Detection Of Pancreatic Lesions Research Articles

Multiscale and multiperception feature learning for pancreatic lesion detection based on noncontrast CT

Background. Pancreatic cancer is one of the most malignant tumours, demonstrating a poor prognosis and nearly identically high mortality and morbidity, mainly because of the difficulty of early diagnosis and timely treatment for localized stages. Objective. To develop a noncontrast CT (NCCT)-based pancreatic lesion detection model that could serve as an intelligent tool for diagnosing pancreatic cancer early, overcoming the challenges associated with low contrast intensities and complex anatomical structures present in NCCT images. Approach. We design a multiscale and multiperception (MSMP) feature learning network with ResNet50 coupled with a feature pyramid network as the backbone for strengthening feature expressions. We added multiscale atrous convolutions to expand different receptive fields, contextual attention to perceive contextual information, and channel and spatial attention to focus on important channels and spatial regions, respectively. The MSMP network then acts as a feature extractor for proposing an NCCT-based pancreatic lesion detection model with image patches covering the pancreas as its input; Faster R-CNN is employed as the detection method for accurately detecting pancreatic lesions. Main results. By using the new MSMP network as a feature extractor, our model outperforms the conventional object detection algorithms in terms of the recall (75.40% and 90.95%), precision (40.84% and 68.21%), F1 score (52.98% and 77.96%), F2 score (64.48% and 85.26%) and Ap50 metrics (53.53% and 70.14%) at the image and patient levels, respectively. Significance.The good performance of our new model implies that MSMP can mine NCCT imaging features for detecting pancreatic lesions from complex backgrounds well. The proposed detection model is expected to be further developed as an intelligent method for the early detection of pancreatic cancer.

The role of endoscopic ultrasound in the detection of pancreatic lesions in high-risk individuals.

Individuals at high risk of developing pancreatic ductal adenocarcinoma are eligible for surveillance within research programs. These programs employ periodic imaging in the form of magnetic resonance imaging/magnetic resonance cholangiopancreatography or endoscopic ultrasound for the detection of early cancer or high-grade precursor lesions. This narrative review discusses the role of endoscopic ultrasound within these surveillance programs. It details its overall strengths and limitations, yield, burden on patients, and how it compares to magnetic resonance imaging. Finally, recommendations are given when and how to incorporate endoscopic ultrasound in the surveillance of high-risk individuals.

Feasibility of deep learning-reconstructed thin-slice single-breath-hold HASTE for detecting pancreatic lesions: A comparison with two conventional T2-weighted imaging sequences

ObjectiveThe objective of this study was to evaluate the clinical feasibility of deep learning reconstruction-accelerated thin-slice single-breath-hold half-Fourier single-shot turbo spin echo imaging (HASTEDL) for detecting pancreatic lesions, in comparison with two conventional T2-weighted imaging sequences: compressed-sensing HASTE (HASTECS) and BLADE. MethodsFrom March 2022 to January 2023, a total of 63 patients with suspected pancreatic-related disease underwent the HASTEDL, HASTECS, and BLADE sequences were enrolled in this retrospectively study. The acquisition time, the pancreatic lesion conspicuity (LCP), respiratory motion artifact (RMA), main pancreatic duct conspicuity (MPDC), overall image quality (OIQ), signal-to-noise ratio (SNR), and contrast-noise-ratio (CNR) of the pancreatic lesions were compared among the three sequences by two readers. ResultsThe acquisition time of both HASTEDL and HASTECS was 16 s, which was significantly shorter than that of 102 s for BLADE. In terms of qualitative parameters, Reader 1 and Reader 2 assigned significantly higher scores to the LCP, RMA, MPDC, and OIQ for HASTEDL compared to HASTECS and BLADE sequences; As for the quantitative parameters, the SNR values of the pancreatic head, body, tail, and lesions, the CNR of the pancreatic lesion measured by the two readers were also significantly higher for HASTEDL than for HASTECS and BLADE sequences. ConclusionsCompared to conventional T2WI sequences (HASTECS and BLADE), deep-learning reconstructed HASTE enables thin slice and single-breath-hold acquisition with clinical acceptable image quality for detection of pancreatic lesions.

Role of Endoscopic Ultrasound in Diagnosis of Pancreatic Ductal Adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) is the most common (90%) type of solid pancreatic neoplasm. Due to its late presentation and poor survival rate, early diagnosis and timely treatment is of utmost importance for better clinical outcomes. Endoscopic ultrasound provides high-resolution images of the pancreas and has excellent sensitivity in the diagnosis of even small (<2 cm) pancreatic lesions. Apart from imaging, it also has an advantage of tissue acquisition (EUS fine-needle aspiration, FNA; or fine-needle biopsy, FNB) for definitive diagnoses. EUS-guided tissue acquisition plays a crucial role in genomic and molecular studies, which in today's era of personalized medicine, are likely to become important components of PDAC management. With the use of better needle designs and technical advancements, EUS has now become an indispensable tool in the management of PDAC. Lastly, artificial intelligence for the detection of pancreatic lesions and newer automated needles for tissue acquisition will obviate observer dependency in the near future, resulting in the wider dissemination and adoption of this technology for improved outcomes in patients with PDAC.

Mask R-CNN Machine Learning Based Pancreatic Lesion Detection and Categorization: With An Open-source Tool For Real World Use

Interest in applying machine learning (ML) in medical research has exploded over the past decade, especially in oncology and medical imaging. The objective of ML, particularly machine vision in medical imaging, is to solve lesion identification, segmentation, and classification problems. Although numerous studies have developed ML models that can be beneficial in various clinical settings, more often than not, there is no easy way to apply the models in practice without technical knowledge. To address this issue, in the process of developing an ML model to detect and categorize pancreatic lesions as either cystic or solid, we developed the PCP2 Toolkit. PCP2 is an open-source tool for training and using Mask R-CNN-based ML vision models. PCP2’s core ML functionality is implemented in Python and the user interface in JavaScript. Here, we discuss the architecture, workflow, and application of PCP2 and demonstrate its use in training a model to classify pancreatic lesions on Computed Tomography (CT) images. The model achieved a mean average precision (mAP) of 61.2% and a mean average recall (mAR) of 65.1%. The mAP at Intersection over Union (IoU) thresholds of 50% and 75% were 80.6% and 65.1%, respectively. The source code, documentation, and trained model are available at nbcatalyst.com. Our objective is to provide an easy-to-use, customizable, and extendable tool for training machine vision models and using the trained model in the real world.

Image Quality and Lesion Detectability of Pancreatic Phase Thin-Slice Computed Tomography Images With a Deep Learning-Based Reconstruction Algorithm.

To evaluate the image quality and lesion detectability of pancreatic phase thin-slice computed tomography (CT) images reconstructed with a deep learning-based reconstruction (DLR) algorithm compared with filtered-back projection (FBP) and hybrid iterative reconstruction (IR) algorithms. Fifty-three patients who underwent dynamic contrast-enhanced CT including pancreatic phase were enrolled in this retrospective study. Pancreatic phase thin-slice (0.625 mm) images were reconstructed with each FBP, hybrid IR, and DLR. Objective image quality and signal-to-noise ratio of the pancreatic parenchyma, and contrast-to-noise ratio of pancreatic lesions were compared between the 3 reconstruction algorithms. Two radiologists independently assessed the image quality of all images. The diagnostic performance for the detection of pancreatic lesions was compared among the reconstruction algorithms using jackknife alternative free-response receiver operating characteristic analysis. Deep learning-based reconstruction resulted in significantly lower image noise and higher signal-to-noise ratio and contrast-to-noise ratio than hybrid IR and FBP ( P < 0.001). Deep learning-based reconstruction also yielded significantly higher visual scores than hybrid IR and FBP ( P < 0.01). The diagnostic performance of DLR for detecting pancreatic lesions was highest for both readers, although a significant difference was found only between DLR and FBP in one reader ( P = 0.02). Deep learning-based reconstruction showed improved objective and subjective image quality of pancreatic phase thin-slice CT relative to other reconstruction algorithms and has potential for improving lesion detectability.

Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning.

This study proposes and evaluates a deep learning method to detect pancreatic neoplasms and to identify main pancreatic duct (MPD) dilatation on portal venous computed tomography scans. A total of 2890 portal venous computed tomography scans from 9 institutions were acquired, among which 2185 had a pancreatic neoplasm and 705 were healthy controls. Each scan was reviewed by one in a group of 9 radiologists. Physicians contoured the pancreas, pancreatic lesions if present, and the MPD if visible. They also assessed tumor type and MPD dilatation. Data were split into a training and independent testing set of 2134 and 756 cases, respectively.A method to detect pancreatic lesions and MPD dilatation was built in 3 steps. First, a segmentation network was trained in a 5-fold cross-validation manner. Second, outputs of this network were postprocessed to extract imaging features: a normalized lesion risk, the predicted lesion diameter, and the MPD diameter in the head, body, and tail of the pancreas. Third, 2 logistic regression models were calibrated to predict lesion presence and MPD dilatation, respectively. Performance was assessed on the independent test cohort using receiver operating characteristic analysis. The method was also evaluated on subgroups defined based on lesion types and characteristics. The area under the curve of the model detecting lesion presence in a patient was 0.98 (95% confidence interval [CI], 0.97-0.99). A sensitivity of 0.94 (469 of 493; 95% CI, 0.92-0.97) was reported. Similar values were obtained in patients with small (less than 2 cm) and isodense lesions with a sensitivity of 0.94 (115 of 123; 95% CI, 0.87-0.98) and 0.95 (53 of 56, 95% CI, 0.87-1.0), respectively. The model sensitivity was also comparable across lesion types with values of 0.94 (95% CI, 0.91-0.97), 1.0 (95% CI, 0.98-1.0), 0.96 (95% CI, 0.97-1.0) for pancreatic ductal adenocarcinoma, neuroendocrine tumor, and intraductal papillary neoplasm, respectively. Regarding MPD dilatation detection, the model had an area under the curve of 0.97 (95% CI, 0.96-0.98). The proposed approach showed high quantitative performance to identify patients with pancreatic neoplasms and to detect MPD dilatation on an independent test cohort. Performance was robust across subgroups of patients with different lesion characteristics and types. Results confirmed the interest to combine a direct lesion detection approach with secondary features such as the MPD diameter, thus indicating a promising avenue for the detection of pancreatic cancer at early stages.

Advanced Faster RCNN: a non-contrast CT-based algorithm for detecting pancreatic lesions in multiple disease stages

To propose a non-contrast CT-based algorithm for automated and accurate detection of pancreatic lesions at a low cost. With Faster RCNN as the benchmark model, an advanced Faster RCNN (aFaster RCNN) model for pancreatic lesions detection based on plain CT was constructed. The model uses the residual connection network Resnet50 as the feature extraction module to extract the deep image features of pancreatic lesions. According to the morphology of pancreatic lesions, 9 anchor frame sizes were redesigned to construct the RPN module. A new Bounding Box regression loss function was proposed to constrain the training process of RPN module regression subnetwork by comprehensively considering the constraints of the lesion shape and anatomical structure. Finally, a detection frame was generated using the detector in the second stage. The data from a total of 728 cases of pancreatic diseases from 4 clinical centers in China were used for training (518 cases, 71.15%) and testing (210 cases, 28.85%) of the model. The performance of aFaster RCNN was verified through ablation experiments and comparison experiments with 3 classical target detection models SSD, YOLO and CenterNet. The aFaster RCNN model for pancreatic lesion detection achieved recall rates of 73.64% at the image level and 92.38% at the patient level, with an average precision of 45.29% and 53.80% at the image and patient levels, respectively, which were higher than those of the 3 models for comparison. The proposed method can effectively extract the imaging features of pancreatic lesions from non-contrast CT images to detect the pancreatic lesions.

Artificial intelligence for the detection of pancreatic lesions.

Pancreatic cancer is one of the most lethal neoplasms among common cancers worldwide, and PCLs are well-known precursors of this type of cancer. Artificial intelligence (AI) could help to improve and speed up the detection and classification of pancreatic lesions. The aim of this review is to summarize the articles addressing the diagnostic yield of artificial intelligence applied to medical imaging (computed tomography [CT] and/or magnetic resonance [MR]) forthedetection of pancreatic cancer and pancreatic cystic lesions. We performed a comprehensive literature search using PubMed, EMBASE, and Scopus (from January 2010 to April 2021) to identify full articles evaluating the diagnostic accuracy of AI-based methods processing CT or MR imagesto detect pancreatic ductal adenocarcinoma (PDAC) or pancreatic cystic lesions (PCLs). We found 20 studies meeting our inclusion criteria. Mostof the AI-based systems used were convolutional neural networks.Tenstudies addressed the use of AI to detect PDAC, eightstudies aimed to detect and classify PCLs, and 4 aimed to predict the presence of high-grade dysplasia or cancer. AI techniques have shown to be a promising tool which is expected to be helpful for mostradiologists'tasks. However, methodologic concerns must be addressed, and prospective clinical studies should be carried out before implementation in clinical practice.

S2484 Endoscopic Ultrasound With Fine Needle Aspiration for Diagnosis of Pancreatic Tumors in Patients With Benign Magnetic Resonance Imaging: Single Center Case Series

Introduction: Pancreatic cancer is the fourth leading cause of cancer-related death in the United States. Computed tomography (CT) scan and Magnetic resonance imaging (MRI) are used for early detection of small pancreatic lesions and cancer risk stratification. Endoscopic ultrasonography (EUS) with FNA (Fine Needle Aspiration) provides accurate diagnosis of pancreatic tumors. This case series introduces four cases of pancreatic tumors diagnosed using EUS/FNA that have been missed on MRI studies Case Description/Methods: Case 1 64-year-old male was referred for evaluation of pancreatic duct dilation on MRI with no detected mass. EUS revealed 15mm x 15mm mass of pancreas. FNA was performed and pathology was consistent with adenocarcinoma Case 2 55-year-old female was referred for evaluation of pancreatic cystic lesion found on MRI with no worrisome features. EUS revealed 15mm x 15mm pancreatic lesion. FNA was performed and pathology was consistent with pancreatic neuroendocrine tumor. Case 3 82-year-old female was referred for evaluation of pancreatic duct dilation on MRI with no discrete mass identified. EUS revealed 26mm x 27mm pancreatic lesion. FNA was performed and pathology was consistent with invasive adenocarcinoma. Case 4 62-year-old male was referred for evaluation of pancreatic lesion on MRI abdomen with features consistent with lipoma. EUS revealed 15mm x 13mm pancreatic lesion. FNA was performed and pathology was consistent with adenocarcinoma. Discussion: The diagnosis of pancreatic neoplasms relies heavily on identification of lesions on CT and MRI. While the sensitivity of MRI is similar to that of CT, the former is preferred in patients with high pre-test probability of pancreatic neoplasms. Sensitivity of EUS has been shown to be significantly higher in detecting pancreatic tumors when compared to CT, However, studies evaluating EUS to MRI are scarce. This case series presents four patients in whom pancreatic tumors were missed on MRI. Two patients had no radiologic evidence of a tumor, while the other two demonstrated lesions with no malignant features. EUS has the added benefit of tumor sampling and higher sensitivity in detecting pancreatic lesions. This case series highlights the potential limitations in the use of MR imaging in diagnosis of pancreatic cancers. Some evidence suggests that EUS is more sensitive than MRI and CT in detecting pancreatic lesions. However, the cost effectiveness and risks associated with routine EUS in the detection of pancreatic lesions has not been evaluated.Figure 1.: (A): Case 3 EUS with arrow pointing at 26mm x 27mm pancreatic lesion (B): Case 4 EUS with arrow pointing at 15mm x 13mm pancreatic lesion.

Comparisons between image quality and diagnostic performance of 2D- and breath-hold 3D magnetic resonance cholangiopancreatography at 3T.

To compare the image quality and diagnostic performance of 2D MRCP to those of breath-hold 3D MRCP using compressed sensing (CS-MRCP) and gradient and spin-echo (GRASE-MRCP) at 3T. From January to November 2018, patients who underwent pancreatobiliary MRI including 2D MRCP and two breath-hold 3D MRCP using CS and GRASE at 3T were included. Three radiologists independently evaluated image quality, motion artifact, and pancreatic cyst conspicuity. Diagnostic performance was assessed for bile duct anatomic variation, bile duct, and pancreatic diseases using a composite algorithm as reference standards. Pancreatic lesion detectability and conspicuity were evaluated using JAFROC and generalized estimating equation analysis. One hundred patients (male = 50) were included. Bile duct anatomic variation, bile duct and pancreatic diseases were present in respectively 31, 15, and 79 patients. Breath-hold 3D MRCP provided better image quality than 2D MRCP (3.5 ± 0.6 in 2D MRCP; 4.0 ± 0.7 in GRASE-MRCP and 3.9 ± 0.8 in CS-MRCP, p < 0.001 for both). There was no difference in motion artifact between 2D and breath-hold 3D MRCP (p = 0.1). Breath-hold 3D CS-MRCP provided better pancreatic cyst conspicuity than 2D MRCP (2.7 [95% CI: 2.5-3.0] vs. 2.3 [95% CI: 2.1-2.5], p = 0.001). There were no significant differences between the diagnostic performance of the three sequences in the detection of bile duct anatomic variation or pancreatic lesions (p > 0.05). Breath-hold 3D MRCP with GRASE or CS can provide better image quality than 2D MRCP in a comparable scan time. • Breath-hold 3D MRCP using compressed sensing (CS) or gradient and spin-echo (GRASE) provided a better image quality with less image blurring than 2D MRCP. • There were no significant differences between 2D MRCP and breath-hold 3D MRCP in either motion artifact or the number of non-diagnostic exams. • There were no significant differences between 2D MRCP and either type of breath-hold 3D MRCP in the diagnosis of bile duct anatomic variation or detection of pancreatic lesions.

The role of endoscopic ultrasound in diagnosis and staging of pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) is a malignant neoplasia with an incidence and a prevalence that are progressively growing. It is estimated that in 2030 it will be the third most common tumor, after lungs and liver. This is due at first because of a delay in the development of new therapies able to change PDAC patients' prognosis and also because at diagnosis the tumor is already in advanced stages. During last years, endoscopic ultrasound (EUS), thanks to its versatility, became the first-choice technique in pancreatic diseases. EUS can be used, in example, in the screening of high-risk subjects (HRI) for the development of PDAC. The screening program is reserved to subjects with germinal mutation in high risk genes and subjects with a familial pancreatic cancer history. EUS was found to be a technique highly sensitive with a slightly good specificity in the detection of pancreatic lesions in HRIs; its diagnostic accuracy is superior to MRI and CT-scan, most of all for small size lesions (respectively 93%, 67% and 53%). A fundamental role of EUS is represented by the PDAC diagnosis. Even in this case a higher sensitivity respect to MRI and CT-scan can be observed (94% vs 79% vs 74%). The diagnostic ability could be improved by the use of ancillary techniques as elastography or contrast agents. Furthermore, with EUS it is possible to obtain a cytological or a histological specimen for the diagnosis of PDAC with low risk of adverse events and a high diagnostic accuracy. Considering therapeutic approaches, EUS can be used for pain control performing the celiac plexus neurolysis; new future insights can be found in the possibility of ablative treatments of pancreatic solid neoplasia.

Improved detectability of hypoattenuating focal pancreatic lesions by dual-layer computed tomography using virtual monoenergetic images

BackgroundMultidetector CT is the mainstay for radiologic evaluation of pancreatic pathology. Still, imaging of focal pancreatic lesions using MDCT is faced by a number of challenges that are related to the limited contrast between the lesion and surrounding parenchyma, such as detecting early-stage pancreatic cancer and subtle features of cystic lesions that point to malignancy. Dual-layer CT is the first dual-energy CT machine based on separation of high- and low-energy photons at the detector level. If improved contrast between the lesions and normal pancreatic parenchyma could be achieved on CT images, we may expect enhanced CT detection of pancreatic lesions. The purpose of this study was to evaluate whether virtual monoenergetic reconstructions generated using contrast-enhanced dual-layer CT could improve detectability of hypoattenuating focal pancreatic lesions compared to conventional polyenergetic reconstructions.ResultsFifty-four lesions were identified and verified by histopathology or follow-up CT, MRCP, and/or EUS along with clinical data. Across the virtual monoenergetic spectrum, 40 KeV images had the highest contrast-to-noise and signal-to-noise ratios (p < 0.001, p < 0.001) and were significantly higher than conventional images (p < 0.001). Subjective scores for lesion visibility at low kiloelectron volt monoenergetic (40 and 50 KeV) images greatly exceeded conventional images (p < 0.001).ConclusionLow kiloelectron volt monoenergetic reconstructions of contrast-enhanced dual-layer CT significantly improve detectability of hypoattenuating focal pancreatic lesions compared to conventional polyenergetic reconstructions.

Differential diagnosis of solid pancreatic masses.

Solid pancreatic lesions include mainly adenocarcinoma, neuroendocrine tumors pancreatic cystic neoplasms with solid component, solid pseudopapillary tumor, pancreatoblastoma, pancreatic lymphoma, and pancreatic metastasis. The most frequent pancreatic lesion is the adenocarcinoma, representing between 70% and 95% of all solid pancreatic neoplasm. The diagnosis of these lesions can be a challenge and currently, there are different imaging techniques such as CT scan, EUS and MRI with high sensitivity and specificity. The most widely used technique for the initial evaluation is the CT scan with a sensitivity between 76% and 92% for the diagnosis of pancreatic cancer. The EUS has a sensitivity for the detection of pancreatic lesions of around 98% and is accepted to be the most sensitive technique for the detection of small pancreatic tumors (<2 cm). The MRI, with a very high soft-tissue contrast resolution, provides an accuracy in the detection and staging of adenocarcinoma of 90-100%. A multimodality approach is usually necessary in patients with clinical suspicion of pancreatic lesion. The EUS is required for the local evaluation of the relation of the lesion with vessels and for tissue acquisition and the CT scan and/or MRI is usually required for the local and distance staging in case of pancreatic cancer. The purpose of this review is to provide an overview of solid pancreatic lesions and the role of the different imaging techniques in their evaluation.

Reduced Contrast Volume and Radiation Dose During Computed Tomography of the Pancreas: Timing-Specific Contrast Media Protocol

To investigate the opacification of the pancreatic vasculature and parenchyma during computed tomography utilizing a patient-specific contrast formula. This hybrid prospective and retrospective study was approved by the institution review board. In 220 consecutive patients, pancreatic CT was performed with one of two protocols: protocol A, 100mL of contrast material injected via timed bolus triggering technique; or protocol B, employing a patient-specific contrast media protocol specifically timed at the gastroduodenal artery; both protocols employed 4.5 mL/s contrast media and 100mL saline chaser. Attenuation of pancreatic parenchymal, arterial, and venous vasculature supplying the pancreas was measured. Effective dose was calculated. Data were compared to the independent two-sample t test. Receiver operating characteristic, visual grading characteristic, and Cohens' kappa analyses were performed. Mean pancreatic density measurements in each of the pancreatic segments during the arterial and venous phase were significantly higher in Protocol B (mean ± standard deviation, art: 96.59 HU ± 27.37; venous: 91.28 HU ± 20.88) compared to A (art: 77.86 HU ± 21.14; venous: 73.99 HU ± 14.75) (p < 0.0001). Mean arterial opacification was significantly higher in protocol B compared to A with the abdominal aorta (p < 0.007), superior mesenteric (p < 0.0002), gastroduodenal (proximal segment only p < 0.014), and splenic arteries (p < 0.036). In the venous circulation, the inferior vena cava, superior mesenteric, portal and splenic veins (all segments) demonstrated significant reduction in vascular opacification protocol B compared to A (p < 0.001). The contrast media volume in protocol B (57.60 ± 12.25 mL) was significantly lower than in protocol A (100 ± 1 mL) (p < 0.001). Effective dose was significantly reduced in protocol B (2.75 ± 0.63 mSv) compared to A (4.015 ± 0.89 mSv) (p < 0.001). Receiver operating characteristic and visual grading characteristic analysis demonstrated significantly higher area under the curve for protocol B (p < 0.0001) (p < 0.034) respectively, with inter-reader agreement increasing from good to excellent in pancreatic lesion detection. Timing-specific contrast media protocol enhances image quality at reduced contrast volume and radiation dose during computed tomography of the pancreas.

Preoperative Evaluation of a Pancreas Mass: Diagnostic Options.

As modern abdominal imaging equipment advances, pancreatic lesion detection improves. Most of these lesions are incidental, and present a conundrum to the clinician and create great anxiety to the patient until a final diagnosis is made. For the practicing physician, the plethora of diagnostic options is overwhelming. The relevant question is, what is the most efficient algorithm to follow and to arrive at a timely and accurate diagnosis. This article presents a logical approach to the initial evaluation of a pancreatic lesion to get the most information possible with the least amount of testing, and to avoid duplicative measures.

Linear-array EUS improves detection of pancreatic lesions in high-risk individuals: a randomized tandem study

Studies comparing linear and radial EUS for the detection of pancreatic lesions in an asymptomatic population with increased risk for pancreatic cancer are lacking. To compare pancreatic lesion detection rates between radial and linear EUS and to determine the incremental diagnostic yield of a second EUS examination. Randomized controlled tandem study. Five academic centers in the United States. Asymptomatic high-risk individuals (HRIs) for pancreatic cancer undergoing screening EUS. Linear and radial EUS performed in randomized order. Pancreatic lesion detection rate by type of EUS, miss rate of 1 EUS examination, and incremental diagnostic yield of a second EUS examination (second-pass effect). Two hundred seventy-eight HRIs were enrolled, mean age 56 years (43.2%), and 90% were familial pancreatic cancer relatives. Two hundred twenty-four HRIs underwent tandem radial and linear EUS. When we used per-patient analysis, the overall prevalence of any pancreatic lesion was 45%. Overall, 16 of 224 HRIs (7.1%) had lesions missed during the initial EUS that were detected by the second EUS examination. The per-patient lesion miss rate was significantly greater for radial followed by linear EUS (9.8%) than for linear followed by radial EUS (4.5%) (P= .03). When we used per-lesion analysis, 73 of 109 lesions (67%) were detected by radial EUS and 99 of 120 lesions (82%) were detected by linear EUS (P< .001) during the first examination. The overall miss rate for a pancreatic lesion after 1 EUS examination was 47 of 229 (25%). The miss rate was significantly lower for linear EUS compared with radial EUS (17.5% vs 33.0%, P= .007). Most detected pancreatic lesions were not confirmed by pathology. Linear EUS detects more pancreatic lesions than radial EUS. There was a "second-pass effect" with additional lesions detected with a second EUS examination. This effect was significantly greater when linear EUS was used after an initial radial EUS examination.

Diffusion-weighted MR imaging of the pancreas: current status and recommendations.

Advances in image quality over the past few years, mainly due to refinements in hardware and coil systems, have made diffusion-weighted ( DW diffusion weighted ) magnetic resonance (MR) imaging a promising technique for the detection and characterization of pancreatic conditions. DW diffusion weighted MR imaging can be routinely implemented in clinical protocols, as it can be performed relatively quickly, does not require administration of gadolinium-based contrast agents, and enables qualitative and quantitative assessment of tissue diffusivity (diffusion coefficients). In this review, acquisition parameters, postprocessing, and quantification methods applied to pancreatic DW diffusion weighted MR imaging will be discussed. The current common clinical uses of DW diffusion weighted MR imaging (ie, pancreatic lesion detection and characterization) and the less-common applications of DW diffusion weighted MR imaging used for the diagnosis of pancreatic parenchymal diseases will be reviewed. Also, the limitations of the technique, mainly image quality and reproducibility of diffusion parameters, as well as future directions for pancreatic DW diffusion weighted MR imaging will be discussed. The utility of apparent diffusion coefficient ( ADC apparent diffusion coefficient ) measurement for the characterization of pancreatic lesions is now well accepted but there are a number of limitations. Future well-designed, multicenter studies are needed to better determine the most appropriate use of ADC apparent diffusion coefficient in the area of pancreatic disease.

EUS is superior for detection of pancreatic lesions compared with standard imaging in patients with multiple endocrine neoplasia type 1

In multiple endocrine neoplasia type 1 (MEN1), pancreatic neuroendocrine tumors (pNETs) are the leading MEN1-related cause of death. To evaluate EUS and (11)C-5-hydroxytryptophan positron emission tomography ((11)C-5-HTP PET), compared with the recommended screening techniques in MEN1 patients for early detection of pNETs. Cross-sectional study. Tertiary-care university medical center. This study involved 41 patients with a proven MEN1 mutation or with one MEN1 manifestation and a mutation carrier as a first-degree family member, with recent screening by abdominal CT or magnetic resonance imaging (MRI) and somatostatin receptor scintigraphy (SRS). EUS by using a linear Pentax echoendoscope and Hitachi EUB-525 and (11)C-5-HTP PET. Patient-based and lesion-based positivity for pNET was calculated for all imaging techniques. The McNemar test was used to compare the yield of the 4 imaging techniques. In 35 of 41 patients, 107 pancreatic lesions were detected in total. EUS detected 101 pancreatic lesions in34 patients, (11)C-5-HTP PET detected 35 lesions in 19 patients, and CT/MRI+ SRS detected 32 lesions in 18patients (P< .001). (11)C-5-HTP PET performed similarly to CT/MRI+ SRS and better compared with SRS only (13 lesions in 12 patients), both at a patient-based and lesion-based level (P< .05). Single-center study. EUS is superior to CT/MRI+ SRS for pancreatic lesion detection in patients with MEN1. In thissetting, (11)C-5-HTP PET is not useful. We recommend EUS as the first-choice pancreas imaging technique in patients with MEN1. ( NTR1668.).

Detection of pancreatic lesions in asymptomatic risk individuals by MRI with MRCP? a prospective study in Taiwan

s / Pancreatology 14 (2014) S1eS129 S46 was high as 32%, but it was not statistically significant. The majority (88%) of pancreatic cancer patients with new-onset DM had symptoms. Conclusion: Diabetes is very common (41%) in pancreatic cancer. Our analysis did not reveal that pancreatic cancer patients diagnosed in association with new-onset DM had lower disease stage than longstanding DM or non-DM patients.