Endoscopic Ultrasound-guided Needle-based Confocal Laser Research Articles

Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy for pancreatic cystic lesions: current status and future prospects.

Pancreatic cystic lesions (PCLs) have increased in prevalence due to the increased usage and advancements in cross-sectional abdominal imaging. Current diagnostic techniques cannot distinguish between PCLs requiring surgery, close surveillance, or expectant management. This has increased the morbidity and healthcare costs from inappropriately aggressive and conservative management strategies. Endoscopic ultrasound (EUS) needle-based confocal laser endomicroscopy (nCLE) allows for microscopic examination and delineation of the surface epithelium of PCLs. Landmark studies have identified characteristics distinguishing various types of PCLs, confirmed the high diagnostic yield of EUS-nCLE (especially for PCLs with an equivocal diagnosis), and shown that EUS-nCLE helps to change management and reduce healthcare costs. Refining procedure technique and reducing procedure length have improved the safety of EUS-nCLE. The utilization of artificial intelligence and its combination with other EUS-based advanced diagnostic techniques would further improve the results of EUS-based PCL diagnosis. A structured training program and device improvements to allow more complete mapping of the pancreas cyst epithelium will be crucial for the widespread adoption of this promising technology.

Deep-Learning-Enabled Computer-Aided Diagnosis in the Classification of Pancreatic Cystic Lesions on Confocal Laser Endomicroscopy.

Accurate classification of pancreatic cystic lesions (PCLs) is important to facilitate proper treatment and to improve patient outcomes. We utilized the convolutional neural network (CNN) of VGG19 to develop a computer-aided diagnosis (CAD) system in the classification of subtypes of PCLs in endoscopic ultrasound-guided needle-based confocal laser endomicroscopy (nCLE). From a retrospectively collected 22,424 nCLE video frames (50 videos) as the training/validation set and 11,047 nCLE video frames (18 videos) as the test set, we developed and compared the diagnostic performance of three CNNs with distinct methods of designating the region of interest. The diagnostic accuracy for subtypes of PCLs by CNNs with manual, maximal rectangular, and U-Net algorithm-designated ROIs was 100%, 38.9%, and 66.7% on a per-video basis and 88.99%, 73.94%, and 76.12% on a per-frame basis, respectively. Our per-frame analysis suggested differential levels of diagnostic accuracy among the five subtypes of PCLs, where non-mucinous PCLs (serous cystic neoplasm: 93.11%, cystic neuroendocrine tumor: 84.31%, and pseudocyst: 98%) had higher diagnostic accuracy than mucinous PCLs (intraductal papillary mucinous neoplasm: 84.43% and mucinous cystic neoplasm: 86.1%). Our CNN demonstrated superior specificity compared to the state-of-the-art for the classification of mucinous PCLs (IPMN and MCN), with high specificity (94.3% and 92.8%, respectively) but low sensitivity (46% and 45.2%, respectively). This suggests the complimentary role of CNN-enabled CAD systems, especially for clinically suspected mucinous PCLs.

In vivo real-time diagnosis of endoscopic ultrasound-guided needle-based confocal laser endomicroscopy in gastric subepithelial lesions.

The effect of real-time analysis of needle-based confocal laser endomicroscopy (nCLE) for gastric subepithelial lesions (SELs) on the diagnostic value is unclear. The study aimed to investigate the diagnostic efficacy of real-time nCLE for gastric SELs and to assess the technical aspects and safety of real-time nCLE. Consecutive patients with gastric SELs ≥1cm were prospectively investigated by endoscopic ultrasound (EUS), followed by nCLE. During EUS-nCLE, real-time nCLE diagnosis was made by an expert endoscopist. The procedure-relative adverse events were assessed and recorded. One-month washout period later, nCLE videos were reviewed off-line by the same endoscopist. The nCLE diagnoses were compared with corresponding pathological results. Additionally, image quality and interobserver agreements for the criteria were evaluated by three experienced endomicroscopists. Except for one failing to be punctured, 60 patients completed EUS-nCLE procedures successfully. Real-time nCLE had high diagnostic accuracies of ≥88.3% for gastric SELs. There were no significant differences between real-time and off-line nCLE diagnoses for gastric SELs (P>0.05). The overall accuracy of real-time nCLE for diagnosis of gastric SELs was 86.7%. There were no procedure-relative adverse events occurred. In addition, the mean image quality score was 3.6 (1=poor and 5=excellent). The interobserver agreement was "almost perfect" for ectopic pancreas and "substantial" for gastrointestinal stromal tumor, leiomyoma, and carcinoma. Endoscopic ultrasound-nCLE could provide in vivo real-time diagnostic imaging with a high diagnostic accuracy. Meanwhile, real-time nCLE was feasible and had a satisfactory safety profile.

Endoscopic Ultrasound-guided Needle-based Confocal Laser Endomicroscopy: Appraisal Concerning In-vivo Imaging of Intraductal Papillary Mucinous Neoplasm

Differential diagnosis between benign and potentially malignant cystic pancreatic lesions may be difficult. Previously we have compared cyst fluid serine protease inhibitor Kazal type I (SPINK1) with some traditionally used tumour markers (amylase, CEA, Ca19-9) and found that it may be a new promising maker in the differential diagnosis of cystic pancreatic lesions. In the present study, we focused on cyst fluid SPINK1 levels in benign and potentially malignant cystic pancreatic lesions.Sixty-one patients operated on for cystic pancreatic lesion in Tampere University Hospital, Finland and in Verona University Hospital, Italy, were included. Cyst fluid was aspirated during surgery, stored at −70 °C, and analysed with immunofluorometric assay for SPINK1. The final diagnosis was acute pancreatitis with fluid collection (Acute FC) in 4 patients, chronic pseudocyst (PS) in 17 patients, serous cystadenoma (SCA) in 7 patients, mucinous cystadenoma (MCA) in 21 patients and intraductal papillary-mucinous neoplasm (IPMN) in 12 patients (9 main/mixed duct type and 3 branch duct type).The acute FC patients had high SPINK1 levels. Among chronic cysts, SPINK1 levels were significantly higher in patients with potentially malignant cysts (main/mixed duct IPMN and MCA) than with benign cysts (side branch IPMN and SCA), (median and range, [480 (13–3602) vs. 18 (0.1–278) μg/L]; p < 0.0001). In the subcohort of 24 patients with <3 cm chronic cyst, cyst fluid SPINK 1 levels were significantly lower in SCA or side branch IPMN (3 [2–116] μg/L) than in main duct IPMN or MCA (638 [66–3602] μg/L; p = 0.018). The best sensitivity and specificity to differentiate any size MCA or main/mixed type IPMN from SCA or side branch IPMN were 85% and 84% (AUC 0.94; cut-off value 118 μg/L). The best sensitivity and specificity to differentiate <3 cm MCA or main duct IPMN from SCA or side branch IPMN were 93% and 89% (AUC 0.98; cut-off value 146 μg/L).Cyst fluid SPINK1 may be a possible marker in the differential diagnosis of benign and potentially malignant cystic pancreatic lesions.

Video Comment on Ming-Ming Zhang et al.

Ming-Ming Zhang et al. Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy for diagnosis of gastric subepithelial tumors: a pilot study

Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy in pancreatic neoplasms: A single-center experience in China

Objective:The objective of the study is to investigate the application of endoscopic ultrasound-guided needle-based confocal laser endomicroscopy (EUS-nCLE) in the diagnosis of pancreatic neoplasms.Methods:Patients with pancreatic neoplasms were diagnosed by endoscopic ultrasound and punctured by 19G needle; Cellvizio AQ-Flex19 confocal microprobe was implanted through the needle. The diagnostic yield and complication were evaluated and compared with pathology.Results:A total of 28 patients successfully underwent EUS-nCLE examination, including serous cystadenoma (n = 5), mucinous cystadenoma (n = 3), intraductal papillary mucinous neoplasms (n = 3), pseudocyst (n = 1), ductal adenocarcinoma (n = 10), neuroendocrine tumors (1), solid pseudopapillary tumor (n = 2), chronic pancreatitis (n = 2), and lymphoma (n = 1). High-quality images were obtained in all the patients. The diagnostic yield in 26 patients with pathology was 73.1% (19/26) and the specificity of serous cystic neoplasm (SCN) and intraductal papillary mucinous neoplasm (IPMN) was 100% (7/7). The complications, mostly pancreatitis and intracystic hemorrhage, were occurred in 10.7% (3/28) patients.Conclusion:EUS-nCLE is a safe and feasible method in the diagnosis of pancreatic neoplasms and shows high specificity in SCN and IPMN.

Can endoscopic ultrasound-guided needle-based confocal laser endomicroscopy replace fine-needle aspiration for pancreatic and mediastinal diseases?

New applications of confocal laser endomicroscopy (CLE) have been developed, such as needle-based CLE (nCLE) for pancreatic masses, pancreatic cystic tumors, and lymph nodes. nCLE is feasible during endoscopic ultrasound (EUS) examination, and preliminary results are very encouraging and suggest this technology may be used in future as a useful adjunct in cases of inconclusive EUS-guided fine-needle aspiration. The aim of this paper is to give an update in this new technology and to define its place in the diagnosis of pancreatic masses and mediastinal diseases.

Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy for diagnosis of solid pancreatic lesions

Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy for diagnosis of solid pancreatic lesions

Últimos avances sobre los tumores pancreáticos

Pancreatic cancer continues to have a bleak prognosis. Hardly any therapeutic advances have been made in the last few years and consequently most efforts have focused on preventing its development and on diagnosing precursor lesions. In this regard, the use of statins as a preventive factor and the implementation of screening programmes in high-risk patients are gaining ground. In the field of treatment, there is greater focus on the role of neoadjuvant therapy in pancreatic cancer and on a multimodal approach to the disease, with few advances in effective novel therapies. Most studies concerned cystic tumours of the pancreas, especially intraductal mucinous papillary tumour, with its known potential for malignant transformation. Multiple studies were devoted to validation of the 2012 Fukuoka international guidelines and the highly controversial 2015 AGA guidelines. Notable among these studies were those demonstrating the suboptimal positive predictive value and questioning important aspects of the guidelines, such as discontinuation of follow-up or the criteria for surgical referral. Notable among diagnostic procedures were cystoscopy and endoscopic ultrasound-guided needle-based confocal laser endomicroscopy as the most promising techniques due to their high efficacy and negative predictive value in detecting mucinous cystic lesions. There were also a large number of studies on the natural history of intraductal papillary mucinous tumours, which help deepen knowledge of these entities and the search for predictive factors of cancer development.

Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy for diagnosis of solid pancreatic lesions (ENES): a pilot study.

Background and study aims: Endoscopic ultrasound-guided needle-based confocal laser endomicroscopy (EUS-nCLE) has been shown to aid in the diagnosis of cystic pancreatic lesions. This is a pilot project to study its findings in patients with solid pancreatic lesions (SPLs) with a prospective single-blinded study design. Methods: Patients with SPLs undergoing trans-gastric EUS fine needle aspiration (EUS-FNA) from July 2013 to March 2014 were prospectively enrolled. The nCLE diagnoses were compared with the final diagnoses. Researchers learned about the EUS-nCLE findings from previously published studies and applied it to diagnose SPLs. In the meantime, the findings were recorded. Results: In total, 22 patients were recruited (mean age 62.7 years, SD 13.8 years; 14 men and eight women). The mean maximal tumor diameter was 36.0 mm (SD 10.9 mm). EUS-nCLE yielded satisfactory images in all patients during the first EUS procedure and diagnosed benign and malignant SPLs in 3 and 19 patients, respectively. Final diagnoses of malignant SPLs were made in 19 patients. Benign SPLs were eventually diagnosed in three patients, with confirmed the cytology and disease stability during the 12-month follow-up period. At the end of the project, based on the results of this current study, EUS-nCLE findings for malignant SPLs were dark clumping with or without dilated vessels (> 40 μm). There were two criteria for diagnosing benign lesions which were white fibrous bands and normal acini cells. The accuracy rate of EUS-nCLE was 90.9 % (20/22). One falsely diagnosed malignant SPL was an inflammatory mass from a recent acute pancreatitis. Another one with a pancreatic neuroendocrine tumor presenting with a symptomatic pseudocyst was incorrectly diagnosed as an inflammatory mass. This was likely from sampling error of the EUS-nCLE probe in an inflammatory area. Only one patient had post EUS-FNA bleeding but did not require a blood transfusion. The inter-observer agreement among three blinded endoscopists was almost perfect (Kappa 0.82). Conclusion: EUS-nCLE is a promising technique for the diagnosis of SPLs with good inter-observer agreement.Study registration‎: TCTR20140402001