Diagnostic Endoscopic Ultrasound: Technique, Current Status and Future Directions

Advancements in biliopancreatic endoscopy: a comprehensive review of artificial intelligence in EUS and ERCP

The development and implementation of artificial intelligence (AI), particularly deep learning (DL) models, has generated significant interest across various fields of gastroenterology. While research in luminal endoscopy has seen rapid translation to clinical practice with approved AI devices, its potential extends far beyond, offering promising benefits for biliopancreatic endoscopy like optical characterization of strictures during cholangioscopy or detection and classification of pancreatic lesions during diagnostic endoscopic ultrasound (EUS). This narrative review provides an up-to-date of the latest literature and available studies in this field. Serving as a comprehensive guide to the current landscape of AI in biliopancreatic endoscopy, emphasizing technological advancements, main applications, ethical considerations, and future directions for research and clinical implementation.

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.

Endoscopic procedures in hepatology: Current trends and new developments

Gastrointestinal endoscopy has long been a reliable backbone in the diagnosis and management of hepatobilary disorders and their complications. However, with evolving non-invasive testing, personalised medicine has reframed the utility and necessity of endoscopic screening. Conversely, the growing interest and use of endoscopic ultrasound (EUS) and advanced endoscopy within gastrointestinal units has also opened novel diagnostic and therapeutic avenues for patients with various hepatobiliary diseases. The integration of "advanced endoscopy" within the practice of hepatology is nowadays referred to as "endo-hepatology". In essence, endo-hepatology consists of two pillars: one focusing primarily on disorders of the liver parenchyma, vascular disorders, and portal hypertension, which is mainly captured via EUS, while the other targets the hepatobiliary tract via endoscopic retrograde cholangiopancreatography and advanced imaging. Applications under the umbrella of endo-hepatology include, amongst others, EUS-guided liver biopsy, EUS-guided portal pressure gradient measurement, coil and glue embolisation of gastric varices as well as cholangioscopy. As such endo-hepatology could become an attractive concept wherein advanced endoscopy might reinforce the medical management of patients with hepatobiliary disorders and their complications after initial basic work-up. In this review, we discuss current trends and future developments within endo-hepatology and the remaining hurdles to overcome.

Diagnostic value of conventional endoscopic ultrasound for lymph node metastasis in upper gastrointestinal neoplasia: A meta-analysis

BACKGROUND

Upper gastrointestinal neoplasia mainly includes esophageal cancer and gastric cancer, both of which have high morbidity and mortality. Lymph node metastasis (LNM), as the most common metastasis mode of both diseases, is an important factor affecting tumor stage, treatment strategy and clinical prognosis. As a new fusion technology, endoscopic ultrasound (EUS) is becoming increasingly used in the diagnosis and treatment of digestive system diseases, but its use in detecting LNM in clinical practice remains limited.

AIM

To evaluate the diagnostic value of conventional EUS for LNM in upper gastrointestinal neoplasia.

METHODS

Using the search mode of "MeSH + Entry Terms" and according to the predetermined inclusion and exclusion criteria, we conducted a comprehensive search and screening of the PubMed, EMBASE and Cochrane Library databases from January 1, 2000 to October 1, 2022. Study data were extracted according to the predetermined data extraction form. The quality of the included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies tool, and the results of the quality assessment were presented using Review Manager 5.3.5 software. Finally, Stata14.0 software was used for a series of statistical analyses.

RESULTS

A total of 22 studies were included in our study, including 2986 patients. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic score and diagnostic odds ratio of conventional EUS in the diagnosis of upper gastrointestinal neoplasia LNM were 0.62 [95% confidence interval (CI): 0.50-0.73], 0.80 (95%CI: 0.73-0.86), 3.15 (95%CI: 2.46-4.03), 0.47 (95%CI: 0.36-0.61), 1.90 (95%CI: 1.51-2.29) and 6.67 (95%CI: 4.52-9.84), respectively. The area under the summary receiver operating characteristic curve was 0.80 (95%CI: 0.76-0.83). Sensitivity analysis indicated that the results of the meta-analysis were stable. There was considerable heterogeneity among the included studies, and the threshold effect was an important source of heterogeneity. Univariable meta-regression and subgroup analysis showed that tumor type, sample size and EUS diagnostic criteria were significant sources of heterogeneity in specificity (P < 0.05). No significant publication bias was found.

CONCLUSION

Conventional EUS has certain clinical value and can assist in the detection of LNM in upper gastrointestinal neoplasia, but it cannot be used as a confirmatory or exclusionary test.

The Latest Advancements in Diagnostic Role of Endosonography of Pancreatic Lesions

Endosonography, a minimally invasive imaging technique, has revolutionized the diagnosis and management of pancreatic diseases. This comprehensive review highlights the latest advancements in endosonography of the pancreas, focusing on key technological developments, procedural techniques, clinical applications and additional techniques, which include real-time elastography endoscopic ultrasound, contrast-enhanced-EUS, EUS-guided fine-needle aspiration or EUS-guided fine-needle biopsy. EUS is well established for T-staging and N-staging of pancreaticobiliary malignancies, for pancreatic cyst discovery, for identifying subepithelial lesions (SEL), for differentiation of benign pancreaticobiliary disorders or for acquisition of tissue by EUS-guided fine-needle aspiration or EUS-guided fine-needle biopsy. This review briefly describes principles and application of EUS and its related techniques.

Ultrasound contrast agents from microbubbles to biogenic gas vesicles

Microbubbles have been the earliest and most widely used ultrasound contrast agents by virtue of their unique features: such as non-toxicity, intravenous injectability, ability to cross the pulmonary capillary bed, and significant enhancement of echo signals for the duration of the examination, resulting in essential preclinical and clinical applications. The use of microbubbles functionalized with targeting ligands to bind to specific targets in the bloodstream has further enabled ultrasound molecular imaging. Nevertheless, it is very challenging to utilize targeted microbubbles for molecular imaging of extravascular targets due to their size. A series of acoustic nanomaterials have been developed for breaking free from this constraint. Especially, biogenic gas vesicles, gas-filled protein nanostructures from microorganisms, were engineered as the first biomolecular ultrasound contrast agents, opening the door for more direct visualization of cellular and molecular function by ultrasound imaging. The ordered protein shell structure and unique gas filling mechanism of biogenic gas vesicles endow them with excellent stability and attractive acoustic responses. What's more, their genetic encodability enables them to act as acoustic reporter genes. This article reviews the upgrading progresses of ultrasound contrast agents from microbubbles to biogenic gas vesicles, and the opportunities and challenges for the commercial and clinical translation of the nascent field of biomolecular ultrasound.

Artificial Intelligence in Endoscopic Ultrasound for Pancreatic Cancer: Where Are We Now and What Does the Future Entail?

Pancreatic cancer is a highly lethal disease associated with significant morbidity and mortality. In the United States (US), the overall 5-year relative survival rate for pancreatic cancer during the 2012-2018 period was 11.5%. However, the cancer stage at diagnosis strongly influences relative survival in these patients. Per the National Cancer Institute (NCI) statistics for 2012-2018, the 5-year relative survival rate for patients with localized disease was 43.9%, while it was 3.1% for patients with distant metastasis. The poor survival rates are primarily due to the late development of clinical signs and symptoms. Hence, early diagnosis is critical in improving treatment outcomes. In recent years, artificial intelligence (AI) has gained immense popularity in gastroenterology. AI-assisted endoscopic ultrasound (EUS) models have been touted as a breakthrough in the early detection of pancreatic cancer. These models may also accurately differentiate pancreatic cancer from chronic pancreatitis and autoimmune pancreatitis, which mimics pancreatic cancer on radiological imaging. In this review, we detail the application of AI-assisted EUS models for pancreatic cancer detection. We also highlight the utility of AI-assisted EUS models in differentiating pancreatic cancer from radiological mimickers. Furthermore, we discuss the current limitations and future applications of AI technology in EUS for pancreatic cancers.

Application of artificial intelligence in diagnosis of pancreatic malignancies by endoscopic ultrasound: a systemic review

Background

Pancreatic cancer (PC) is a highly fatal malignancy with a global overall 5-year survival of under 10%. Screening of PC is not recommended outside of clinical trials. Endoscopic ultrasonography (EUS) is a very sensitive test to identify PC but lacks specificity and is operator-dependent, especially in the presence of chronic pancreatitis (CP). Artificial Intelligence (AI) is a growing field with a wide range of applications to augment the currently available modalities. This study was undertaken to study the effectiveness of AI with EUS in the diagnosis of PC.

Methods

Studies from MEDLINE and EMBASE databases reporting the AI performance applied to EUS imaging for recognizing PC. Data were analyzed using descriptive statistics. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used to assess the quality of the included studies.

Results

A total of 11 articles reported the role of EUS in the diagnosis of PC. The overall accuracy, sensitivity, and specificity of AI in recognizing PC were 80-97.5%, 83-100%, and 50-99%, respectively, with corresponding positive predictive value (PPV) and negative predictive value (NPV) of 75-99% and 57-100%, respectively. Types of AI studied were artificial neural networks (ANNs), convolutional neural networks (CNN), and support vector machine (SVM). Seven studies using other than basic ANN reported a sensitivity and specificity of 88-96% and 83-94% to differentiate PC from CP. Two studies using SVM reported a 94-96% sensitivity, 93%-99% specificity, and 94-98% accuracy to diagnose PC from CP. The reported sensitivity and specificity of detection of malignant from benign Intraductal Papillary Mucinous Neoplasms (IPMNs) was 96% and 92%, respectively.

Conclusion

AI reported a high sensitivity with high specificity and accuracy to diagnose PC, differentiate PC from CP, and differentiate benign from malignant IPMN when used with EUS.

A Bibliometric Analysis of Publications on Endoscopic Ultrasound

Background

Over the past 40 years, endoscopic ultrasound (EUS) has become a safe and effective tool for both diagnostic and therapeutic applications. A growing number of articles have been published annually. We aimed to explore global scientific outputs and hotspots of EUS published by different countries, organizations, and authors.

Methods

The global literature regarding EUS during the 1900–2020 period was identified from the Web of Science (WOS) Core database. “Bibliometrix” and software VOSviewer were applied to perform bibliometric analysis.

Results

The annual growth rate of publications from 1980 to 2020 was around 16% and the number of EUS-related articles had experienced a sudden increase in the last decade. Bhutani MS was the most productive author over the past years, with 94 publications. Hawes RH had the highest number of citations, with 6,034 citations. The United States and institutions from United States dominated the EUS research. Among the journals, GASTROINTESTINAL ENDOSCOPY published the highest number of articles, followed by ENDOSCOPY. The majority of top 10 frequently cited references were cited more than 200 times. Carcinoma, diagnosis, fine-needle-aspiration, cytology, and pancreatitis were the important keywords in co-occurrence analysis of keywords. Recent studies focused more on tissue acquisition, size of the needle, lumen-apposing metal stent, and fine-needle- biopsy.

Conclusion

Research on EUS has significantly increased in the last decade globally and it will continue to increase. Active collaboration among different authors and countries was observed in the EUS field. Tissue acquisition, size of the needle, apposing metal stent, and fine-needle-biopsy might be the latest research frontiers and should receive more attention.

Therapeutic ultrasound experiments in vitro: Review of factors influencing outcomes and reproducibility

Current in vitro sonication experiments show immense variability in experimental set-ups and methods used. As a result, there is uncertainty in the ultrasound field parameters experienced by sonicated samples, poor reproducibility of these experiments and thus reduced scientific value of the results obtained. The scope of this narrative review is to briefly describe mechanisms of action of ultrasound, list the most frequently used experimental set-ups and focus on a description of factors influencing the outcomes and reproducibility of these experiments. The factors assessed include: proper reporting of ultrasound exposure parameters, experimental geometry, coupling medium quality, influence of culture vessels, formation of standing waves, motion/rotation of the sonicated sample and the characteristics of the sample itself. In the discussion we describe pros and cons of particular exposure geometries and factors, and make a few recommendations as to how to increase the reproducibility and validity of the experiments performed.

Reliability of Endoscopic Ultrasound Using Miniprobes and Grayscale Histogram Analysis in Diagnosing Upper Gastrointestinal Subepithelial Lesions

Background

To assess the role of endoscopic ultrasound (EUS) in the diagnosis of upper gastrointestinal subepithelial lesions (SELs) and to investigate EUS combined with a grayscale histogram analysis for the differentiation of leiomyomas and gastrointestinal stromal tumors (GISTs).

Methods

A retrospective study of 709 patients with upper gastrointestinal SELs was conducted by EUS before endoscopic resection. The EUS findings of SELs and pathological results after endoscopic resection were compared. The EUS images of SELs, particularly, leiomyoma and GIST, were further analyzed via a grayscale histogram to differentiate between the two tumors.

Results

Of the 709 patients, 47 cases were pathologically undetermined. The diagnostic consistency of EUS with endoscopic resection was 88.2% (584/662), including 185 muscularis mucosa, 61 submucosa, and 338 muscularis propria, respectively. The diagnostic consistency of EUS with pathology was 80.1% (530/662). The gray value of GISTs was significantly higher than that of leiomyomas (58.9 ± 8.3 vs. 39.5 ± 5.9, t = 57.0, P < 0.0001). The standard deviation of leiomyomas was significantly lower than that of GISTs (20.6 ± 7.0 vs. 39.8 ± 9.3, t = 23.7, P < 0.0001). The grayscale histogram analysis of GISTs showed higher echo ultrasound, and the echo of leiomyoma was more uniform.

Conclusion

EUS is the preferred procedure for the evaluation of upper gastrointestinal SELs. EUS combined with a grayscale histogram analysis is an effective method for the differentiation of leiomyomas and GISTs.

Present and Future of Endoscopic Ultrasound-Guided Tissue Acquisition in Solid Pancreatic Tumors

Endoscopic ultrasound-guided tissue acquisition (EUS-TA) is a well-established method for pathological diagnosis of solid pancreatic neoplasm. It can be performed either as EUS-guided fine-needle aspiration (EUS-FNA) or EUS-guided fine-needle biopsy (EUSFNB). The incidence of adverse events related to EUS-TA is less than 1%. The factors that affect the diagnostic accuracy and specimen adequacy include the techniques used, type and size of the needle, competency of endosonographers, presence of cytopathologists/ cytotechnologists, and rapid on-site examination. EUS-TA may contribute to precision medicine through obtaining tissue samples for next-generation sequencing. The current status, several clinical issues for diagnostic yield and adverse events, and future perspectives of EUS-FNA/FNB for diagnosing pancreatic neoplasm have been discussed in this review article.

Time-to-isolation-guided cryoballoon ablation reduces oesophageal and mediastinal alterations detected by endoscopic ultrasound: results of the MADE-PVI trial

Aims

Cryoballoon ablation is safe and efficient for achieving pulmonary vein isolation (PVI) in atrial fibrillation. Structural oesophago-mediastinal lesions, which seem to be associated with an increased risk of the lethal complication of an atrio-oesophageal fistula, have been described. MADE-PVI (Mediastino-oesophageal Alterations Detected by Endosonography after PVI) aimed at evaluating safety of cryoballoon PVI in relation to two different freeze protocols. As time-to-isolation-(TTI)-guided protocol has been reported to be as effective as conventional ‘two freeze protocol’, we hypothesized a TTI-guided protocol causes less oesophago-mediastinal lesions.

Methods and results

Seventy consecutive patients were scheduled for cryoballoon (2nd generation) PVI employing either a conventional protocol (n = 35: 2 × 180 s per vein) or a TTI-guided approach (n = 35: TTI + 120 s per vein or 1 × 180 s in case TTI could not be measured). Oesophagogastroduodenoscopy and endoscopic ultrasound, assessing oesophago-mediastinal alterations (e.g. ulceration, oedema) were performed blinded prior and post-ablation. Post-interventional mediastinal oedematous alterations were detected in 70% with a mean diameter of 14 mm (±0.9 mm), while only 15% revealed large mediastinal oedema >20 mm. Oesophageal lesions due to PVI occurred in 5%. Freeze protocols had a distinct impact on oesophago-mediastinal alterations as mean diameter and frequency of large oedema were significantly increased in patients after conventional protocol PVI (17 mm vs. 11 mm; 26% vs. 6%). Furthermore, every oesophageal lesion was detected in patients with conventional protocol (9%). No major complication occurred in either group.

Conclusion

The present prospective study demonstrates a significant impact of freeze protocol on oesophago-mediastinal alterations. A TTI-guided protocol reduces mediastino-oesophageal lesions and may reduce short- and long-term complications of cryoballoon PVI.

Diagnostic yield of endoscopic ultrasound-guided biopsy of focal liver lesions

Endoscopic ultrasonography (EUS) has become an indispensable method for diagnosis and therapeutic procedures in gastroenterology. As experience with this technique grows, new indications continue to emerge. Due to the vicinity of the transducer to the liver, endoscopic ultrasonography provides detailed images of the liver segments and its vascular and biliary structures. Endosonographers have made an effort to define a clinical role for endoscopic ultrasound in liver diseases; however, not much is known about endoscopic ultrasound guided fine needle aspiration (EUS-FNA) in hepatic focal lesions. This review summarizes the available evidence regarding the usefulness of endoscopic ultrasound-guided fine needle aspiration in patients with focal liver lesions.

Concise review on the comparative efficacy of endoscopic ultrasound-guided fine-needle aspiration vs core biopsy in pancreatic masses, upper and lower gastrointestinal submucosal tumors

Endoscopic ultrasound (EUS)-guided fine needle aspiration with or without biopsy (FNA/FNB) are the primary diagnostic tools for gastrointestinal submucosal tumors. EUS-guided fine needle aspiration (EUS-FNA) is considered a first line diagnostic method for the characterization of pancreatic and upper gastrointestinal lesions, since it allows for the direct visualization of the collection of specimens for cytopathologic analysis. EUS-FNA is most effective and accurate when immediate cytologic assessment is permitted by the presence of a cytopathologist on site. Unfortunately, the accuracy and thus the diagnostic yield of collected specimens suffer without this immediate analysis. Recently, a EUS-FNB needle capable of obtaining core samples (fine needle biopsy, FNB) has been developed and has shown promising results. This new tool adds a new dimension to the diagnostic and therapeutic utility of this technique. The aim of the present review is to compare the efficacy of EUS-FNA to that afforded by EUS-FNB in the characterization of pancreatic masses and of upper and lower gastrointestinal submucosal tumors.