateral) on Google's cloud-based AutoML platform. Three cardiothoracic radiologists analyzed the complete 2-view dataset (n=120) and, for comparison to the ML, the single-view testing subsets (12 images each). Gray-scale inversion (area under the curve (AUC) 0.80, 95% confidence interval (CI) 0.75-0.85) did not improve diagnostic performance for radiologists compared to grayscale (AUC 0.84, 95% CI 0.79-0.88). Gray-scale inversion also did not improve diagnostic performance for the ML. The ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5% respectively). In the limited testing dataset, the ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5%, respectively). Further investigation of other post-processing algorithms to improve diagnostic performance of ML is warranted.

Current status of ultrasonography in national cancer surveillance program for hepatocellular carcinoma in South Korea: a large-scale multicenter study

Background/Aim

Abdominal ultrasonography (USG) is recommended as a surveillance test for high-risk groups for hepatocellular carcinoma (HCC). This study aimed to analyze the current status of the national cancer surveillance program for HCC in South Korea and investigate the effects of patient-, physician-, and machine-related factors on HCC detection sensitivity.

Methods

This multicenter retrospective cohort study collected surveillance USG data from the high-risk group for HCC (liver cirrhosis or chronic hepatitis B or C >40 years of age) at eight South Korean tertiary hospitals in 2017.

Results

In 2017, 45 experienced hepatologists or radiologists performed 8,512 USG examinations. The physicians had a mean 15.0±8.3 years of experience; more hepatologists (61.4%) than radiologists (38.6%) participated. Each USG scan took a mean 12.2±3.4 minutes. The HCC detection rate by surveillance USG was 0.3% (n=23). Over 27 months of follow-up, an additional 135 patients (0.7%) developed new HCC. The patients were classified into three groups based on timing of HCC diagnosis since the 1st surveillance USG, and no significant intergroup difference in HCC characteristics was noted. HCC detection was significantly associated with patient-related factors, such as old age and advanced fibrosis, but not with physician- or machine-related factors.

Conclusions

This is the first study of the current status of USG as a surveillance method for HCC at tertiary hospitals in South Korea. It is necessary to develop quality indicators and quality assessment procedures for USG to improve the detection rate of HCC.

Ultrasound-Based Machine Learning Approach for Detection of Nonalcoholic Fatty Liver Disease

OBJECTIVES

Current diagnosis of nonalcoholic fatty liver disease (NAFLD) relies on biopsy or MR-based fat quantification. This prospective study explored the use of ultrasound with artificial intelligence for the detection of NAFLD.

METHODS

One hundred and twenty subjects with clinical suspicion of NAFLD and 10 healthy volunteers consented to participate in this institutional review board-approved study. Subjects were categorized as NAFLD and non-NAFLD according to MR proton density fat fraction (PDFF) findings. Ultrasound images from 10 different locations in the right and left hepatic lobes were collected following a standard protocol. MRI-based liver fat quantification was used as the reference standard with >6.4% indicative of NAFLD. A supervised machine learning model was developed for assessment of NAFLD. To validate model performance, a balanced testing dataset of 24 subjects was used. Sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy with 95% confidence interval were calculated.

RESULTS

A total of 1119 images from 106 participants was used for model development. The internal evaluation achieved an average precision of 0.941, recall of 88.2%, and precision of 89.0%. In the testing set AutoML achieved a sensitivity of 72.2% (63.1%-80.1%), specificity of 94.6% (88.7%-98.0%), positive predictive value (PPV) of 93.1% (86.0%-96.7%), negative predictive value of 77.3% (71.6%-82.1%), and accuracy of 83.4% (77.9%-88.0%). The average agreement for an individual subject was 92%.

CONCLUSIONS

An ultrasound-based machine learning model for identification of NAFLD showed high specificity and PPV in this prospective trial. This approach may in the future be used as an inexpensive and noninvasive screening tool for identifying NAFLD in high-risk patients.

Clinical-radiomic analysis for non-invasive prediction of liver steatosis on non-contrast CT: A pilot study

Purpose: Our aim is to build and validate a clinical-radiomic model for non-invasive liver steatosis prediction based on non-contrast computed tomography (CT). Methods: We retrospectively reviewed 342 patients with suspected NAFLD diagnoses between January 2019 and July 2020 who underwent non-contrast CT and liver biopsy. Radiomics features from hepatic and splenic regions-of-interests (ROIs) were extracted based on abdominal non-contrast CT imaging. The radiomics signature was constructed based on reproducible features by adopting the least absolute shrinkage and selection operator (LASSO) regression. Then, multivariate logistic regression analysis was applied to develop a combined clinical-radiomic nomogram integrating radiomics signature with several independent clinical predictors in a training cohort of 124 patients between January 2019 and December 2019. The performance of models was determined by the area under the receiver operating characteristic curves and calibration curves. We conducted an internal validation during 103 consecutive patients between January 2020 and July 2020. Results: The radiomics signature was composed of four steatosis-related features and positively correlated with pathologic liver steatosis grade (p < 0.01). In both subgroups (Group One, none vs. steatosis; Group Two, none/mild vs. moderate/severe steatosis), the clinical-radiomic model performed best within the validation cohort with an AUC of 0.734 and 0.930, respectively. The calibration curve confirmed the concordance of excellent models. Conclusion: We developed a robust clinical-radiomic model for accurate liver steatosis stage prediction in a non-invasive way, which may improve the clinical decision-making ability.

Artificial Intelligence for Detecting and Quantifying Fatty Liver in Ultrasound Images: A Systematic Review

BACKGROUND

Non-alcoholic Fatty Liver Disease (NAFLD) is growing more prevalent worldwide. Although non-invasive diagnostic approaches such as conventional ultrasonography and clinical scoring systems have been proposed as alternatives to liver biopsy, their efficacy has been called into doubt. Artificial Intelligence (AI) is now combined with traditional diagnostic processes to improve the performance of non-invasive approaches.

OBJECTIVE

This study explores how well various AI methods function and perform on ultrasound (US) images to diagnose and quantify non-alcoholic fatty liver disease.

METHODOLOGY

A systematic review was conducted to achieve this objective. Five science bibliographic databases were searched, including PubMed, Association for Computing Machinery ACM Digital Library, Institute of Electrical and Electronics Engineers IEEE Xplore, Scopus, and Google Scholar. Only peer-reviewed English articles, conferences, theses, and book chapters were included. Data from studies were synthesized using narrative methodologies per Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) criteria.

RESULTS

Forty-nine studies were included in the systematic review. According to the qualitative analysis, AI significantly enhanced the diagnosis of NAFLD, Non-Alcoholic Steatohepatitis (NASH), and liver fibrosis. In addition, modalities, image acquisition, feature extraction and selection, data management, and classifiers were assessed and compared in terms of performance measures (i.e., accuracy, sensitivity, and specificity).

CONCLUSION

AI-supported systems show potential performance increases in detecting and quantifying steatosis, NASH, and liver fibrosis in NAFLD patients. Before real-world implementation, prospective studies with direct comparisons of AI-assisted modalities and conventional techniques are necessary.

Artificial intelligence for identification of focal lesions in intraoperative liver ultrasonography

PURPOSE

Intraoperative ultrasonography (IOUS) of the liver is a crucial adjunct in every liver resection and may significantly impact intraoperative surgical decisions. However, IOUS is highly operator dependent and has a steep learning curve. We describe the design and assessment of an artificial intelligence (AI) system to identify focal liver lesions in IOUS.

METHODS

IOUS images were collected during liver resections performed between November 2020 and November 2021. The images were labeled by radiologists and surgeons as normal liver tissue versus images that contain liver lesions. A convolutional neural network (CNN) was trained and tested to classify images based on the labeling. Algorithm performance was tested in terms of area under the curves (AUCs), accuracy, sensitivity, specificity, F1 score, positive predictive value, and negative predictive value.

RESULTS

Overall, the dataset included 5043 IOUS images from 16 patients. Of these, 2576 were labeled as normal liver tissue and 2467 as containing focal liver lesions. Training and testing image sets were taken from different patients. Network performance area under the curve (AUC) was 80.2 ± 2.9%, and the overall classification accuracy was 74.6% ± 3.1%. For maximal sensitivity of 99%, the classification specificity is 36.4 ± 9.4%.

CONCLUSIONS

This study provides for the first time a proof of concept for the use of AI in IOUS and show that high accuracy can be achieved. Further studies using high volume data are warranted to increase accuracy and differentiate between lesion types.

Contrast-Enhanced Ultrasound Features of Histopathologically Proven Hepatocellular Carcinoma in the Non-cirrhotic Liver: A Multicenter Study

Current literature on the role of contrast-enhanced ultrasound (CEUS) in the diagnosis of hepatocellular carcinoma (HCC) in non-cirrhotic patients is limited. The aim of this retrospective multicenter study was to analyze CEUS features of histologically proven HCC in patients with non-cirrhotic liver. In this multicenter study, 96 patients from eight medical institutions with histologically proven HCC lesions in non-cirrhotic liver were retrospectively reviewed regarding SonoVue-enhanced CEUS features. Two ultrasound experts assessed the CEUS enhancement pattern and came to a consensus using the World Federation of Societies for Ultrasound in Medicine and Biology guideline criteria. The mean size of HCC lesions included was 60.3 ± 37.8 mm (mean ± standard deviation). Most of the lesions were heterogeneous but predominantly hypo-echoic on B-mode ultrasound (64.5%, 62/96), with ill-defined margins and irregular shapes. During the arterial phase of CEUS, most of the HCC lesions in non-cirrhotic liver exhibited heterogeneous hyperenhancement (78.1%, 75/96) compared with the surrounding liver parenchyma. Almost 30% of HCC lesions (28.1%, 27/96) exhibited early wash-out (<60 s). All lesions exhibited wash-out and hypo-enhancement in the late phase. CEUS features of HCC lesions in non-cirrhotic patients typically include hyperenhancement in the arterial phase and relatively rapid wash-out in the portal venous phase, which is different from HCC in cirrhotic livers and more similar to liver metastasis.

Multi-Omics and Artificial Intelligence-Guided Data Integration in Chronic Liver Disease: Prospects and Challenges for Precision Medicine

Chronic liver disease (CLD) is a significant planetary health burden. CLD includes a broad range of liver pathologies from different causes, for example, hepatitis B virus infection, fatty liver disease, hepatocellular carcinoma, and nonalcoholic fatty liver disease or the metabolic associated fatty liver disease. Biomarker and diagnostic discovery, and new molecular targets for precision treatments are timely and sorely needed in CLD. In this context, multi-omics data integration is increasingly being facilitated by artificial intelligence (AI) and attendant digital transformation of systems science. While the digital transformation of multi-omics integrative analyses is still in its infancy, there are noteworthy prospects, hope, and challenges for diagnostic and therapeutic innovation in CLD. This expert review aims at the emerging knowledge frontiers as well as gaps in multi-omics data integration at bulk tissue levels, and those including single cell-level data, gut microbiome data, and finally, those incorporating tissue-specific information. We refer to AI and related digital transformation of the CLD research and development field whenever possible. This review of the emerging frontiers at the intersection of systems science and digital transformation informs future roadmaps to bridge digital technology discovery and clinical omics applications to benefit planetary health and patients with CLD.

The Emerging Factors and Treatment Options for NAFLD-Related Hepatocellular Carcinoma

Simple Summary

Nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, and it is an increasing factor in the cause of hepatocellular carcinoma (HCC). The incidence of NAFLD has increased in recent decades, accompanied by an increase in the prevalence of other metabolic diseases, such as obesity and type 2 diabetes. However, current treatment options are limited. Both genetic factors and non-genetic factors impact the initiation and progression of NAFLD-related HCC. The early diagnosis of liver cancer predicts curative treatment and longer survival. Some key molecules play pivotal roles in the initiation and progression of NAFLD-related HCC, which can be targeted to impede HCC development. In this review, we summarize some key factors and important molecules in NAFLD-related HCC development, the latest progress in HCC diagnosis and treatment options, and some current clinical trials for NAFLD treatment.

Abstract

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer, followed by cholangiocarcinoma (CCA). HCC is the third most common cause of cancer death worldwide, and its incidence is rising, associated with an increased prevalence of obesity and nonalcoholic fatty liver disease (NAFLD). However, current treatment options are limited. Genetic factors and epigenetic factors, influenced by age and environment, significantly impact the initiation and progression of NAFLD-related HCC. In addition, both transcriptional factors and post-transcriptional modification are critically important for the development of HCC in the fatty liver under inflammatory and fibrotic conditions. The early diagnosis of liver cancer predicts curative treatment and longer survival. However, clinical HCC cases are commonly found in a very late stage due to the asymptomatic nature of the early stage of NAFLD-related HCC. The development of diagnostic methods and novel biomarkers, as well as the combined evaluation algorithm and artificial intelligence, support the early and precise diagnosis of NAFLD-related HCC, and timely monitoring during its progression. Treatment options for HCC and NAFLD-related HCC include immunotherapy, CAR T cell therapy, peptide treatment, bariatric surgery, anti-fibrotic treatment, and so on. Overall, the incidence of NAFLD-related HCC is increasing, and a better understanding of the underlying mechanism implicated in the progression of NAFLD-related HCC is essential for improving treatment and prognosis.

Noninvasive Assessment of Hepatitis C Virus Infected Patients Using Vibration-Controlled Transient Elastography

Chronic infection with hepatitis C virus (HCV) is one of the leading causes of cirrhosis and hepatocellular carcinoma (HCC). Surveillance of these patients is an essential strategy in the prevention chain, including in the pre/post-antiviral treatment states. Ultrasound elastography techniques are emerging as key methods in the assessment of liver diseases, with a number of advantages such as their rapid, noninvasive, and cost-effective characters. The present paper critically reviews the performance of vibration-controlled transient elastography (VCTE) in the assessment of HCV patients. VCTE measures liver stiffness (LS) and the ultrasonic attenuation through the embedded controlled attenuation parameter (CAP), providing the clinician with a tool for assessing fibrosis, cirrhosis, and steatosis in a noninvasive manner. Moreover, standardized LS values enable proper staging of the underlying fibrosis, leading to an accurate identification of a subset of HCV patients that present a high risk for complications. In addition, VCTE is a valuable technique in evaluating liver fibrosis prior to HCV therapy. However, its applicability in monitoring fibrosis regression after HCV eradication is currently limited and further studies should focus on extending the boundaries of VCTE in this context. From a different perspective, VCTE may be effective in identifying clinically significant portal hypertension (CSPH). An emerging prospect of clinical significance that warrants further study is the identification of esophageal varices. Our opinion is that the advantages of VCTE currently outweigh those of other surveillance methods.

Ultrasound Methods in the Evaluation of Atherosclerosis: From Pathophysiology to Clinic

Atherosclerosis is a key pathological process that causes a plethora of pathologies, including coronary artery disease, peripheral artery disease, and ischemic stroke. The silent progression of the atherosclerotic disease prompts for new surveillance tools that can visualize, characterize, and provide a risk evaluation of the atherosclerotic plaque. Conventional ultrasound methods—bright (B)-mode US plus Doppler mode—provide a rapid, cost-efficient way to visualize an established plaque and give a rapid risk stratification of the patient through the Gray–Weale standardization—echolucent plaques with ≥50% stenosis have a significantly greater risk of ipsilateral stroke. Although rather disputed, the measurement of carotid intima-media thickness (C-IMT) may prove useful in identifying subclinical atherosclerosis. In addition, contrast-enhanced ultrasonography (CEUS) allows for a better image resolution and the visualization and quantification of plaque neovascularization, which has been correlated with future cardiovascular events. Newly emerging elastography techniques such as strain elastography and shear-wave elastography add a new dimension to this evaluation—the biomechanics of the arterial wall, which is altered in atherosclerosis. The invasive counterpart, intravascular ultrasound (IVUS), enables an individualized assessment of the anti-atherosclerotic therapies, as well as a direct risk assessment of these lesions through virtual histology IVUS.