Digital Single-operator Cholangioscopy (DSOC) Improves Interobserver Agreement (IOA) and Accuracy for Evaluation of Indeterminate Biliary Strictures: The Monaco Classification

Acceptable number of cholangioscopy-guided biopsies for diagnosing perihilar cholangiocarcinoma

INTRODUCTION

diagnosing perihilar cholangiocarcinoma can be challenging. Previous studies suggest that the sensitivity of taking three cholangioscopy-guided biopsies is approximately 70 %. We hypothesized that obtaining four or more biopsies might improve the sensitivity for diagnosing perihilar cholangiocarcinoma.

OBJECTIVE

to determine the acceptable number of cholangioscopy-guided biopsies to improve sensitivity for diagnosing perihilar cholangiocarcinoma.

METHODS

this retrospective study analyzed clinical records of adults with perihilar stenosis who underwent cholangioscopy-guided biopsies. Patients with gallbladder cancer or metastatic bile duct obstruction were excluded. Data were grouped based on the number of biopsies taken: group A (one to three biopsies), group B (four to six biopsies), and group C (seven to ten biopsies). Results from each group were compared against a composite standard, including clinical follow-up and/or biopsies performed by alternative methods.

RESULTS

the group that underwent 4-6 biopsies had a sensitivity of 77.4 %, while the group with 7-10 biopsies had a sensitivity of 70.8 %. The group with 1-3 biopsies had a sensitivity of 34.5 %. Statistically significant differences were observed between the groups, with comparisons showing improved sensitivity in the 4-6 biopsy group versus the 1-3 biopsy group (χ² = 14.42, p = 0.0001), and the 7-10 biopsy group versus the 1-3 biopsy group (χ² = 6.56, p = 0.010).

CONCLUSIONS

performing four to six cholangioscopy-guided biopsies significantly improves sensitivity for diagnosing perihilar cholangiocarcinoma compared to one to three biopsies. Further studies are needed to validate these findings.

Diagnosing hilar cholangiocarcinoma: ERCP with cholangioscopy

Cholangiocarcinoma of the hepatic hilum represents a challenge in its diagnosis, in the palliation of the frequently associated jaundice, and in its treatment. Noninvasive imaging tests can offer a fairly accurate diagnostic approximation, but very often a histopathological diagnosis is necessary to exclude the so-called Klatskin-mimicking lesions, which can reach up to 20% in surgical series. ERCP is the most commonly used endoscopic procedure, both for tissue acquisition and for palliation of jaundice. Although probably underused, intraductal ultrasonography performed during ERCP can provide valuable information for the diagnosis of hilar cholangiocarcinoma. During ERCP, brush cytology and biopsy are performed to acquire tissue for histopathological confirmation of cholangiocarcinoma. The sensitivity of both methods alone is less than 50%. When biopsies are taken through a cholangioscope, the sensitivity is significantly increased. In this editorial we discuss a study by Alonso-Lárraga et al. published in the Spanish Journal of Gastroenterology. The highest sensitivity (77.4%) was obtained when 4 to 6 biopsies were taken with the SpyGlass cholangioscope. Direct visualization of lesions and the higher diagnostic yield of biopsies make ERCP with cholangioscopy the standard approach for patients with suspected perihilar cholangiocarcinoma.

The Role of Artificial Intelligence Combined With Digital Cholangioscopy for Indeterminant and Malignant Biliary Strictures: A Systematic Review and Meta-analysis

BACKGROUND

Current endoscopic retrograde cholangiopancreatography (ERCP) and cholangioscopic-based diagnostic sampling for indeterminant biliary strictures remain suboptimal. Artificial intelligence (AI)-based algorithms by means of computer vision in machine learning have been applied to cholangioscopy in an effort to improve diagnostic yield. The aim of this study was to perform a systematic review and meta-analysis to evaluate the diagnostic performance of AI-based diagnostic performance of AI-associated cholangioscopic diagnosis of indeterminant or malignant biliary strictures.

METHODS

Individualized searches were developed in accordance with PRISMA and MOOSE guidelines, and meta-analysis according to Cochrane Diagnostic Test Accuracy working group methodology. A bivariate model was used to compute pooled sensitivity and specificity, likelihood ratio, diagnostic odds ratio, and summary receiver operating characteristics curve (SROC).

RESULTS

Five studies (n=675 lesions; a total of 2,685,674 cholangioscopic images) were included. All but one study analyzed a deep learning AI-based system using a convoluted neural network (CNN) with an average image processing speed of 30 to 60 frames per second. The pooled sensitivity and specificity were 95% (95% CI: 85-98) and 88% (95% CI: 76-94), with a diagnostic accuracy (SROC) of 97% (95% CI: 95-98). Sensitivity analysis of CNN studies (4 studies, 538 patients) demonstrated a pooled sensitivity, specificity, and accuracy (SROC) of 95% (95% CI: 82-99), 88% (95% CI: 72-95), and 97% (95% CI: 95-98), respectively.

CONCLUSIONS

Artificial intelligence-based machine learning of cholangioscopy images appears to be a promising modality for the diagnosis of indeterminant and malignant biliary strictures.

Artificial intelligence for automatic diagnosis and pleomorphic morphological characterization of malignant biliary strictures using digital cholangioscopy

Diagnosing and characterizing biliary strictures (BS) remains challenging. Artificial intelligence (AI) applied to digital single-operator cholangioscopy (D-SOC) holds promise for improving diagnostic accuracy in indeterminate BS. This multicenter study aimed to validate a convolutional neural network (CNN) model using a large dataset of D-SOC images to automatically detect and characterize malignant BS. D-SOC exams from three centers-Centro Hospitalar Universitário de São João, Porto, Portugal (n = 123), Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Spain (n = 18), and New York University Langone Hospital, New York, USA (n = 23)-were included. Frames were categorized based on histopathology. The CNN's performance in detecting tumor vessels, papillary projections, nodules, and masses was assessed. The dataset was split into 90% training and 10% validation sets. Performance metrics included AUC, sensitivity, specificity, PPV, and NPV. Analysis of 96,020 images from 164 D-SOC exams (50,427 malignant strictures and 45,593 benign findings) showed the CNN achieved 92.9% accuracy, 91.7% sensitivity, 94.4% specificity, 95.1% PPV, 93.1% NPV, and an AUROC of 0.95. Accuracy rates for morphological features were 90.8% (papillary projections), 93.6% (nodules), 93.2% (masses), and 78.1% (tumor vessels). AI-driven CNN models hold promise for enhancing diagnostic accuracy in suspected biliary malignancies. This multicenter study contributes diverse datasets to ongoing research, supporting further AI applications in this patient population.

Effectiveness of cholangioscopy guided biopsy versus ERCP guided brushings in diagnosing malignant biliary strictures

BACKGROUND

Evaluation of lesions of the biliary tract are essential to diagnose given the dismal outcomes of cholangiocarcinoma. Historically, these diagnoses were made using brush biopsies obtained under Endoscopic Retrograde Cholangiopancreatography (ERCP). To increase the accuracy of biliary biopsies, SpyGlassTM Discover cholangioscopy guided biopsy has been developed, providing greater tissue yield and direct visualization of the biliary epithelium. We evaluated the diagnostic accuracy of ERCP guided brushings and SpyGlassTM Discover guided biopsies at a single institution.

METHODS

Following IRB approval, all diagnostic biliary biopsies utilizing both ERCP guided brushings and/or SpyGlassTM Discover between 8/2015 and 6/2022 were retrospectively evaluated. Demographic and clinicopathologic data were collected. Fischer's t-tests and Chi-square analyses were completed as appropriate (p < 0.05).

RESULTS

Overall, 46 patients with an average age of 61 years were included in this study; 59% of the patients were female and 41% were male. 87% of patients had at least one SpyGlassTM Discover guided biopsy and one ERCP guided brushing and 13% of patients had at least one SpyGlassTM Discover guided biopsy alone. SpyGlassTM Discover correctly identified 82% of malignancies while brushings identified only 47% of malignancies.

CONCLUSIONS

SpyGlassTM Discover guided biopsies yield a greater diagnostic result than ERCP guided brushings. Therefore, SpyGlassTM Discover should be considered as the standard for diagnosing biliary lesions at our institution in conjunction with ERCP procedure. The classification of visual characteristics of biliary lesions should be investigated in the future as the high-resolution image generated by SpyGlassTM Discover can allow for detailed visual observation of strictures and potentially aid in better characterization and location of disease.

Endoscopic retrograde cholangiopancreatography: A comprehensive review as a single diagnostic tool

Endoscopic retrograde cholangiopancreatography (ERCP) was initially introduced in clinical practice as diagnostic tool. However, the presence of adverse events and the development of non-invasive techniques, such as magnetic resonance cholangiopancreatography (MRCP) and endoscopic ultrasound (EUS), limited its role as a stand-alone diagnostic choice, modifying its role to the leader of therapeutic pancreatobiliary endoscopy. Despite technological advances, there are still conditions where non-invasive diagnostic modalities are inconclusive, such as indeterminate biliary and pancreatic duct strictures, primary sclerosing cholangitis functional stenoses, intraductal papillary mucinous neoplasms (IPMNs) and paediatric indications, such as congenital anatomical abnormalities. This narrative review aimed to identify and analyse indications of diagnostic ERCP, without the need for therapeutic manipulations.

Diagnostic Approach to Biliary Strictures

Biliary strictures represent a narrowing of the bile ducts, leading to obstruction that may result from benign or malignant etiologies. Accurate diagnosis is crucial but challenging due to overlapping features between benign and malignant strictures. This review presents a comprehensive diagnostic approach that integrates biochemical markers, imaging modalities, and advanced endoscopic techniques to distinguish between these causes. Imaging tools such as ultrasound, MRI/MRCP, and CECT are commonly used, each with distinct advantages and limitations. Furthermore, endoscopic procedures such as ERCP and EUS are key in tissue acquisition, enhancing diagnostic accuracy, especially for indeterminate or complex strictures. Recent innovations, including artificial intelligence and new endoscopic techniques, hold promise in enhancing precision and reducing diagnostic challenges. This review emphasizes a multidisciplinary strategy to improve diagnostic pathways, ensuring timely management for patients with biliary strictures.

Diagnostic cholangioscopy for surgical planning of extrahepatic cholangiocarcinoma

The recent clinical outcomes of multi-regimen chemotherapy included prolonged survival and a high rate of conversion to surgery in Asian patients with advanced biliary tract cancer. The ability of single-operator cholangioscopy (SOC) to detect and stage extrahepatic cholangiocarcinoma (CCC) in intraductal lesions is becoming more important in determining the extent of surgery. The aim of this study was to evaluate the role of SOC in surgical planning for extrahepatic CCC. We reviewed the consecutive data of patients who received nab-paclitaxel plus gemcitabine-cisplatin for the management of extrahepatic CCC and underwent preoperative evaluations between June 2020 and August 2022. SOC was performed to determine the precise extent of the disease in patients with a good response to chemotherapy who were considering surgical treatment. Among the 38 patients included, 30 (79%) were diagnosed with perihilar CCC, six (16%) with distal CCC, and two (5%) with intraductal papillary neoplasm of the bile duct. Intraductal evaluation with SOC altered disease extent defined by previous imaging findings in 14 (37%) patients. In those patients, five (36%) were changed to less extensive surgery, four (29%) to conversion surgery, four (29%) avoided surgery, and one (7%) was changed to more extensive surgery. Among the 38 included patients, 27 (71%) underwent surgery, and the accuracy of the visual impressions was 93%, as confirmed by the surgical pathology report. In conclusion, SOC examination of patients with potentially resectable extrahepatic CCC was more precise than conventional diagnostic evaluations and could help in planning surgical options.

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.

Diagnostic Accuracy Performance of Fluorescence In Situ Hybridization (FISH) for Biliary Strictures: A Systematic Review and Meta-Analysis

Background and Aims: This systematic review and meta-analysis aims to compare the performance of UroVysion® FISH based on the different definitions of a positive result used in published literature with the goal of determining the optimal FISH definition for detecting pancreaticobiliary malignancy. Methods: A systematic literature search identified studies from database inception to Sept 2024 that evaluated the diagnostic performance of FISH in determining malignancy among patients with biliary strictures. All thresholds for positive FISH, as defined by the individual study, were included in this review. Subgroup analysis was performed based on the definitions of positive FISH as follows: (1) polysomy only; (2) polysomy, tetrasomy, or trisomy; and (3) polysomy or 9p deletion. Results: Eighteen studies comprising 2516 FISH specimens were analyzed, including 1133 (45.0%) with malignancy. Using a threshold for positivity as defined in individual studies, the overall sensitivity of FISH was 57.6% (95% confidence interval [CI], 49.4-65.4%), and the overall specificity was 87.8% (95% CI, 79.2-93.2%). Subgroup analysis showed that polysomy as the threshold for positive FISH yielded a sensitivity of 49.4% (95% CI, 43.2-55.5%), with an increased specificity of 96.2% (95% CI, 92.7-98.1%), while polysomy + tetrasomy/trisomy as positive FISH resulted in an increased sensitivity of 64.3% (95% CI 55.4-72.2%) but a decreased specificity of 78.9% (95% CI 64.4-88.5%). The addition of 9p deletion to polysomy as the criteria for a positive test resulted in a non-significant increase in sensitivity (54.7% (95% CI 42.4-66.5%) while maintaining specificity (95.1% (95% CI 84.0-98.6%). Conclusions: Based on these findings, polysomy only or polysomy/9p deletion should be considered as the criterion for defining a positive FISH test to improve diagnostic sensitivity while maintaining high specificity.

Cholangioscopy-based convoluted neuronal network vs. confocal laser endomicroscopy in identification of neoplastic biliary strictures

Background and study aims Artificial intelligence (AI) models have demonstrated high diagnostic performance identifying neoplasia during digital single-operator cholangioscopy (DSOC). To date, there are no studies directly comparing AI vs. DSOC-guided probe-base confocal laser endomicroscopy (DSOC-pCLE). Thus, we aimed to compare the diagnostic accuracy of a DSOC-based AI model with DSOC-pCLE for identifying neoplasia in patients with indeterminate biliary strictures. Patients and methods This retrospective cohort-based diagnostic accuracy study included patients ≥ 18 years old who underwent DSOC and DSOC-pCLE (June 2014 to May 2022). Four methods were used to diagnose each patient's biliary structure, including DSOC direct visualization, DSOC-pCLE, an offline DSOC-based AI model analysis performed in DSOC recordings, and DSOC/pCLE-guided biopsies. The reference standard for neoplasia was a diagnosis based on further clinical evolution, imaging, or surgical specimen findings during a 12-month follow-up period. Results A total of 90 patients were included in the study. Eighty-six of 90 (95.5%) had neoplastic lesions including cholangiocarcinoma (98.8%) and tubulopapillary adenoma (1.2%). Four cases were inflammatory including two cases with chronic inflammation and two cases of primary sclerosing cholangitis. Compared with DSOC-AI, which obtained an area under the receiver operator curve (AUC) of 0.79, DSOC direct visualization had an AUC of 0.74 ( P = 0.763), DSOC-pCLE had an AUC of 0.72 ( P = 0.634), and DSOC- and pCLE-guided biopsy had an AUC of 0.83 ( P = 0.809). Conclusions The DSOC-AI model demonstrated an offline diagnostic performance similar to that of DSOC-pCLE, DSOC alone, and DSOC/pCLE-guided biopsies. Larger multicenter, prospective, head-to-head trials with a proportional sample among neoplastic and nonneoplastic cases are advisable to confirm the obtained results.

Artificial intelligence in pancreaticobiliary endoscopy: Current applications and future directions

Pancreaticobiliary endoscopy is an essential tool for diagnosing and treating pancreaticobiliary diseases. However, it does not fully meet clinical needs, which presents challenges such as significant difficulty in operation and risks of missed diagnosis or misdiagnosis. In recent years, artificial intelligence (AI) has enhanced the diagnostic and treatment efficiency and quality of pancreaticobiliary endoscopy. Diagnosis and differential diagnosis based on endoscopic ultrasound (EUS) images, pathology of EUS-guided fine-needle aspiration or biopsy, need for endoscopic retrograde cholangiopancreatography (ERCP) and assessment of operational difficulty, postoperative complications and prediction of patient prognosis, and real-time procedure guidance. This review provides an overview of AI applications in pancreaticobiliary endoscopy and proposes future development directions in aspects such as data quality and algorithmic interpretability, aiming to provide new insights for the integration of AI technology with pancreaticobiliary endoscopy.

Endoscopic evaluation of indeterminate biliary strictures: Cholangioscopy, endoscopic ultrasound, or both?

Accurate and timely diagnosis of biliary strictures can be challenging. Because the diagnostic sensitivity and accuracy of standard endoscopic retrograde cholangiopancreatography-based tissue sampling for malignancy are suboptimal, additional endoscopic evaluation by cholangioscopy and/or endoscopic ultrasound (EUS) is often necessary to differentiate between malignant and benign biliary strictures to guide clinical management. While direct visualization by cholangioscopy and/or high-resolution imaging by EUS are often the first step in the evaluation of an indeterminate biliary stricture (IDBS), tissue diagnosis by cholangioscopy-guided biopsy and/or EUS-guided fine-needle tissue acquisition is the preferred modality to establish a diagnosis of malignancy. Because each modality has its own strengths and limitations, selection of cholangioscopy and EUS is best guided by the biliary stricture location and local expertise. Artificial intelligence-assisted diagnosis, biopsy forceps with improved design, contrast-enhanced EUS, and dedicated fine-needle biopsy devices are recent technological advances that may further improve the diagnostic performance of cholangioscopy and EUS in patients with IDBS.

Direct Single-Operator Cholangioscopy and Intraductal Ultrasonography in Patients with Indeterminate Biliary Strictures: A Single Center Experience

The evaluation of biliary strictures poses a challenge due to the low sensitivity of standard diagnostic approaches, but the advent of direct single-operator cholangioscopy (DSOC) has revolutionized this paradigm. Our study aimed to assess the diagnostic performance of DSOC and DSOC-targeted biopsies, intraductal ultrasound (IDUS), and standard brush cytology in patients with indeterminate biliary strictures (IBS). We reviewed patients who underwent advanced diagnostic evaluation for IBS at our endoscopy unit from January 2018 to December 2022, all of whom had previously undergone at least one endoscopic attempt to characterize the biliary stricture. Final diagnoses were established based on surgical pathology and/or clinical and radiological follow-up spanning at least 12 months. A total of 57 patients, with a mean age of 67.2 ± 10.0 years, were included, with a mean follow-up of 18.2 ± 18.1 months. The majority of IBS were located in the distal common bile duct (45.6%), with malignancy confirmed in 35 patients (61.4%). DSOC and IDUS demonstrated significantly higher accuracies (89.5% and 82.7%, respectively) compared to standard cytology (61.5%, p < 0.05). Both DSOC visualization and IDUS exhibited optimal diagnostic yields in differentiating IBS with an acceptable safety profile.

Still elusive: Developments in the accurate diagnosis of indeterminate biliary strictures

Indeterminate biliary strictures pose a significant diagnostic dilemma for gastroenterologists. Despite advances in endoscopic techniques and instruments, it is difficult to differentiate between benign and malignant pathology. A positive histological diagnosis is always preferred prior to high risk hepatobiliary surgery, or to inform other types of therapy. Endoscopic retrograde cholangiopancreatography with brushings has low sensitivity and despite significant improvements in instruments there is still an unacceptably high false negative rate. Other methods such as endoscopic ultrasound and cholangioscopy have improved diagnostic quality. In this review we explore the techniques available to aid accurate diagnosis of indeterminate biliary strictures and obtain accurate histology to facilitate clinical management.

Atlas for Cholangioscopy and Cholecystoscopy: A Primer for Diagnostic and Therapeutic Endoscopy in the Biliary Tree and Gallbladder

Percutaneous endoscopy of the biliary system (cholangioscopy) and gallbladder (cholecystoscopy) has significantly impacted diagnostic and therapeutic approaches to many diseases in interventional radiology, overcoming previous challenges related to scope size and rigidity. The current endoscopes offer enhanced maneuverability within narrow tubular structures such as bile ducts. Before endoscopy, reliance on 2D imaging modalities limited real-time visualization during percutaneous procedures. Percutaneous endoscopy provides 3D perspectives, enabling a better appreciation of normal structures, targeted biopsy of lesions, and accurate deployment of therapeutic interventions. This review aims to explore percutaneous endoscopic findings across various biliary and gallbladder pathologies.

Accurate and safe diagnosis and treatment of neoplastic biliary lesions using a novel 9F and 11F digital single-operator cholangioscope

Background and study aims Digital single-operator cholangioscopy (DSOC) allows the diagnosis of biliary duct disorders and treatment for complicated stones. However, these technologies have limitations such as the size of the probe and working channel, excessive cost, and low image resolution. Recently, a novel DSOC system (eyeMAX, Micro-Tech, Nanjing, China) was developed to address these limitations. We aimed to evaluate the usefulness and safety of a novel 9F and 11F DSOC system in terms of neoplastic diagnostic accuracy based on visual examination, ability to evaluate tumor extension and to achieve complete biliary stone clearance, and procedure-related adverse events (AEs). Patients and methods Data from ≥ 18-year-old patients who underwent DSOC from July 2021 to April 2022 were retrospectively recovered and divided into a diagnostic and a therapeutic cohort. Results A total of 80 patients were included. In the diagnostic cohort (n = 49/80), neovascularity was identified in 26 of 49 patients (46.9%). Biopsy was performed in 65.3% patients with adequate tissue sample obtained in 96.8% of cases. Biopsy confirmed neoplasia in 23 of 32 cases. DSOC visual impression achieved 91.6% sensitivity and 87.5% specificity in diagnosing neoplasms. In the therapeutic cohort (n = 43/80), 26 of 43 patients required lithotripsy alone. Total stone removal was achieved in 71% patients in the first session. Neither early nor late AEs were documented in either the diagnostic or therapeutic cohort. Conclusions The novel DSOC device has excellent diagnostic accuracy in distinguishing neoplastic biliary lesions as well as therapeutic benefits in the context of total stone removal, with no documented AEs.

Potential versatile uses of a novel ultra-thin peroral cholangioscope

Tonozuka and colleagues report the usefulness of a newly developed ultra-thin mother-baby type peroral cholangioscope with a tip external diameter of 2.3 mm for a case of biliary stricture in which conventional peroral cholangioscope insertion was challenging. The novel scope allows simple and low-cost peroral cholangioscopy, making it highly versatile.

Updates in Diagnosis and Endoscopic Management of Cholangiocarcinoma

Cholangiocarcinoma (CCA) is an adenocarcinoma originating from the epithelial cells of the bile ducts/hepatocytes or peribiliary glands. There are three types of cholangiocarcinoma: intrahepatic, perihilar and distal. CCA represents approximately 3% of the gastrointestinal malignancies. The incidence of CCA is higher in regions of the Eastern world compared to the Western countries. There are multiple risk factors associated with cholangiocarcinoma such as liver fluke, primary sclerosing cholangitis, chronic hepatitis B, liver cirrhosis and non-alcoholic fatty liver disease. Endoscopy plays an important role in the diagnosis and management of cholangiocarcinoma. The main endoscopic methods used for diagnosis, biliary drainage and delivering intrabiliary local therapies are endoscopic retrograde cholangiopancreatography and endoscopic ultrasound. The purpose of this review is to analyze the current data found in literature about cholangiocarcinoma, with a focus on the actual diagnostic tools and endoscopic management options.

The Use of Cholangioscopy In the Diagnosis of Indeterminate Biliary Strictures: A Case Report and Review of the Literature

Biliary strictures or narrowing of a portion of the biliary tree can have benign and malignant etiologies. One third of these will originate from iatrogenic injury and these are typically managed endoscopically. We present the case of a 76-year-old man with history of laparoscopic cholecystectomy ten years prior, who presented with one week of jaundice, dark urine, and pruritus. Along with non-invasive biliary imaging, he underwent cholangioscopy during endoscopic retrograde cholangiopancreatography revealing inflammatory-appearing stenosis of the common hepatic duct with embedded suture material. The stenotic area was biopsied using mini forceps and subsequently dilated with a balloon dilator. A plastic biliary stent was placed with improvement in the patient's hepatic function, with final cytology and pathology being negative for malignancy. Cholangioscopy facilitated detailed visual inspection of strictures and biopsies under direct visualization. The visual impression increased the sensitivity of the biopsy and assisted in ruling out malignancy from the most critical portion of the stricture. While timing of cholangioscopy remains to be determined, its use is a valuable tool in the diagnosis of indeterminate biliary strictures.

Deep Learning for Automatic Diagnosis and Morphologic Characterization of Malignant Biliary Strictures Using Digital Cholangioscopy: A Multicentric Study

Digital single-operator cholangioscopy (D-SOC) has enhanced the ability to diagnose indeterminate biliary strictures (BSs). Pilot studies using artificial intelligence (AI) models in D-SOC demonstrated promising results. Our group aimed to develop a convolutional neural network (CNN) for the identification and morphological characterization of malignant BSs in D-SOC. A total of 84,994 images from 129 D-SOC exams in two centers (Portugal and Spain) were used for developing the CNN. Each image was categorized as either a normal/benign finding or as malignant lesion (the latter dependent on histopathological results). Additionally, the CNN was evaluated for the detection of morphologic features, including tumor vessels and papillary projections. The complete dataset was divided into training and validation datasets. The model was evaluated through its sensitivity, specificity, positive and negative predictive values, accuracy and area under the receiver-operating characteristic and precision-recall curves (AUROC and AUPRC, respectively). The model achieved a 82.9% overall accuracy, 83.5% sensitivity and 82.4% specificity, with an AUROC and AUPRC of 0.92 and 0.93, respectively. The developed CNN successfully distinguished benign findings from malignant BSs. The development and application of AI tools to D-SOC has the potential to significantly augment the diagnostic yield of this exam for identifying malignant strictures.

The Role of Cholangioscopy in Biliary Diseases

Endoscopy plays a central role in diagnostic and therapeutic approaches to biliary disease in both benign and malignant conditions. A cholangioscope is an endoscopic instrument that allows for the direct exploration of the biliary tree. Over the years, technology has improved endoscopic image quality and allowed for the development of an operative procedure that can be performed during cholangioscopy. Different types of instruments are available in this context, and they can be used in different anatomical access points according to the most appropriate clinical indication. The direct visualization of biliary mucosa is essential in the presence of biliary strictures of unknown significance, allowing for the appropriate allocation of patients to surgery or conservative treatments. Cholangioscopy has demonstrated excellent performance in discriminating malignant conditions (such as colangiocarcinoma) from benign inflammatory strictures, and more recent advances (e.g., artificial intelligence and confocal laser endomicroscopy) could further increase its diagnostic accuracy. Cholangioscopy also plays a primary role in the treatment of benign conditions such as difficult bile stones (DBSs). In this case, it may not be possible to achieve complete biliary drainage using standard ERCP. Therapeutic cholangioscopy-guided lithotripsy allows for stone fragmentation and complete biliary drainage. Indeed, other complex clinical situations, such as patients with intra-hepatic lithiasis and patients with an altered anatomy, could benefit from the therapeutic role of cholangioscopy. The aim of the present review is to explore the most recent diagnostic and therapeutic advances in the roles of cholangioscopy in the management of biliary diseases.

A real-time interpretable artificial intelligence model for the cholangioscopic diagnosis of malignant biliary stricture (with videos)

BACKGROUND AND AIMS

It is crucial to accurately determine malignant biliary strictures (MBSs) for early curative treatment. This study aimed to develop a real-time interpretable artificial intelligence (AI) system to predict MBSs under digital single-operator cholangioscopy (DSOC).

METHODS

A novel interpretable AI system called MBSDeiT was developed consisting of 2 models to identify qualified images and then predict MBSs in real time. The overall efficiency of MBSDeiT was validated at the image level on internal, external, and prospective testing data sets and subgroup analyses, and at the video level on the prospective data sets; these findings were compared with those of the endoscopists. The association between AI predictions and endoscopic features was evaluated to increase the interpretability.

RESULTS

MBSDeiT can first automatically select qualified DSOC images with an area under the curve (AUC) of .963 and .968 to .973 on the internal testing data set and the external testing data sets, and then identify MBSs with an AUC of .971 on the internal testing data set, an AUC of .978 to .999 on the external testing data sets, and an AUC of .976 on the prospective testing data set, respectively. MBSDeiT accurately identified 92.3% of MBSs in prospective testing videos. Subgroup analyses confirmed the stability and robustness of MBSDeiT. The AI system achieved superior performance to that of expert and novice endoscopists. The AI predictions were significantly associated with 4 endoscopic features (nodular mass, friability, raised intraductal lesion, and abnormal vessels; P < .05) under DSOC, which is consistent with the endoscopists' predictions.

CONCLUSIONS

The study findings suggest that MBSDeiT could be a promising approach for the accurate diagnosis of MBSs under DSOC.

Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model

BACKGROUND

We aimed to develop a convolutional neural network (CNN) model for detecting neoplastic lesions during real-time digital single-operator cholangioscopy (DSOC) and to clinically validate the model through comparisons with DSOC expert and nonexpert endoscopists.

METHODS

In this two-stage study, we first developed and validated CNN1. Then, we performed a multicenter diagnostic trial to compare four DSOC experts and nonexperts against an improved model (CNN2). Lesions were classified into neoplastic and non-neoplastic in accordance with Carlos Robles-Medranda (CRM) and Mendoza disaggregated criteria. The final diagnosis of neoplasia was based on histopathology and 12-month follow-up outcomes.

RESULTS

In stage I, CNN2 achieved a mean average precision of 0.88, an intersection over the union value of 83.24 %, and a total loss of 0.0975. For clinical validation, a total of 170 videos from newly included patients were analyzed with the CNN2. Half of cases (50 %) had neoplastic lesions. This model achieved significant accuracy values for neoplastic diagnosis, with a 90.5 % sensitivity, 68.2 % specificity, and 74.0 % and 87.8 % positive and negative predictive values, respectively. The CNN2 model outperformed nonexpert #2 (area under the receiver operating characteristic curve [AUC]-CRM 0.657 vs. AUC-CNN2 0.794, P < 0.05; AUC-Mendoza 0.582 vs. AUC-CNN2 0.794, P < 0.05), nonexpert #4 (AUC-CRM 0.683 vs. AUC-CNN2 0.791, P < 0.05), and expert #4 (AUC-CRM 0.755 vs. AUC-CNN2 0.848, P < 0.05; AUC-Mendoza 0.753 vs. AUC-CNN2 0.848, P < 0.05).

CONCLUSIONS

The proposed CNN model distinguished neoplastic bile duct lesions with good accuracy and outperformed two nonexpert and one expert endoscopist.

Fluorescence In Situ Hybridization in Primary Diagnosis of Biliary Strictures: A Single-Center Prospective Interventional Study

Background and aims: Diagnosis of the biliary stricture remains a challenge. In view of the low sensitivity of brush cytology (BC), fluorescence in situ hybridization (FISH) has been reported as a useful adjunctive test in patients with biliary strictures. We aimed to determine performance characteristics of BC and FISH individually and in combination (BC + FISH) in the primary diagnosis of biliary strictures. Methods: This single-center prospective study was conducted between April 2019 and January 2021. Consecutive patients with unsampled biliary strictures undergoing first endoscopic retrograde cholangiopancreatography in our institution were included. Tissue specimens from two standardized transpapillary brushings from the strictures were examined by routine cytology and FISH. Histopathological confirmation after surgery or 12-month follow-up was regarded as the reference standard for final diagnosis. Results: Of 109 enrolled patients, six were excluded and one lost from the final analysis. In the remaining 102 patients (60.8% males, mean age 67.4, range 25–92 years), the proportions of benign and malignant strictures were 28 (27.5%) and 74 (72.5%), respectively. The proportions of proximal and distal strictures were 26 (25.5%) and 76 (74.5%), respectively. In comparison to BC alone, FISH increased the sensitivity from 36.1% to 50.7% (p = 0.076) while maintaining similar specificity (p = 0.311). Conclusions: Dual-modality tissue evaluation using BC + FISH showed an improving trend in sensitivity for the primary diagnosis of biliary strictures when compared with BC alone.

A novel peroral digital cholangioscope with a large accessory channel: An experimental study

BACKGROUND/PURPOSE

A peroral cholangioscope (POCS) can allow direct visualization of the biliary mucosa and its use is becoming more widespread due to improvements in functionality, image quality, and operability, as well as the development of related devices. Recently, a novel mother-baby peroral cholangioscope (nMB-POCS) with a large (2-mm) accessory channel has been developed. In this study, we evaluated the feasibility of this novel POCS in a dry simulation and animal model.

METHODS

We evaluated the ease of insertion and maneuverability of the nMB-POCS, the image quality, and the passage of the devices into the accessory channel and into the common bile duct in a dry and live porcine model.

RESULTS

In both models, the nMB-POCS could be easily inserted into the duodenoscope and into the distal bile duct and hilum. The image quality was good, and it was possible to observe the surface structure and the vascular network of the bile duct mucosa in detail.

CONCLUSIONS

The nMB-POCS with its larger accessory channel is expected to improve the efficiency of diagnosis and  treatment, and reduce the procedure time. Clinical studies in patients are warranted.

Cholangioscopy for biliary diseases

PURPOSE OF REVIEW

Cholangioscopy is a mini-invasive endoscopic procedure, which consists in a direct intraductal visualization of the biliary tract. The purpose of this review is to summarize the technique, the clinical applications, as well as future perspectives of cholangioscopy.

RECENT FINDINGS

Numerous technologic advances during the last decades have allowed for an improved utility and functionality, leading to a broader use of this procedure, for diagnostic or therapeutic purposes, in the setting of biliary diseases. Novel tools and emerging indications have been developed and more are yet to come.

SUMMARY

Cholangioscopy can be performed by peroral, percutaneous transhepatic or intra-operative transcystic or transcholedochal access. Clinical applications of cholangioscopy are multiple, ranging from visual impression and optical guided biopsies of indeterminate biliary strictures to the management of difficult stones , guidance before biliary stenting and retrieval of migrated ductal stents. Multiple devices such as lithotripsy probes, biopsy forceps, snares and baskets have been developed to help achieve these procedures successfully.Cholangioscopy has improved the way biliary diseases can be visualized and treated. New technology, accessories, and applications are expected in the future.

Advanced endoscopy meets molecular diagnosis of cholangiocarcinoma

Cholangiocarcinoma remains an aggressive and deadly malignancy that is often diagnosed late. Intrinsic tumour characteristics and the growth pattern of cancer cells contribute to the challenges of diagnosis and chemoresistance. However, establishing an early and accurate diagnosis, and in some instances identifying targetable changes, has the potential to impact survival. Primary sclerosing cholangitis, a chronic cholangiopathy prodromal to the development of a minority of cholangiocarcinomas, poses a particular diagnostic challenge. We present our diagnostic and theranostic approach to the initial evaluation of cholangiocarcinomas, focusing on extrahepatic cholangiocarcinoma. This involves a multipronged strategy incorporating advanced imaging, endoscopic methods, multiple approaches to tissue sampling, and molecular markers. We also provide an algorithm for the sequential use of these tools.

Identification of patients with malignant biliary strictures using a cholangioscopy-based deep learning artificial intelligence (with video)

BACKGROUND AND AIMS

Accurately diagnosing malignant biliary strictures (MBSs) as benign or malignant remains challenging. It has been suggested that direct visualization and interpretation of cholangioscopy images provide greater accuracy for stricture classification than current sampling techniques (ie, brush cytology and forceps biopsy sampling) using ERCP. We aimed to develop a convolutional neural network (CNN) model capable of accurate stricture classification and real-time evaluation based solely on cholangioscopy image analysis.

METHODS

Consecutive patients with cholangioscopy examinations from 2012 to 2021 were reviewed. A CNN was developed and tested using cholangioscopy images with direct expert annotations. The CNN was then applied to a multicenter, reserved test set of cholangioscopy videos. CNN performance was then directly compared with that of ERCP sampling techniques. Occlusion block heatmap analyses were used to evaluate and rank cholangioscopy features associated with MBSs.

RESULTS

One hundred fifty-four patients with available cholangioscopy examinations were included in the study. The final image database comprised 2,388,439 still images. The CNN demonstrated good performance when tasked with mimicking expert annotations of high-quality malignant images (area under the receiver-operating characteristic curve, .941). Overall accuracy of CNN-based video analysis (.906) was significantly greater than that of brush cytology (.625, P = .04) or forceps biopsy sampling (.609, P = .03). Occlusion block heatmap analysis demonstrated that the most frequent image feature for an MBS was the presence of frond-like mucosa/papillary projections.

CONCLUSIONS

This study demonstrates that a CNN developed using cholangioscopy data alone has greater accuracy for biliary stricture classification than traditional ERCP-based sampling techniques.

Current endoscopic approaches to biliary strictures

PURPOSE OF REVIEW

To summarize the current status and future perspectives of the endoscopic management of biliary strictures.

RECENT FINDINGS

In addition to conventional diagnostic modalities, such as cross-sectional imaging and endoscopic ultrasonography (EUS), per-oral cholangioscopy is helpful for indeterminate biliary strictures. It allows direct visualization of the biliary tract and targeted biopsy. For distal malignant biliary obstruction (MBO), a self-expandable metal stent (SEMS) via endoscopic retrograde cholangiopancreatography (ERCP) is a standard of care. EUS-guided biliary drainage (EUS-BD) is an emerging alternative to percutaneous transhepatic biliary drainage in cases with failed ERCP. EUS-BD is also an effective salvage option for perihilar MBO, which can not be managed via ERCP or percutaneous transhepatic biliary drainage. Preoperative drainage is necessary for most jaundiced patients as neoadjuvant chemotherapy is widely administered for resectable and borderline resectable pancreatic cancer, and a SEMS is preferred in this setting, too. For benign biliary strictures, a covered SEMS can improve stricture resolution and reduce the number of endoscopic sessions as compared to plastic stents.

SUMMARY

ERCP and EUS play a central role in the diagnosis and drainage for both malignant and benign biliary strictures.

Identification of endoscopic predictors of biliary malignancy during digital cholangioscopy

OBJECTIVES

Biliary brushings and biopsies obtained during endoscopic retrograde cholangiopancreatography (ERCP) have a low sensitivity for the diagnosis of malignant biliary strictures. While cholangioscopic analysis is useful, visual criteria have not yet been defined. The aim of this study was to identify visual criteria for the diagnosis of indeterminate biliary strictures (IDBS).

METHODS

A multicenter study was conducted based on the analysis of cholangioscopic recordings of IBDS. Diagnostic criteria were identified in a study group and verified in a validation group.

RESULTS

Four criteria were identified to be associated with malignancy, one negatively ("endobiliary material," odds ratio [OR]  0.62, 95% confidence interval [CI] 0.41-0.92) and three positively ("vascularized villous projections," OR  1.52, 95% CI 1.03-2.24; "twisted or dilated vessels," OR  2.18, 95% CI 1.47-3.24; and "dark color of the mucosa," OR  1.82, 95% CI 1.23-2.70). Between two playbacks, the mean (95% CI) sensitivity of the observer's visual diagnosis increased from 66.1% (60-72) to 73.8% (69-78) (P = 0.004); in the second playback, the kappa value for interobserver agreement ranged between 0.36 (color) and 0.56 (endobiliary material), with a significant improvement (P = 0.0031-0.0001) between the first and second playbacks. Blind assessment by endoscopists not involved in this study had a diagnostic accuracy of 73% (71.4-74.5).

CONCLUSION

The four identified cholangioscopic features are easy to implement in clinical practice and have the potential to increase the level of diagnostic confidence during the workup of IDBS.

First interobserver agreement of optical coherence tomography in the bile duct: A multicenter collaborative study

Background and study aims  Optical coherence tomography (OCT) is a new technology available for evaluation of indeterminate biliary strictures. It allows under-the-surface visualization and preliminary studies have confirmed standardized characteristics associated with malignancy. The aim of this study is to evaluate the first interobserver agreement in identifying previously agreed upon OCT criteria and diagnosing of malignant versus benign disease. Patients and methods  Fourteen endoscopists were asked to review an atlas of reference clips and images of eight criteria derived from expert consensus A total of 35 de-identified video clips were then evaluated for presence of the eight criteria and for final diagnosis of malignant versus benign using the atlas as reference Intraclass correlation (ICC) analysis was done to evaluate interrater agreement. Results  Clips of 23 malignant lesions and 12 benign lesions were scored. Excellent interobserver agreement was seen with dilated hypo-reflective structures (0.85) and layering effacement (0.89); hyper-glandular mucosa (0.76), intact layering (0.81), and onion-skin layering (0.77); fair agreement was seen with scalloping (0.58), and thickened epithelium (0.4); poor agreement was seen with hyper-reflective surface (0.36). The diagnostic ICC for both neoplastic (0.8) and non-neoplastic (0.8) was excellent interobserver agreement. The overall diagnostic accuracy was 51 %, ranging from 43 % to 60 %. Conclusions  Biliary OCT is a promising new modality for evaluation of indeterminate biliary strictures. Interobserver agreement ranged from fair to almost perfect on eight previously identified criteria. Interobserver agreement for malignancy diagnosis was substantial (0.8). Further studies are needed to validate this data.

The role of pancreatoscopy in the diagnostic work-up of intraductal papillary mucinous neoplasms: a systematic review and meta-analysis

BACKGROUND

Confirming the diagnosis, invasiveness, and disease extent of intraductal papillary mucinous neoplasms (IPMNs) of the pancreas is challenging. The aim of this study was to summarize the literature on the efficacy and safety of peroral pancreatoscopy (POP) in the diagnosis of IPMN, including the impact of pre- and intraoperative POP on the management of IPMN.

METHODS

The EMBASE, Medline Ovid, Web of Science, Cochrane CENTRAL, and Google Scholar databases were systematically searched for articles. Eligible articles investigated cohorts of patients who underwent POP for (suspected) IPMN.

RESULTS

25 articles were identified and included in this review; with 22 of these reporting on the diagnostic yield of POP in IPMN and 11 reporting on the effect of pre- or intraoperative POP on clinical decision-making. Cannulation and observation rates, and overall diagnostic accuracy were high across all studies. Frequently reported visual characteristics of IPMN were intraductal fish-egg-like lesions, hypervascularity, and granular mucosa. Overall, the adverse event rate was 12 %, primarily consisting of post-endoscopic retrograde cholangiopancreatography pancreatitis, with a pooled rate of 10 %, mostly of mild severity. Regarding the impact of POP on clinical decision-making, POP findings altered the surgical approach in 13 %-62 % of patients.

CONCLUSION

POP is technically successful in the vast majority of patients with (suspected) IPMN, has a consistently high diagnostic accuracy, but an adverse event rate of 12 %. Data on intraoperative pancreatoscopy are scarce, but small studies suggest its use can alter surgical management. Future studies are needed to better define the role of POP in the diagnostic work-up of IPMN.

New technologies for indeterminate biliary strictures

An early and accurate diagnosis of biliary strictures yields optimal patient outcomes; however, endoscopic retrograde cholangiopancreatography (ERCP) with cytobrush/biopsy forceps has low sensitivity with a high number of false negatives. Various attempts to improve the accuracy of diagnosing indeterminate biliary strictures though ERCP-guided specimen acquisition have been proposed, such as with the use of fluorescence in situ hybridization, an endoscopic scraper, and the wire-grasping method, with modest to large improvements in sensitivity. Direct visualization of the biliary tree during peroral cholangioscopy has shown high sensitivity and specificity for the differentiation of neoplastic and non-neoplastic biliary lesions; however, there is no consensus on the visual characteristics of neoplastic lesions and moderate agreement between observers. Peroral cholangioscopy system (POCS)-guided specimen acquisition using forceps has shown inferior sensitivity compared to the visual characteristics; however, the specificity remains high. Optimal specimen processing with onsite evaluations and touch imprint cytology have been shown to improve the sensitivity and accurately diagnose nearly 90% of patients. In vivo evaluations of biliary strictures with probe-based confocal laser endomicroscopy have demonstrated high sensitivity with modest specificity for malignant biliary strictures. Optical computed tomography described reproductible criteria for malignancy detection in biliary strictures, increasing the sensitivity during ERCP evaluations. Differentiating benign causes from malignant causes of biliary strictures is a challenging task in clinical practice, with various concerns that still need to be addressed. Efforts should be made to define each diagnostic method's role in the evaluation of indeterminate biliary strictures.

Digital Cholangioscopic Interpretation: When North Meets the South

BACKGROUND

Digital single-operator cholangioscopy (DSOC) (SpyGlass DS™, Boston Scientific, MA, USA) allows for high-definition imaging of the biliary tree. The superior visualization has led to the development of two different sets of criteria to evaluate and classify indeterminate biliary strictures: the Monaco criteria and the criteria in Carlos Robles-Medranda's publication (CRM). Our objective was to assess the interrater agreement (IA) of DSOC interpretation for indeterminate biliary strictures using the two newly published criteria.

METHODS

Forty de-identified DSOC video recordings were sent to 15 interventional endoscopists with experience in cholangioscopy. They were asked to score the videos based on the presence of Monaco Classification criteria: stricture, lesion, mucosal changes, papillary projections, ulceration, white linear bands or rings, and vessels. Next, they scored the videos using CRM criteria: villous pattern, polypoid pattern, inflammatory pattern, flat pattern, ulcerate pattern and honeycomb pattern. The endoscopists then diagnosed the recordings as neoplastic or non-neoplastic based on the criteria. Intraclass correlation (ICC) analysis was done to evaluate interrater agreement for both criteria set and final diagnosis.

RESULTS

Recordings of 26 malignant lesions and 14 benign lesions were scored. The IA using both the Monaco criteria and CRM criteria ranged from poor to excellent (range 0.1-0.76) and (range 0.1-0.62), respectively. Within the Monaco criteria, IA was excellent for lesion (0.75) and fingerlike papillary projections (0.74); good for tortuous vessels (0.7), mucosal features (0.62), uniform papillary projections (0.53), and ulceration (0.58); and fair for white linear bands (0.4). Within the CRM criteria, the IA was good for villous pattern (0.62), flat pattern (0.62), and honeycomb pattern; fair for ulcerated pattern (0.56), polypoid pattern (0.52) and inflammatory pattern (0.54). The diagnostic IA using Monaco criteria was good (0.65), while the diagnostic IA using CRM was fair (0.58). The overall diagnostic accuracy using the Monaco classification was 61% and CRM criteria were 57%.

CONCLUSION

The IOA and accuracy rate of DSOC using visual criteria from both Monaco Criteria and CRM are similar. However, some criteria from both sets suffer from poor IA, thus affecting the overall diagnostic accuracy. More formal training and refinements in visual criteria with additional validation are needed to improve diagnostic accuracy.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT02166099.

Automatic detection of tumor vessels in indeterminate biliary strictures in digital single-operator cholangioscopy

Background and study aims  Indeterminate biliary strictures pose a significative clinical challenge. Dilated, irregular, and tortuous vessels, often described as tumor vessels, are frequently reported in biliary strictures with high malignancy potential during digital single-operator cholangioscopy (D-SOC). In recent years, the development of artificial intelligence (AI) algorithms for application to endoscopic practice has been intensely studied. We aimed to develop an AI algorithm for automatic detection of tumor vessels (TVs) in D-SOC images. Patients and methods  A convolutional neural network (CNN) was developed. A total of 6475 images from 85 patients who underwent D-SOC (Spyglass, Boston Scientific, Marlborough, Massachusetts, United States) were included. Each frame was evaluated for the presence of TVs. The performance of the CNN was measured by calculating the area under the curve (AUC), sensitivity, specificity, positive and negative predictive values. Results  The sensitivity, specificity, positive predictive value, and negative predictive value were 99.3 %, 99.4 %, 99.6% and 98.7 %, respectively. The AUC was 1.00. Conclusions  Our CNN was able to detect TVs with high accuracy. Development of AI algorithms may enhance the detection of macroscopic characteristics associated with high probability of biliary malignancy, thus optimizing the diagnostic workup of patients with indeterminate biliary strictures.

Peroral cholangioscopy: Update on the state-of-the-art

Peroral cholangioscopy (POC) is an endoscopic procedure that allows direct intraductal visualization of the biliary tract. POC has emerged as a vital tool for indeterminate biliary stricture evaluation and treatment of difficult biliary stones. Over several generations of devices, POC has fulfilled additional clinical needs where other diagnostic or therapeutic modalities have been inadequate. With adverse event rates comparable to standard endoscopic retrograde cholangioscopy and unique technical attributes, the role of POC is likely to continue expand. In this frontiers article, we highlight the existing and growing clinical applications of POC as well as areas of ongoing research.

Improving Diagnostic Yield in Indeterminate Biliary Strictures

Indeterminate biliary strictures are defined as a narrowing of the bile duct that cannot be differentiated as malignant or benign after performing cross-sectional imaging and an ERCP. Identifying the etiology of a bile duct stricture is the single most important step in determining whether a complex and potentially morbid surgical resection is warranted. Due to this diagnostic and therapeutic dilemma, new technologies, laboratory tests, and procedures are emerging to solve this problem.

Consensus guidelines on the role of cholangioscopy to diagnose indeterminate biliary stricture

BACKGROUND

Indeterminate strictures pose a therapeutic dilemma. In recent years, cholangioscopy has evolved and the availability of cholangioscopy has increased. However, the position of cholangioscopy in the diagnostic algorithm to diagnose malignancy have not been well established. We aim to develop a consensus statement regarding the clinical role of cholangioscopy in the diagnosis of indeterminate biliary strictures.

METHODS

The international experts reviewed the evidence and modified the statements using a three-step modified Delphi method. Each statement achieves consensus when it has at least 80% agreement.

RESULTS

Nine final statements were formulated. An indeterminate biliary stricture is defined as that of uncertain etiology under imaging or tissue diagnosis. When available, cholangioscopic assessment and guided biopsy during the first round of ERCP may reduce the need to perform multiple procedures. Cholangioscopy are helpful in diagnosing malignant biliary strictures by both direct visualization and targeted biopsy. The absence of disease progression for at least 6 months is supportive of non-malignant etiology. Direct per-oral cholangioscopy provides the largest accessory channel, better image definition, with image enhancement but is technically demanding. Image enhancement during cholangioscopy may increase the diagnostic sensitivity of visual impression of malignant biliary strictures. Cholangioscopic imaging characteristics including tumor vessels, papillary projection, nodular or polypoid mass, and infiltrative lesions are highly suggestive for neoplastic/malignant biliary disease. The risk of cholangioscopy related cholangitis is higher than in standard ERCP, necessitating prophylactic antibiotics and ensuring adequate biliary drainage. Per-oral cholangioscopy may not be the modality of choice in the evaluation of distal biliary strictures due to inherent technical difficulties.

CONCLUSION

Evidence supports that cholangioscopy has an adjunct role to abdominal imaging and ERCP tissue acquisition in order to evaluate and diagnose indeterminate biliary strictures.

Endoscopic Diagnosis of Biliary Stricture Combined with Digital Cholangioscope: A Case Series

The endoscopic diagnosis of biliary tract lesions is applied as a non-invasive method; however, its diagnostic accuracy is not yet high. Moreover, digital cholangioscopy is used for directly visualizing the inside of the bile duct, resulting in a more precise biopsy. We present the case series of the outcomes of diagnosis using digital cholangioscopy in patients who underwent cholangioscopy for the evaluation of biliary stenosis in our department between January 2014 and March 2021. The controls were those who underwent a biopsy for biliary stenosis with conventional endoscopic retrograde cholangiopancreatography (ERCP). Background data for each case were collected, and the clinical outcomes by biopsy were evaluated, focusing on the accuracy of the diagnosis. Cholangioscopy was performed in 15 cases, while a conventional biopsy by ERCP was performed in 172 cases. Nine of 15 cases (60.0%) were diagnosed with cholangiocarcinoma. The number of specimens obtained through conventional ERCP and cholangioscopy was 2.5 ± 1.3 and 3.3 ± 1.5, respectively (p = 0.043). The diagnostic accuracy of conventional ERCP and cholangioscopy were 65.7% (113 of 172 cases) and 100%, respectively, which was significantly higher in the group with cholangioscopy. Digital cholangioscopy is useful when the diagnosis of the biliary stricture using the conventional ERCP method is difficult.

Choledochoscopy: An update

Choledochoscopy, or cholangioscopy, is an endoscopic procedure for direct visualization within the biliary tract for diagnostic or therapeutic purposes. Since its conception in 1879, many variations and improvements are made to ensure relevance in diagnosing and managing a range of intrahepatic and extrahepatic biliary pathologies. This ranges from improved visual impression and optical guided biopsies of indeterminate biliary strictures and clinically indistinguishable pathologies to therapeutic uses in stone fragmentation and other ablative therapies. Furthermore, with the evolving understanding of biliary disorders, there are significant innovative ideas and techniques to fill this void, such as nuanced instances of biliary stenting and retrieving migrated ductal stents. With this in mind, we present a review of the current advancements in choledo-choscopy with new supporting evidence that further delineates the role of choledochoscopy in various diagnostic and therapeutic interventions, complications, limitations and put forth areas for further study.

Clinical practice patterns in indirect peroral cholangiopancreatoscopy: outcome of a European survey

Background and aims  Indirect peroral cholangiopancreatoscopy (IPOC) is a relatively new diagnostic and therapeutic tool for biliopancreatic diseases. This international survey aimed to evaluate clinical practice patterns in IPOC among endoscopists in Europe. Methods  An online survey was developed comprising 66 questions on the use of IPOC. Questions were grouped into four domains. The survey was sent to 369 endoscopists who perform IPOC. Results  86 respondents (23.3 %) from 21 different countries across Europe completed the survey. The main indications for cholangioscopy were determination of biliary strictures (85 [98.8 %]) and removal of common bile duct or intrahepatic duct stones (79 [91.9 %]), accounting for an estimated use of 40 % (interquartile range [IQR] 25-50) and 40 % (IQR 30-60), respectively, of all cases undergoing cholangioscopy. Pancreatoscopy was mainly used for removal of pancreatic duct stones (68/76 [89.5 %]), accounting for an estimated use of 76.5 % (IQR 50-95) of all cases undergoing pancreatoscopy. Only 13/85 respondents (15.3 %) had an institutional standardized protocol for targeted cholangioscopy-guided biopsy sampling. IPOC with lithotripsy was used as first-line treatment in selected patients with bile duct stones or pancreatic stones by 24/79 (30.4 %) and 53/68 (77.9 %) respondents, respectively. Conclusions  This first European survey on the clinical practice of IPOC demonstrated wide variation in experience, indications, and techniques. These results emphasize the need for prospective studies and development of an international consensus guideline to standardize the practice and quality of IPOC.

Automatic Identification of Papillary Projections in Indeterminate Biliary Strictures Using Digital Single-Operator Cholangioscopy

INTRODUCTION

Characterization of biliary strictures is challenging. Papillary projections (PP) are often reported in biliary strictures with high malignancy potential during digital single-operator cholangioscopy. In recent years, the development of artificial intelligence (AI) algorithms for application to endoscopic practice has been intensely studied. We aimed to develop an AI algorithm for automatic detection of PP in digital single-operator cholangioscopy images.

METHODS

A convolutional neural network (CNN) was developed. Each frame was evaluated for the presence of PP. The CNN's performance was measured by the area under the curve, sensitivity, specificity, and positive and negative predictive values.

RESULTS

A total of 3,920 images from 85 patients were included. Our model had a sensitivity and specificity 99.7% and 97.1%, respectively. The area under the curve was 1.00.

DISCUSSION

Our CNN was able to detect PP with high accuracy. Future development of AI tools may optimize the macroscopic characterization of biliary strictures.

Tips and tricks for the diagnosis and management of biliary stenosis-state of the art review

Biliary stenosis may represent a diagnostic and therapeutic challenge resulting in a delay in diagnosis and initiation of therapy due to the frequent difficulty in distinguishing a benign from a malignant stricture. In such cases, the diagnostic flowchart includes the sequential execution of imaging techniques, such as magnetic resonance, magnetic resonance cholangiopancreatography, and endoscopic ultrasound, while endoscopic retrograde cholangiopancreatography is performed to collect tissue for histopathological/cytological diagnosis or to treat the stenosis by insertion of stent. The execution of percutaneous transhepatic drainage with subsequent biopsy has been shown to increase the possibility of tissue diagnosis after failure of the above techniques. Although the diagnostic yield of histopathology and imaging has increased with improvements in endoscopic ultrasound and peroral cholangioscopy, differential diagnosis between malignant and benign stenosis may not be easy in some patients, and strictures are classified as indeterminate. In these cases, a multidisciplinary workup including biochemical marker assays and advanced technologies available may speed up a diagnosis of malignancy or avoid unnecessary surgery in the event of a benign stricture. Here, we review recent advancements in the diagnosis and management of biliary strictures and describe tips and tricks to increase diagnostic yields in clinical routine.