Diagnosis Of Focal Pancreatic Masses Research Articles

Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.

Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.

Clinical impact of strain histogram EUS elastography and contrast-enhanced EUS for the differential diagnosis of focal pancreatic masses: A prospective multicentric study.

Background:Recent advances in EUS techniques (real-time EUS elastography and contrast-enhanced EUS) have allowed a better characterization of focal pancreatic masses. Mean strain histograms (SHs) are considered a good parameter for the semi-quantitative evaluation of focal pancreatic masses, alongside complementary contrast-enhanced EUS parameters which can be quantified during both the early arterial and late venous phase.Materials and Methods:The study design was prospective, blinded, and multicentric, assessing real-time EUS elastography and contrast-enhanced EUS results for the characterization of focal pancreatic masses using parametric measurements, in comparison with pathology which is the gold standard. SHs were performed based on the embedded software of the ultrasound system, with the values being reversed as opposed to our initially published data on hue histograms. Consequently, a cutoff of 80 was derived from previous multicentric trials. Contrast-enhanced EUS also allowed the focal masses to be classified as hyper-, iso-, or hypoenhanced in comparison with the normal pancreatic parenchyma. EUS-FNA was then performed for all patients, with a positive cytological diagnosis taken as a final proof of malignancy for the pancreatic masses. The diagnoses obtained by EUS-FNA were verified further either by surgery or during a clinical follow-up of at least 6 months.Results:A total number of 97 consecutive patients with focal pancreatic masses were included in the study. Based on previously defined cutoffs of 80, the values of sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the mean SHs for the diagnosis of pancreatic cancer were 100%, 29.63%, 78.65%, 100%, and 80.41%, respectively. Corresponding values for contrast-enhanced EUS (taking into consideration hypoenhencement as a predictive factor of malignancy) were 98.57%, 77.78%, 92%, 95.45%, and 92.78%, respectively. Combining contrast enhancement-EUS (hypoenhencement) and semi-quantitative EUS elastography (SH cutoffs <80), the resulting values corresponding for sensitivity, specificity, and accuracy were 98.57%, 81.48%, and 93.81%, respectively.Conclusion:The current study using objective parametric tools for both EUS elastography and contrast-enhanced EUS confirmed the results of previous studies and meta-analyses that indicated a complementary role for the differential diagnosis of focal pancreatic masses. Moreover, the best values for the receiver operating curves were obtained using a sequential clinical algorithm based on the initial use of elastography, followed by contrast enhancement.

Su1333 Clinical Impact of Strain Histogram Real-Time Elastography in Combination With Contrast Harmonic Imaging Eus for the Differential Diagnosis of Focal Pancreatic Masses: A Multicentric Trial

Su1333 Clinical Impact of Strain Histogram Real-Time Elastography in Combination With Contrast Harmonic Imaging Eus for the Differential Diagnosis of Focal Pancreatic Masses: A Multicentric Trial

Quantitative contrast-enhanced harmonic EUS in differential diagnosis of focal pancreatic masses (with videos)

The role of EUS with contrast agents can be expanded through the use of time-intensity curve (TIC) analysis and computer-aided interpretation. To validate the use of parameters derived from TIC analysis in an artificial neural network (ANN) classification model designed to diagnose pancreatic carcinoma (PC) and chronic pancreatitis (CP). Prospective, multicenter, observational trial-endoscopy units from Romania, Denmark, Germany, and Spain. A total of 167 consecutive patients with PC or CP. Contrast-enhanced harmonic EUS (CEH-EUS) and EUS-guided FNA (EUS-FNA), TIC analysis, andANN processing. Sensitivity, specificity, positive and negative predictive values (PPV, NPV) for EUS-FNA, CEH-EUS, and the ANN. After excluding all of the recordings that did not meet the technical and procedural criteria, 112 cases of PCand 55 cases of CP were included. EUS-FNA was performed in 129 patients, and the diagnosis was confirmed by surgery (n= 15) or follow-up (n= 23) in the remaining cases. Its sensitivity and specificity were 84.82% and100%, respectively, whereas the PPV and NPV were 100% and 76.63%, respectively. The sensitivity of real-time quantitative assessment of CEH-EUS was 87.5%, specificity 92.72%, PPV 96.07%, and NPV 78.46%. Peak enhancement, wash-in area under the curve, wash-in rate, and the wash-in perfusion index were significantly different between the groups. No significant differences were found between rise time, mean transit time, and time to peak. For the ANN, sensitivity was 94.64%, specificity 94.44%, PPV 97.24%, and NPV 89.47%. Only PC and CP lesions were included. Parameters obtained through TIC analysis can differentiate between PC and CP cases and can beused in an automated computer-aided diagnostic system with good diagnostic results. ( NCT01315548.).

Advanced Endoscopic Ultrasound Imaging: Contrast-Enhanced Endoscopic Ultrasound (Low MI, High MI), Including 3D Techniques in Pancreatic Imaging

Contrast-enhanced endoscopic ultrasound (CE-EUS) represents a new technique that can be used in conjunction with radial or linear EUS scopes, coupled with the corresponding ultrasound system. The technique is based on a second-generation blood-pool ultrasound contrast agent injected through a peripheral vein, which subsequently can be visualized through the microcirculation in the early arterial and late venous phase, especially when used with contrast harmonic imaging techniques (low mechanical index techniques). Contrast agents can be used as a Doppler signal enhancer (high mechanical index techniques), although this technique is particularly prone to artifacts. Both techniques can be used in conjunction with 3D acquisition modes, in order to quantify the vascularity of tumors or to better delineate the relationship with surrounding vessels. The CE-EUS techniques have been used mostly for pancreatic examinations, i.e., for the differential diagnosis of focal pancreatic masses. Thus, pancreatic adenocarcinoma has a hypovascular (hypoenhanced) appearance, whereas neuroendocrine tumors are usually hypervascular (hyperenhanced). Also, pseudotumoral chronic pancreatitis and autoimmune pancreatitis have an iso- or hypervascular appearance. All these techniques are described in the present article, with emphasis on the examination modes and technical details. This article is part of an expert video encyclopedia.

Endoscopic ultrasound-guided fine needle aspiration versus percutaneous ultrasound-guided fine needle aspiration in diagnosis of focal pancreatic masses

Objective:Pancreatic carcinoma is one of the leading cancer morbidity and mortality world-wide. Controversy has arisen about whether the percutaneous approach with computed tomography/ultrasonography-guidance fine needle aspiration (US-FNA) or endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) is the preferred method to obtain diagnostic tissue. Our purpose of this study is to compare between the diagnostic accuracy of EUS-FNA and percutaneous US-FNA in diagnosis of pancreatic cancer.Patients and Methods:A total of 197 patients with pancreatic masses were included in the study, 125 patients underwent US-FNA (Group 1) and 72 patients underwent EUS-FNA (Group 2).Results:EUS-FNA has nearly the same accuracy (88.9%) as US-FNA (87.2%) in diagnosis of pancreatic cancer. The sensitivity, specificity, positive predictive value and negative predictive value for EUS-FNA was 84%, 100%, 100%, 73.3% respectively. It was 85.5%, 90.4%, 94.7%, 76% respectively for US-FNA. EUS-FNA had a lower complication rate (1.38%) than US-FNA (5.6%).Conclusion:EUS-FNA has nearly the same accuracy as US-FNA of pancreatic masses with a lower complication rate.

Contrast-enhanced harmonic endoscopic ultrasound

Second-generation intravenous blood-pool ultrasound contrast agents are increasingly used in endoscopic ultrasound (EUS) for characterization of microvascularization, differential diagnosis of benign and malignant focal lesions, and improving staging and guidance of therapeutic procedures. Although initially used as Doppler signal enhancers, second-generation microbubble contrast agents are now used with specific contrast harmonic imaging techniques, which benefit from the highly nonlinear behavior of the microbubbles. Contrast-specific modes based on multi-pulse technology are used to perform contrast-enhanced harmonic EUS based on a very low mechanical index (0.08 - 0.12). Quantification techniques based on dynamic contrast-enhanced ultrasound have been recommended for perfusion imaging and monitoring of anti-angiogenic treatment, mainly based on time-intensity curve analysis. Most of the clinical applications include the differential diagnosis of focal pancreatic masses, with adenocarcinoma having a distinct hypovascular (hypo-enhanced) appearance compared with neuroendocrine tumors, which are hypervascular (with strong arterial hyper-enhancement). However, pseudotumoral chronic pancreatitis and autoimmune pancreatitis also have an iso- or hypervascular appearance, making the differential diagnosis difficult. Even more promising is the use of dynamic contrast-enhanced harmonic EUS for the longitudinal monitoring of the effects of chemotherapy and/or anti-angiogenic therapy in advanced digestive cancers, which are difficult to examine by conventional cross-sectional imaging techniques.

Sa1571 Diagnosis of Focal Pancreatic Masses by Quantitative Low Mechanical Index Contrast-Enhanced Endoscopic Ultrasound (EUS)

manually reviewed; 14 met criteria and 2x2 data were abstracted. 5 RS were used alone or in combination: ERCP, function tests, radiologic/clinical follow-up, and histology. As seen in Fig 1, adjusting for the imperfect RS yielded higher test performance characteristics for EUS (solid lines) than if perfection in RS was assumed (dashed lines). Similar results were obtained with “non-informative prior”. Median pooled sensitivity & specificity were 87.1% (95%CI: 67-97%) & 92.9% (95%CI: 71-99%) for the 3 cutoff. Adjusted RS sensitivities’ & specificities’ ranges were 74-95% & 85-95%, for MCCP; histology was most accurate (95%, 93%), and function tests least sensitive but specific (74%, 93%). Conclusions: EUS diagnostic performance in MCCP can be summarized from existing literature using novel Bayesian methods to correct for imperfections in the array of RS used to date. EUS accuracy is high, especially in comparison to estimated “true” test performance of the RS to which it is being compared.

Efficacy of an Artificial Neural Network–Based Approach to Endoscopic Ultrasound Elastography in Diagnosis of Focal Pancreatic Masses

By using strain assessment, real-time endoscopic ultrasound (EUS) elastography provides additional information about a lesion's characteristics in the pancreas. We assessed the accuracy of real-time EUS elastography in focal pancreatic lesions using computer-aided diagnosis by artificial neural network analysis. We performed a prospective, blinded, multicentric study at of 258 patients (774 recordings from EUS elastography) who were diagnosed with chronic pancreatitis (n = 47) or pancreatic adenocarcinoma (n = 211) from 13 tertiary academic medical centers in Europe (the European EUS Elastography Multicentric Study Group). We used postprocessing software analysis to compute individual frames of elastography movies recorded by retrieving hue histogram data from a dynamic sequence of EUS elastography into a numeric matrix. The data then were analyzed in an extended neural network analysis, to automatically differentiate benign from malignant patterns. The neural computing approach had 91.14% training accuracy (95% confidence interval [CI], 89.87%-92.42%) and 84.27% testing accuracy (95% CI, 83.09%-85.44%). These results were obtained using the 10-fold cross-validation technique. The statistical analysis of the classification process showed a sensitivity of 87.59%, a specificity of 82.94%, a positive predictive value of 96.25%, and a negative predictive value of 57.22%. Moreover, the corresponding area under the receiver operating characteristic curve was 0.94 (95% CI, 0.91%-0.97%), which was significantly higher than the values obtained by simple mean hue histogram analysis, for which the area under the receiver operating characteristic was 0.85. Use of the artificial intelligence methodology via artificial neural networks supports the medical decision process, providing fast and accurate diagnoses.

Accuracy of endoscopic ultrasound elastography used for differential diagnosis of focal pancreatic masses: a multicenter study

Endoscopic ultrasound (EUS) elastography represents a new imaging procedure that might characterize the differences of hardness and strain between diseased tissue and normal tissue. The aim of this study was to assess the efficiency of EUS elastography for the differentiation of focal masses in chronic pancreatitis and pancreatic cancer. The study group comprised 258 patients with focal pancreatic masses included prospectively at 13 participating centers. Qualitative analysis of the diagnoses made by two expert doctors using all recorded video clips was performed in order to test the interobserver variability. A post-processing software analysis was used to examine the EUS elastography videos by calculating average-hue histograms of individual elastography images. The quantitative information was used to calculate intra-observer variability and the accuracy of the method. Qualitative analysis of the recorded videos revealed a kappa value of 0.72. Intra-observer variability analysis revealed that the single measure intraclass correlation ranged between 0.86 and 0.94. The average-hue histogram analysis of the data indicated a sensitivity of 93.4 %, a specificity of 66.0 %, a positive predictive value of 92.5 %, a negative predictive value of 68.9 %, and an overall accuracy of 85.4 %, based on a cut-off value of 175. Area under the receiver operating characteristic curve (AUROC) was 0.854 ( P < 0.0001) with a confidence interval of 0.804 - 0.894. The value of quantitative analysis of EUS elastography recordings was proven by good reproducibility of the videos, as well as good parameters of the AUROC analysis. (Clinical Trials.gov identifier: CT00909103).

State-of-the-art imaging techniques in endoscopic ultrasound

Endoscopic ultrasound (EUS) has recently evolved through technological improvement of equipment, with a major clinical impact in digestive and mediastinal diseases. State-of-the-art EUS equipment now includes real-time sono-elastography, which might be useful for a better characterization of lesions and increased accuracy of differential diagnosis (for e.g. lymph nodes or focal pancreatic lesions). Contrast-enhanced EUS imaging is also available, and is already being used for the differential diagnosis of focal pancreatic masses. The recent development of low mechanical index contrast harmonic EUS imaging offers hope for improved diagnosis, staging and monitoring of anti-angiogenic treatment. Tridimensional EUS (3D-EUS) techniques can be applied to enhance the spatial understanding of EUS anatomy, especially for improved staging of tumors, obtained through a better assessment of the relationship with major surrounding vessels. Despite the progress gained through all these imaging techniques, they cannot replace cytological or histological diagnosis. However, real-time optical histological diagnosis can be achieved through the use of single-fiber confocal laser endomicroscopy techniques placed under real-time EUS-guidance through a 22G needle. Last, but not least, EUS-assisted natural orifice transluminal endoscopic surgery (NOTES) procedures offer a whole new area of imaging applications, used either for combination of NOTES peritoneoscopy and intraperitoneal EUS, but also for access of retroperitoneal organs through posterior EUS guidance.

Combined contrast-enhanced power Doppler and real-time sonoelastography performed during EUS, used in the differential diagnosis of focal pancreatic masses (with videos)

Contrast-enhanced power Doppler (CEPD) and real-time sonoelastography (RTSE) performed during EUS were previously described to be useful for the differential diagnosis between chronic pseudotumoral pancreatitis and pancreatic cancer. To prospectively assess the accuracy of the combination of CEPD and RTSE to differentiate pancreatic focal masses. Cross-sectional feasibility study. A tertiary-care academic referral center. The study group included 54 patients with chronic pancreatitis (n = 21) and pancreatic adenocarcinoma (n = 33). Both imaging methods (CEPD and RTSE) were performed sequentially during the same EUS examination. Power Doppler mode examination was performed after intravenous injection of a second-generation contrast agent (2.4 mL of SonoVue), and the data were digitally recorded, comprising both the early arterial phase and venous/late phase. Three 10-second sonoelastographic videos were also digitally recorded that included the focal mass and the surrounding pancreatic parenchyma. Postprocessing analyses based on specially designed software were used to analyze the CEPD and RTSE videos. A power Doppler vascularity index was used to characterize CEPD videos, the values being averaged during a 10-second video in the venous phase. Hue histogram analysis was used to characterize RTSE videos, with the mean hue histogram values being also averaged during a 10-second video. To differentiate chronic pancreatitis and pancreatic cancer. The sensitivity, specificity, and accuracy of combined information provided by CEPD and RTSE to differentiate hypovascular hard masses suggestive of pancreatic carcinoma were 75.8%, 95.2%, and 83.3%, respectively, with a positive predictive value and negative predictive value of 96.2% and 71.4%, respectively. A single-center, average size of study population. A combination of CEPD and RTSE performed during EUS seems to be a promising method that allows characterization and differentiation of focal pancreatic masses.

415i: Accuracy of Endoscopic Ultrasound Elastography Used for Differential Diagnosis of Chronic Pancreatitis and Pancreatic Cancer: A Multicentric Study

Endoscopic ultrasound (EUS) elastography represents a new imaging procedure that might characterize the differences of hardness and strain between diseased tissue and normal tissue. The method has been used for the differential diagnosis of focal pancreatic masses with variable accuracy and contradictory results.

Neural network analysis of dynamic sequences of EUS elastography used for the differential diagnosis of chronic pancreatitis and pancreatic cancer

EUS elastography is a newly developed imaging procedure that characterizes the differences of hardness and strain between diseased and normal tissue. To assess the accuracy of real-time EUS elastography in pancreatic lesions. Cross-sectional feasibility study. The study group included, in total, 68 patients with normal pancreas (N = 22), chronic pancreatitis (N = 11), pancreatic adenocarcinoma (N = 32), and pancreatic neuroendocrine tumors (N = 3). A subgroup analysis of 43 cases with focal pancreatic masses was also performed. A postprocessing software analysis was used to examine the EUS elastography movies by calculating hue histograms of each individual image, data that were further subjected to an extended neural network analysis to differentiate benign from malignant patterns. To differentiate normal pancreas, chronic pancreatitis, pancreatic cancer, and neuroendocrine tumors. Based on a cutoff of 175 for the mean hue histogram values recorded on the region of interest, the sensitivity, specificity, and accuracy of differentiation of benign and malignant masses were 91.4%, 87.9%, and 89.7%, respectively. The positive and negative predictive values were 88.9% and 90.6%, respectively. Multilayer perceptron neural networks with both one and two hidden layers of neurons (3-layer perceptron and 4-layer perceptron) were trained to learn how to classify cases as benign or malignant, and yielded an excellent testing performance of 95% on average, together with a high training performance that equaled 97% on average. A lack of the surgical standard in all cases. EUS elastography is a promising method that allows characterization and differentiation of normal pancreas, chronic pancreatitis, and pancreatic cancer. The currently developed methodology, based on artificial neural network processing of EUS elastography digitalized movies, enabled an optimal prediction of the types of pancreatic lesions. Future multicentric, randomized studies with adequate power will have to establish the clinical impact of this procedure for the differential diagnosis of focal pancreatic masses.

Variables Affecting the Accuracy of EUS-Guided FNA in the Diagnosis of Focal Pancreatic Masses

Variables Affecting the Accuracy of EUS-Guided FNA in the Diagnosis of Focal Pancreatic Masses