Introduction

Contrast enhanced endoscopic ultrasound (CE-EUS) has emerged as an invaluable real time tool in the characterisation and diagnosis of gastrointestinal(GI) lesions but application in therapeutic EUS (post tissue acquisition) remains under evaluated. Bleeding post EUS tissue acquisition(TA) is usually mild, self limiting though serious complications can still occur. We aim to review if application of real time CE-EUS to assess and quantify severity of bleeding has any impact on the clinical outcome and need for intervention.

Aims & Methods

This was a retrospective study of 1597 consecutive patients who underwent tissue acquisition at a single tertiary centre between March 2018 to March 2023. Patients with new onset fluid collection/haemorrhage post tissue acquisition who underwent CE- EUS using Sonazoid contrast agent were included. Information on baseline demographics, pre/post laboratory tests, EUS procedural findings and clinical outcomes were collected. Video recordings of the CE-EUS were reviewed and graded according to the extent of perfusion with presence/absence of contrast extravasation and pseudo-aneurysm.
Severity EUS findings of the fluid/hematoma post CH-EUS injection(observed for at least 90s)
Grade 0 No perfusion noted
Grade 1 Perfusion noted < 50% of total area
Grade2 Perfusion noted > 50% of total area
Grade 3 100% perfusion of the area of concern

Results

60/1597 (4.4%) patients had hematoma/new onset fluid collection post EUS-TA with CE-EUS performed. Overall intervention rate post EUS-TA was 5/1597 (0.31%). 29 patients were subsequently analysed based on video availability and divided into no leak(grade 0) and active leak group(grade1-3). There were no significant differences in the median age (53 vs 64, p = 0.13), Charlson Co-morbidity index (3.5 vs 3, p = 0.561) and antiplatelet usage. There were also no significant differences between lesion size (24.6 vs 31.6, p= 0.246), needle sizes and the number of passes(3 vs 2, p= 0.34). 53% (8/17) of the active leak group had final diagnosis of neuroendocrine/cystic lesions as compared to the non active leak 3/12(25%). Fisher’s exact test used did not show any statistically significant association between haemoglobin drop, need for intervention and death (p=0.413) respectively with the CE-EUS results.

Conclusion

Post EUS Tissue acquisition bleeding is mostly mild and self-limiting. More studies are required to see if CE-EUS can play a objective role in predicting adverse outcomes.

Introduction

The use of contrast-enhanced endoscopic ultrasound (CE-EUS) for characterizing solid pancreatic masses has improved diagnostic capabilities. We aimed to evaluate the performance of an artificial intelligence (AI)-powered system for differential diagnosis of pancreatic adenocarcinoma using CE-EUS.

Aims & Methods

The methodology integrates advanced imaging analysis and machine learning (ML) to develop an automated framework for pancreatic tumor characterization using EUS. A convolutional neural network (CNN) is first trained on labeled non-contrast EUS images to detect and segment the pancreas and tumor regions accurately. Once trained, the CNN is applied to new cases, identifying regions of interest (ROIs) in the non-contrast images, which are subsequently mapped onto the corresponding contrast-enhanced images for further analysis. Time-Intensity Curve (TIC) analysis was performed on the mapped ROIs, extracting a comprehensive set of quantitative parameters describing contrast enhancement dynamics. These parameters include temporal metrics (e.g., time to peak, rise time), intensity measures (e.g., peak intensity, wash-in intensity), slopes (e.g., wash-in and wash-out rates), area-based metrics (e.g., area under the curve), and perfusion-related characteristics (e.g., perfusion index, blood flow). The extracted TIC parameters are then used to train a feedforward neural network (FNN), which learns to differentiate diagnostic categories based on the perfusion characteristics of the lesions. In the final integrated model, the CNN detects pancreas and tumor regions, maps them to contrast-enhanced images, computes TIC parameters, and feeds these into the FNN to provide automated diagnostic predictions.

Results

Retrospective analysis was performed on a prospectively collected dataset of 120 CE-EUS videos obtained from patients with solid pancreatic masses in 3 tertiary referral centers. The dataset included 88 pancreatic adenocarcinomas, 1 lymphoma, 4 metastatic lesions, 10 neuroendocrine neoplasms (G1/G2), 15 cases of chronic pancreatitis, and 2 solid pseudopapillary neoplasms (SPNs). Diagnostic performance was evaluated by calculating sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy. Based on CNN analysis, both precision and recall were also calculated. The AI-powered CE-EUS system achieved high diagnostic performance, with an accuracy of over 95% for the diagnosis of pancreatic adenocarcinoma. Precision and recall were also excellent for differentiating adenocarcinoma from other pancreatic lesions based on CNN analysis.

Conclusion

This novel AI-based approach using CE-EUS reliably distinguished pancreatic adenocarcinoma from other solid pancreatic masses. Real-time analysis of time-intensity curve parameters enhances diagnostic accuracy and offers a promising adjunct to traditional EUS methods. Further prospective validation is warranted to confirm these findings and explore clinical applicability.

References

1. Săftoiu A, Vilmann P, Bhutani MS, Hassan H, Hawes R, Dietrich CF, et al. Enhanced endoscopic ultrasound imaging for pancreatic lesions: A review.
World J Gastrointest Endosc. 2022 Jul 16;14(7):369–84. doi:10.4253/wjge.v14.i7.369 PMID: 35967758; PMCID: PMC9367228.
2. Liang T, Zhang H, Wang Y, Sun Y, Ma K, Liu W, et al. Artificial intelligence-assisted endoscopic ultrasound for detection of pancreatic lesions: A systematic review and meta-analysis. World J Gastroenterol. 2023 Feb 21;29(7):1150–1164. doi:10.3748/wjg.v29.i7.1150 PMID: 36849883; PMCID: PMC10720860.

Clinical Case Summary

Endoscopic ultrasound (EUS) is an essential tool in the diagnosis, staging, and treatment of various pathologies, playing an increasingly significant role in clinical practice.

We present the case of a 35-year-old patient with a history of hypertriglyceridemia and post-measles pneumopathy at 6 months of age. He was referred to the endocrinology clinic for hypoglycemia detected on routine blood tests. Upon exploration, the patient reported sudden episodes of hunger, sweating, and malaise, relieved by food intake for two years. A prolonged fasting test revealed glucose of 26mg/dL, insulin of 14.8 uUI/mL, and C-peptide of 2.4ng/mL. Initially, an abdominopelvic computed tomography (CT) scan showed an homogeneous pancreas without lesions. Due to persistent suspicion of insulinoma, magnetic resonance cholangiopancreatography was requested but without abnormalities. A chest CT scan also revealed no findings. Finally, the patient underwent EUS, revealing a hypoechoic nodule in the cephalopancreatic region of 10x8mm. Fine-needle aspiration biopsy confirmed a neuroendocrine tumor. After three years since the onset of symptoms, the patient underwent a cephalic duodenopancreatectomy, with histology confirmation of a well-differentiated G1 pT1 pN0 neuroendocrine tumor. One month later, the patient experienced intractable vomiting, fever, and elevated inflammatory markers. Imaging revealed a peri-pancreatic collection, leading to therapeutic EUS. An 85x60mm heterogeneous collection was observed and drained using a pigtail stent, allowing purulent content to flow into the gastric lumen. The patient showed substantial improvement after drainage and antibiotic. One month of follow-up showed no further complications.

Clinical suspicion of insulinoma can be confirmed by standard endocrinological tests, yet its identification remains challenging. This case illustrates how EUS not only enhanced diagnostic sensitivity but also played a key role in managing subsequent complications.

Introduction

Endoscopic ultrasound (EUS) emerged as a revolutionary intervention in gastroenterology, it has been extensively utilized among adult patients, however EUS utility in pediatric patients has remained limited due to EUS endoscope design which includes rigidity, diameter, traumatic distal tip, further more complicated by need of Monitored Anesthesia Care (MAC) or General Anesthesia (GA) for intervention which require specialized pediatric anesthesia team[i]. Fewer studies have been conducted so far regarding EUS utility, effectiveness and safety among children, most of the studies have smaller data. Recently, the European Society for Pediatric Gastroenterology Hepatology and Nutrition (ESPGHAN) and the European Society of Gastrointestinal Endoscopy (ESGE) have published joint guidelines for EUS in children which highlights the various indications for EUS in children[ii].In Pakistan, only few endoscopy centers are performing pediatric EUS.

Aims & Methods

This article aims to describe the safety along with technical and clinical success of EUS for both diagnostic and therapeutic purposes among children at a tertiary referral endoscopy center in Pakistan.
Retrospective charts review of patients ≤ 18 years of age who underwent EUS for disgnostic or therapeutic purpose over 10 years, from 2015 to 2024, at Sindh Institute of Advanced Endoscopy and Gastroenterology. This institute was initially working under Civil Hospital Karachi as Endoscopy Suite of S4 Unit. Since May 2023, it has been working as a separate endoscopy unit. This endoscopy center is a referral unit located in the largest city of Pakistan.

Results

A total of 130 patients ≤ 18 years age had EUS, the youngest was 5 years old and 54.3% were male gender. Primary indication for EUS examination included: 35 chronic pancreatitis, 39 pancreatic pseudocyst, 12 pancreatic mass, 3 biliary obstruction with suspected choledochal cyst, 2 liver biopsy, 21 gastrointestinal tract lesions, 6 lymph nodes and 12 other causes. 96 EUS were performed for diagnostic purpose, in which 20 patients underwent fine needle biopsy and 6 underwent fine needle aspiration. Among therapeutic EUS, patients underwent 21 EUS guided pseudocyst drainage, one patient had EUS guided walled off necrosis drainage, 4 patients underwent celiac plexus block referred for pain management of chronic pancreatitis,one patient underwent EUS guided pancreatic duct cannulation and stent placement and one patient had EUS guided randezvous procedure. All therapeutic procedures were performed under general anesthesia whereas diagnostic EUS were performed under monitored anesthesia care. No immediate or early complications were seen.

Conclusion

In this modern era of advanced diagnostic tools and minimally invasive interventions, EUS related procedures are safe and effective in pediatric group of patients too. However, this procedure should be standardized and performed at centers with trained endoscopists and an experienced pediatric anesthesia team.

References

[i] Thomson, M., Tringali, A., Dumonceau, J.-M., Tavares, M., Tabbers, M.M., Furlano, R., Spaander, M., Hassan, C., Tzvinikos, C., Ijsselstijn, H., Viala, J., Dall'Oglio, L., Benninga, M., Orel, R., Vandenplas, Y., Keil, R., Romano, C., Brownstone, E., Hlava, Š., Gerner, P., Dolak, W., Landi, R., Huber, W.D., Everett, S., Vecsei, A., Aabakken, L., Amil-Dias, J. and Zambelli, A. (2017), Paediatric Gastrointestinal Endoscopy. Journal of Pediatric Gastroenterology and Nutrition, 64: 133-153. https://doi.org/10.1097/MPG.0000000000001408.
[ii] Thomson, M., Tringali, A., Dumonceau, J.-M., Tavares, M., Tabbers, M.M., Furlano, R., Spaander, M., Hassan, C., Tzvinikos, C., Ijsselstijn, H., Viala, J., Dall'Oglio, L., Benninga, M., Orel, R., Vandenplas, Y., Keil, R., Romano, C., Brownstone, E., Hlava, Š., Gerner, P., Dolak, W., Landi, R., Huber, W.D., Everett, S., Vecsei, A., Aabakken, L., Amil-Dias, J. and Zambelli, A. (2017), Paediatric Gastrointestinal Endoscopy. Journal of Pediatric Gastroenterology and Nutrition, 64: 133-153. https://doi.org/10.1097/MPG.0000000000001408

Introduction

Contrast-enhanced endoscopic ultrasound (CE-EUS) is a valuable tool for evaluating gastrointestinal lesions, providing real-time insights into vascular patterns and tissue perfusion. It is increasingly utilized to differentiate solid and cystic lesions, particularly in pancreaticobiliary diseases. However, CE-EUS interpretation remains operator-dependent, with variability influenced by observer expertise and a lack of standardized criteria. Previous studies on interobserver agreement (IOA) in CE-EUS interpretation have yielded inconsistent results, underscoring the need for further investigation into dynamic contrast features such as enhancement patterns and wash-in/wash-out phases.

Aims & Methods

This study aimed to evaluate IOA among endosonographers with varying levels of expertise in interpreting CE-EUS videos, focusing on lesion classification, dynamic contrast features, and video quality. This multicenter retrospective study involved 24 endosonographers (15 experts, 9 non-experts) from 16 European centers. Participants completed an initial survey capturing their experience and institutional characteristics. Subsequently, they independently reviewed 60 CE-EUS videos (~1 minute each), recorded between 2021 and 2023, comprising 40 solid, 15 cystic, and 5 mixed lesions. Videos varied in quality. Observers assessed lesion type (solid or cystic), arterial and venous enhancement patterns (hyper-, hypo-, or non-enhancing), wash-in and wash-out timing (rapid or late), contrast distribution (homogeneous or inhomogeneous), and video quality. Fleiss’ kappa (κ) was used to calculate IOA for each parameter. A multivariate analysis was conducted to identify factors influencing IOA.

Results

Moderate agreement was found for lesion classification (κ = 0.47). IOA for arterial phase enhancement was slight (κ = 0.38), as was agreement for arterial wash-in timing (κ = 0.27), venous wash-out timing (κ = 0.21), and contrast distribution homogeneity (κ = 0.24). No agreement was reached for video quality assessment (κ = 0.14). Operator experience was not significantly associated with IOA. Multivariate analysis revealed that IOA for wash-in timing was influenced by procedural volume at the observer's center and the type of endoscopic equipment used (p = 0.004 and p = 0.034, respectively). Additionally, center volume significantly affected perceived video quality assessment (p = 0.035).

Conclusion

This study demonstrates considerable variability in CE-EUS interpretation among observers, particularly for dynamic contrast features, where agreement was slight. Lesion classification showed moderate reproducibility, but standardized evaluation criteria are needed for other parameters. Procedural volume at the observer's center significantly influenced IOA, emphasizing the importance of institutional experience. These findings highlight the need for improved training programs and interpretation frameworks to enhance the diagnostic consistency and clinical utility of CE-EUS.

Introduction

Chronic pancreatitis represents a risk for pancreatic cancer with an estimated effect of 16 in the first 2 years, 7.9 in the first 5 years and over 3 in 9 years. The sensitivity of endoscopic ultrasound fine needle aspiration (EUS-FNA) in diagnosing pancreatic malignancy in cases with and without chronic pancreatitis drops from 91.5% to 65.3%. Although contrast-enhanced fine needle aspiration (CH-EUS-FNA) was not statistically superior to standard EUS-FNA in diagnosing solid pancreatic lesions, some emphasis was placed on the usefulness of CH-EUS-FNA in cases of pancreatic masses on chronic pancreatitis.

Aims & Methods

Aim. To assess and compare the diagnostic rate of CH-EUS tissue acquisition (CH-EUS-TA) compared to standard EUS-TA in cases of solid pancreatic masses with features of chronic pancreatitis.

Material and methods. This is a retrospective unicenter study from 2020 to 2022 that included solid pancreatic masses (solid component > 80%) that required EUS-guided sampling and features of chronic pancreatitis that needed EUS tissue acquisition. We excluded patients with previous surgery or chemotherapy for pancreatic diseases, contraindications for tissue sampling or without 1-year follow-up in negative cases. We divided patients in two groups: group 1 with CH-EUS-FNA and group 2 with standard FNA, both using 22G needles. The final diagnosis was based on FNA or surgery results or on 1-year follow-up.

Results

There were 13 patients included in group 1 and 27 patients included in group 2. The sensitivity for malignancy was 85% in group 1 and 80% in group 2. No difference was proved regarding size or mass location, percentage of definitive chronic pancreatitis between groups. The most common lesion location was the head of the pancreas (60%), while the mean mass size was 2,4 cm. Less than 50% of patients (42%) were classified as “Definitive Chronic Pancreatitis” according to Rosemont Criteria. Regarding the severity of disease according to Cambridge Severity Score, the largest group (45% of patients) was the “Cambridge 3” group. 45% of the patients required main bile duct stenting for main bile duct stenosis. A small percent of patients (15%) showed signs of portal hypertension. In group 1, the hypo-enhancement was observed in 38.4% of patients.

Conclusion

In this retrospective series, the CH-EUS-FNA proved to perform similarly with EUS-FNA when chronic pancreatitis features were noticed. Further studies using EUS fine needle biopsy (EUS-FNB) contrast guided procedures are needed in this category of patients.

References

1. Kirkegard J et al. Chronic Pancreatitis and Pancreatic Cancer Risk: A Systematic Review and Meta-analysis. Am J Gastroenterol 2017
2. Abdallah MA, et al. Endoscopic Ultrasound Guided Fine-Needle Aspiration for Solid Lesions in Chronic Pancreatitis: A Systematic Review and Meta-Analysis. Dig Dis Sci. 2022

Disclosure

The authors have no conflicts of interest to declare.

Introduction

Endoscopic ultrasound guided Shear wave elastography (EUS-SWE) is a noninvasive technique to evaluate
organ fibrosis as hardness. Velocity of SWE (Vs, m/s) enables to quantify, and the measured value is
also evaluated with confidence index: VsN (Percentage of the net amount of effective of Vs, %). EUS-SWE has been reported as a useful diagnostic modality for chronic pancreatitis (S Shintani et al JMU 2023). As for pancreatic cancer, previous reports using transabdominal ultrasound have reported only that Vs of pancreatic cancer is elevated, but there are no reports of VsN or using EUS devices. In this study, we examined the characteristics of pancreatic cancer using EUS-SWE.

Aims & Methods

The subjects were patients who underwent EUS-SWE at Shiga University Hospital from April 2019 to December 2022. The retrospective study was conducted with 121 patients (pancreatic cancer, chronic pancreatitis, normal pancreas). EUS-SWE was performed at least 5 times, and the median value was measured. Vs and VsN were measured at central site of tumor cases, and pancreatic body with chronic pancreatitis and normal cases. Histogram analysis (Complexity) at the SWE measurement site was also performed to evaluate tissue heterogeneity. ALOKA ARIETTA 850 (FIJIFILM, Tokyo, Japan) and GF-UCT260 (Olympus Co., Tokyo, Japan) was used.

Results

The subjects were 69 cases of pancreatic cancer (39 males, age: 68.9±10.6 years), 10 cases of chronic pancreatitis (6 males, age: 74.3±5.5 years), and 42 normal cases (22 males, age: 57.5±11.1 years) The EUS-SWE results (pancreatic cancer / chronic pancreatitis / normal) were Success rate (%): 87.2 / 93.5 / 98.1, Vs (m/s): 2.27±0.61 / 2.6±0.67 / 1.68±0.49, VsN (%): 22.6±15.9 / 76.2±21.2 / 79.6±20.6. Complexity: 30.1±12.3 / 23.9±4.8 / 13.5±10.6 indicate that heterogeneity within the tissue is higher in the order of pancreatic cancer > chronic pancreatitis > normal group. VsN and Complexity were inversely correlated, and the higher the tissue heterogeneity, the lower the VsN (r=-0.45, p<0.001, Spearman correlation test).

Conclusion

Vs was increased in pancreatic cancer compared to normal pancreas. However, VsN was more likely to be decreased in pancreatic cancer, which associated with higher tissue heterogeneity. EUS-SWE for pancreatic cancer should consider tissue heterogeneity.

References

none