Classification Of Pancreatic Cysts Research Articles

Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists.

A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist. In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis. 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist. Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.

Discrimination of mucinous pancreatic cysts using an enzymatic turnover assay to improve clinical diagnostic accuracy.

4151 Background: One impact of medical imaging technology has been an approximately 3-fold increase in the incidental detection of pancreatic cysts during routine clinical examinations. To reduce burden on the healthcare system and patients, clinicians desire accurate classification of pancreatic cysts into benign non-mucinous or potentially malignant, mucinous populations. Using EUS-FNA, fluid from these cysts can provide molecular biomarkers of predictive value. However, current in vitro diagnostics lack the desired sensitivity and specificity for clinicians to accurately stratify patients for risk of pre-malignant cancers. This situation can be improved by introducing new biomarkers and novel assay platforms. An enzymatic biomarker, pepsin C, has shown high accuracy for diagnosing mucinous cysts. The use of enzymatic activity assays is applicable to clinical workflows without disruption of current standards of care. Methods: A pepsin C activity assay using a magnetic bead-based platform was developed, with both fluorescent and surface-enhanced Raman spectroscopy (SERS) readouts. The assay platform utilizes selective peptide substrates, and a dimeric Rhodamine-6G-based dye, which allows ultrasensitive detection and significantly decreases the sample volume requirement for analysis, down to 1 µL of cyst fluid. The dye-labeled substrate is immobilized on magnetic beads and reacted with enzyme-containing samples to produce a quantitative assay signal that is standardized and expressed in true enzyme activity units. Results: While both readouts were quantitative and produced linear standard curves, SERS-based analysis was more robust against established biological matrix effects than fluorescence. Nevertheless, both assay modes successfully differentiated mucinous and non-mucinous cysts in a retrospective cohort of 69 cyst fluid samples. Compared with the standard of care CEA assay, this activity-based assay displays much improved sensitivity in diagnosing mucinous pancreatic cysts (Table). Conclusions: This pepsin c activity assay differentiates between mucinous and non-mucinous cysts better than the CEA assay and provides a quantifiable standardized readout. This work establishes a path to a true rule-out assay enabling clinicians to better stratify patients into low risk vs. potential malignancy thus impacting treatment and monitoring plans. [Table: see text]

Endoscopic ultrasound-guided through-the-needle microforceps biopsy in the evaluation of pancreatic cystic lesions: a multicenter study.

Background and study aims Accurate diagnosis and classification of pancreatic cysts (PCs) remains a challenge. The aims of this study were to: (1) evaluate the safety and technical success of a novel microforceps for EUS-guided through-the-needle biopsy (TTNB) of PCs; and (2) assess its diagnostic yield for mucinous PCs when compared to FNA cyst fluid analysis and cytology. Patients and methods This was a multicenter retrospective analysis of 47 patients who underwent EUS-FNA and TTNB for PCs between January 2014 and June 2017. Technical success was defined as acquisition of a specimen adequate for cytologic or histological evaluation. Cyst fluid carcinoembryonic antigen (CEA) was used to initially categorize cysts as non-mucinous (CEA < 192 ng/mL) or mucinous (CEA ≥ 192 ng/mL). Final diagnosis was based on identifiable mucinous pancreatic cystic epithelium on cytology, microforceps histology and/or surgical histology when available. Results Forty-seven patients with PCs (mean size 30.7 mm) were included. TTNB was successfully performed in 46 of 47 (97.9 %). Technical success was significantly lower with FNA (48.9 %) compared to TTNB (85.1 %) ( P < .001). For cysts with insufficient amount of fluid for CEA (n = 19) or CEA < 192 ng/mL, the cumulative incremental diagnostic yield of a mucinous PC was significantly higher with TTNB vs. FNA (52.6 % vs 18.4 %; P = .004). TTNB alone (34.4 %) diagnosed more mucinous PCs than either CEA ≥ 192 ng/mL alone (6.3 %) or when combined with FNA cytology (9.4 %). One episode of self-limited bleeding (2.1 %) and one of pancreatitis (2.1 %) occurred. Conclusions EUS-TTNB is safe and effective for evaluating PCs. TTNB may help increase the diagnostic yield of mucinous PCs.

Classification of Pancreatic Cysts in Computed Tomography Images Using a Random Forest and Convolutional Neural Network Ensemble.

There are many different types of pancreatic cysts. These range from completely benign to malignant, and identifying the exact cyst type can be challenging in clinical practice. This work describes an automatic classification algorithm that classifies the four most common types of pancreatic cysts using computed tomography images. The proposed approach utilizes the general demographic information about a patient as well as the imaging appearance of the cyst. It is based on a Bayesian combination of the random forest classifier, which learns subclass-specific demographic, intensity, and shape features, and a new convolutional neural network that relies on the fine texture information. Quantitative assessment of the proposed method was performed using a 10-fold cross validation on 134 patients and reported a classification accuracy of 83.6%.

Interobserver Agreement in the Classification of Pancreatic Cysts With Needle-Based Confocal Laser Endomicroscopy

Introduction: Needle-based confocal laser endomicroscopy (nCLE) may serve as an accurate and clinically relevant adjunct in classifying pancreatic cysts. The question remains whether clinician interpretation of nCLE images is consistent enough to render nCLE a precise tool. The aim of this study was to determine our institutional interobserver agreement for interpretation of nCLE images of pancreatic cysts. Methods: All pancreatic cyst EUS-FNA cases with nCLE from 3/2014-4/2015 at a large tertiary medical center were included. 3 interventional endoscopists who independently had performed the cases reviewed all nCLE images in a blinded manner and classified each case as serous cystadenoma (SCA), intraductal papillary mucinous neoplasm (IPMN), neuroendocrine tumor (NET), or other. Each clinician designated diagnostic certainty (certain/uncertain) and image quality (poor/fair/good). The primary outcome was interobserver agreement in pancreatic cyst classification, as calculated by the Fleiss kappa in SAS 9.3. Secondary outcomes were accuracy of individual and group diagnosis, as compared to overall cyst clinical impression as previously determined by the performing endoscopist, based upon radiology studies, EUS, nCLE, CEA/amylase, cytology and surgical pathology.Table 1: Interobserver Agreement in Pancreatic Cyst Evaluation with nCLEResults: 14 cases were included. Interobserver agreement was “fair to good” (kappa=0.65, p=0.003). nCLE diagnosis by the performing endoscopist was accurate in 11/14 cases. Blinded accuracy was 43%, 50%, and 57%, respectively. Majority consensus, with at least 2 of 3 clinicians independently achieving the same diagnosis, occurred in 12/14 cases. Consensus accuracy was 58% and increased to 67% in cases of unanimous agreement. There was little correlation between consensus diagnostic accuracy and certainty. In all instances of unanimous agreement, regardless of diagnostic accuracy, there was high level of certainty. Image quality appeared to have limited impact on achieving consensus or the accuracy of consensus diagnosis. Conclusion: Our prior work has shown that nCLE enhances accuracy in classifying pancreatic cysts and is clinically relevant in preventing referral for surgical resection. Interobserver agreement is high demonstrating the reliability of this tool, yet both individual and group diagnostic accuracy fell short of that of the performing endoscopist, indicating that clinical context is vital to nCLE's utility. Clinicians would benefit from greater training with nCLE to improve the yield of this new technology.

Abstract B33: Classification of pancreatic cysts in a minority population through cytokine profiling of cyst fluid fine-needle aspirate

Abstract Pancreatic cyst detection rate has increased due to the widespread use of cross-sectional imaging. Pancreatic cysts can be divided pathologically into pseudocysts, non-neoplastic cysts such as serous cystadenomas, and pancreatic cystic neoplasms. Malignant potential is seen in pancreatic cystic neoplasms, particularly mucinous cystic neoplasms and intraductal papillary mucinous neoplasms. Proper identification of mucinous cysts warrants either continual surveillance or evaluation for surgical resection to prevent potential development of pancreatic adenocarcinoma. Large urban medical centers, serving a predominantly minority population with an increased incidence of pancreatic cancer, require accurate and prompt diagnosis of malignant cysts. Currently, the standard cyst fluid analyses include CEA, amylase and cytology. In many cases these are of limited value and new biomarkers need to be defined to assist in accurate designation of cyst type. Previous studies have used proteomic analyses to improve cyst identification. One candidate set of protein markers are cytokines, which are involved in cell-mediated responses. A subset of cytokines has been implicated in the carcinogenic process. We hypothesized that the cytokine concentration in the pancreatic cyst fluid obtained via endoscopic ultrasound fine-needle aspiration will be differentially detected and could be used as an additional test to differentiate mucinous cystadenomas and cystadenocarcinomas from pseudocysts and serous cystoadenomas. The study protocol was designed to determine the pancreatic cyst fluid cytokine levels between mucinous and nonmucinous pancreatic cysts using a slide-based quantitative multiplex cytokine antibody array (Raybiotech, Norcross, GA). The cytokine array allowed for the quantitative detection of 20 cytokines with the parallel measurement of individual cytokine standard curves. Initial screening of 18 samples (8 mucinous, 10 nonmucinous) demonstrated differential detection of multiple cytokine targets, such as IL-1α and IL-5 that were statistically significant (P&amp;lt;0.05). Both cytokines have been linked to protective effects and immune surveillance in the setting of cancer. Additional sample screening will assess cytokines found to be borderline non-significant and validate the preliminary cytokine hits. These types of biomarkers are easily measured by ELISA in a clinical laboratory and would be useful in clinical practice as an adjunct for pre-surgical cyst classification. The establishment of differential cytokine measurements between mucinous and nonmucinous cysts would play a role in enhancing detection of premalignant and malignant cysts and improving current surveillance strategies. In addition, examination of the role of these cytokines in cyst development and progression could lead to new insight into the role of inflammation in the biology of cysts. Citation Format: Rajesh Ramachandran, Larry Siu, Vadim Kurbatov, Evan Grossman, Frank Gress, Laura Martello. Classification of pancreatic cysts in a minority population through cytokine profiling of cyst fluid fine-needle aspirate. [abstract]. In: Proceedings of the AACR Special Conference on Pancreatic Cancer: Innovations in Research and Treatment; May 18-21, 2014; New Orleans, LA. Philadelphia (PA): AACR; Cancer Res 2015;75(13 Suppl):Abstract nr B33.

Classification of Pancreatic Cysts: Should We Rely on Molecular Analysis or is It Still a Clinical Judgment?

Classification of Pancreatic Cysts: Should We Rely on Molecular Analysis or is It Still a Clinical Judgment?

Pancreatic cysts: a report of 10 cases.

Abstract Ten cases of pancreatic cysts seen in 12 years in the University College Hospital, Ibadan, are reported. The clinical features and diagnoses are reviewed and found to be similar to those reported elsewhere. Pancreatic cysts occur in a younger age-group in this series than in other reports and this is related to malnutritional fibrocalcific pancreatic disease. The classification of pancreatic cysts is discussed and modified according to the experience of this series. The operative management of pancreatic cysts is briefly discussed.

Pseudocysts of the pancreas.

Pseudocysts of the pancreas occur infrequently. In 4329 admissions to the V. A. Hospital, Huntington, W. Va., from Jan. 1, 1952, to June 30, 1954, five patients with cysts have been operated upon. On reviewing the literature it was found that but few surgeons have had large series of cases, and most reports are made on the basis of one or two cases. There has been no uniformity of opinion as to treatment. Classification of pancreatic cysts is well agreed upon and is based on etiology. They are usually divided into (1) congenital, (2) neoplastic, (3) retention, (4) parasitic, and (5) pseudocysts. Congenital cysts of the pancreas are rare and are usually associated with cysts of other viscera, such as liver and kidney. The term retention cysts should be used to designate cystic dilatations arising secondary to partial or complete occlusion of the pancreatic ducts. The neoplastic cysts are the

Diagnosis and treatment of pancreatic cysts in children with report of a case

Summary 1. A brief review of the literature reveals seven cases of solitary cyst ofthe pancreas reported in children, chiefly in infants. 2. A case of a very large solitary cyst of the pancreas is reported in a 6-month-old male infant, in which the cyst was treated by surgical extirpation. 3. An attempt is made to clarify the classification of pancreatic cysts, and diagnosis and surgical treatment methods are discussed, with the recommendation that wherever possible extirpation is the treatment of choice. 4. The possibility of association of some pancreatic cysts with cystic fibrosisof the pancreas is raised for speculation.