Prospective evaluation of reader performance on MDCT in characterization of cystic pancreatic lesions and prediction of cyst biologic aggressiveness. AJR Am J Roentgenol. 2011;197:W53-W61. [PMID: 21700995 DOI: 10.2214/ajr.10.5866]

Role of artificial intelligence in the characterization of indeterminate pancreatic head mass and its usefulness in preoperative diagnosis

Artificial intelligence (AI) has been used in various fields of day-to-day life and its role in medicine is immense. Understanding of oncology has been improved with the introduction of AI which helps in diagnosis, treatment planning, management, prognosis, and follow-up. It also helps to identify high-risk groups who can be subjected to timely screening for early detection of malignant conditions. It is more important in pancreatic cancer as it is one of the major causes of cancer-related deaths worldwide and there are no specific early features (clinical and radiological) for diagnosis. With improvement in imaging modalities (computed tomography, magnetic resonance imaging, endoscopic ultrasound), most often clinicians were being challenged with lesions that were difficult to diagnose with human competence. AI has been used in various other branches of medicine to differentiate such indeterminate lesions including the thyroid gland, breast, lungs, liver, adrenal gland, kidney, etc. In the case of pancreatic cancer, the role of AI has been explored and is still ongoing. This review article will focus on how AI can be used to diagnose pancreatic cancer early or differentiate it from benign pancreatic lesions, therefore, management can be planned at an earlier stage.

Artificial intelligence for the detection of pancreatic lesions

PURPOSE

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]) for the detection of pancreatic cancer and pancreatic cystic lesions.

METHODS

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 images to detect pancreatic ductal adenocarcinoma (PDAC) or pancreatic cystic lesions (PCLs).

RESULTS

We found 20 studies meeting our inclusion criteria. Most of the AI-based systems used were convolutional neural networks. Ten studies addressed the use of AI to detect PDAC, eight studies aimed to detect and classify PCLs, and 4 aimed to predict the presence of high-grade dysplasia or cancer.

CONCLUSION

AI techniques have shown to be a promising tool which is expected to be helpful for most radiologists' tasks. However, methodologic concerns must be addressed, and prospective clinical studies should be carried out before implementation in clinical practice.

Radiomics in pancreatic cancer for oncologist: Present and future

Radiomics is changing the world of medicine and more specifically the world of oncology. Early diagnosis and treatment improve the prognosis of patients with cancer. After treatment, the evaluation of the response will determine future treatments. In oncology, every change in treatment means a loss of therapeutic options and this is key in pancreatic cancer. Radiomics has been developed in oncology in the early diagnosis and differential diagnosis of benign and malignant lesions, in the evaluation of response, in the prediction of possible side effects, marking the risk of recurrence, survival and prognosis of the disease. Some studies have validated its use to differentiate normal tissues from tumor tissues with high sensitivity and specificity, and to differentiate cystic lesions and pancreatic neuroendocrine tumor grades with texture parameters. In addition, these parameters have been related to survival in patients with pancreatic cancer and to response to radiotherapy and chemotherapy. This review aimed to establish the current status of the use of radiomics in pancreatic cancer and future perspectives.

[Pancreatic cystic space-occupying lesions-Diagnostics, treatment and follow-up care : Current recommendations taking the current German S3 guidelines on pancreatic cancer into account]

Due to their increased detection pancreatic cystic space-occupying lesions are becoming increasingly relevant in the clinical routine and represent a morphologically and biologically heterogeneous and thus clinically demanding as well as potentially (pre)malignant entity. As a result, recommendations for the diagnostics and treatment of pancreatic cystic tumors have now been incorporated into the current German S3 guidelines on pancreatic cancer. The diagnostics of pancreatic cystic space-occupying lesions are based on the following three elements: collection of relevant clinical information, performance of high-resolution imaging procedures and if diagnostic uncertainty persists, puncture diagnostics. Differentiated diagnostics are of essential importance as these represent the basis for an adequate treatment decision. Pancreatic cystic lesions with a relevant risk of malignant transformation, e.g., main duct intraductal papillary mucinous neoplasms (IPMN), followed by mucinous cystic neoplasms (MCN), solid pseudopapillary neoplasms (SPN) and generally pancreatic cystic lesions with risk factors independent of the entity, should be resected, whereas a differentiated and individualized approach is necessary, especially for branch-duct IPMNs. The serous cystic neoplasms (SCN) have no malignant potential and do not require any treatment if they are asymptomatic. Important principles in surgery of pancreatic cancer, such as adequate surgical resection taking oncological standards into account and standardized appropriate histopathological processing of the specimens as well as intraoperative frozen section analysis also play an important role in pancreatic cystic space-occupying lesions. An annual follow-up seems to be meaningful, especially for IPMNs.

Using Quantitative Imaging for Personalized Medicine in Pancreatic Cancer: A Review of Radiomics and Deep Learning Applications

Simple Summary

With a five-year survival rate of only 3% for the majority of patients, pancreatic cancer is a global healthcare challenge. Radiomics and deep learning, two novel quantitative imaging methods that treat medical images as minable data instead of just pictures, have shown promise in advancing personalized management of pancreatic cancer through diagnosing precursor diseases, early detection, accurate diagnosis, and treatment personalization. Radiomics and deep learning methods aim to collect hidden information in medical images that is missed by conventional radiology practices through expanding the data search and comparing information across different patients. Both methods have been studied and applied in pancreatic cancer. In this review, we focus on the current progress of these two methods in pancreatic cancer and provide a comprehensive narrative review on the topic. With better regulation, enhanced workflow, and larger prospective patient datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through personalized precision medicine.

Abstract

As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization.

Cystic Neoplasms of the Pancreas: Differential Diagnosis and Radiology Correlation

Although the probability of pancreatic cystic neoplasms (PCNs) being detected is raising year by year, their differential diagnosis and individualized treatment are still a challenge in clinical work. PCNs are tumors containing cystic components with different biological behaviors, and their clinical manifestations, epidemiology, imaging features, and malignant risks are different. Some are benign [e.g., serous cystic neoplasms (SCNs)], with a barely possible that turning into malignant, while others display a low or higher malignant risk [e.g., solid pseudopapillary neoplasms (SPNs), intraductal papillary mucinous neoplasms (IPMNs), and mucinous cystic neoplasms (MCNs)]. PCN management should concentrate on preventing the progression of malignant tumors while preventing complications caused by unnecessary surgical intervention. Clinically, various advanced imaging equipment are usually combined to obtain a more reliable preoperative diagnosis. The challenge for clinicians and radiologists is how to accurately diagnose PCNs before surgery so that corresponding surgical methods and follow-up strategies can be developed or not, as appropriate. The objective of this review is to sum up the clinical features, imaging findings and management of the most common PCNs according to the classic literature and latest guidelines.

Single-operator peroral pancreatoscopy in the preoperative diagnostics of suspected main duct intraductal papillary mucinous neoplasms: efficacy and novel insights on complications

Background

Distinguishing intraductal papillary mucinous neoplasms (IPMNs) from other pancreatic cystic lesions is essential since IPMNs carry the risk of becoming malignant. Differentiating the main pancreatic duct involving IPMNs (MD-IPMNs) through conventional imaging is deficient. Single-operator peroral pancreatoscopy (SOPP) represents a promising method offering additional information on suspected lesions in the pancreatic main duct (MD). We aimed to determine the role of SOPP in the preoperative diagnostics of suspected MD-IPMNs and identify factors contributing to SOPP-related complications.

Materials and Methods

In this primarily retrospective study, SOPPs were performed at three high-volume centers on suspected MD-IPMNs. Primary outcome was the clinical impact of SOPP to subsequent patient care. Additionally, we documented post-SOPP complications and analyzed several assumed patient- and procedure-related risk factors.

Results

One hundred and one (101) SOPPs were performed. Subsequent clinical management was affected due to the findings in 86 (85%) cases. Surgery was planned for 29 (29%) patients. A condition other than IPMN explaining MD dilatation was found in 28 (28%) cases. In 35 (35%) cases, follow-up with MRI was continued. Post-SOPP pancreatitis occurred in 20 (20%) patients and one of them was fatal. A decrease in odds of post-SOPP pancreatitis was seen as the MD diameter increases (OR 0.714 for 1.0 mm increase in MD diameter, CI 95% 0.514–0.993, p = 0.045). Furthermore, a correlation between lower MD diameter values and higher severity post-SOPP pancreatitis was seen (T_JT = 599, SE = 116.6, z = − 2.31; p = 0.020). History of pancreatitis after endoscopic retrograde cholangiopancreatography was a confirmed risk factor for post-SOPP pancreatitis. Conclusions between complications and other risk factors could not be drawn.

Conclusion

SOPP aids clinical decision-making in suspected MD-IPMNs. Risk for post-SOPP pancreatitis is not negligible compared to non-invasive imaging methods. The risk for pancreatitis decreases as the diameter of the MD increases.

3D Virtual Pancreatography

We present 3D virtual pancreatography (VP), a novel visualization procedure and application for non-invasive diagnosis and classification of pancreatic lesions, the precursors of pancreatic cancer. Currently, non-invasive screening of patients is performed through visual inspection of 2D axis-aligned CT images, though the relevant features are often not clearly visible nor automatically detected. VP is an end-to-end visual diagnosis system that includes: A machine learning based automatic segmentation of the pancreatic gland and the lesions, a semi-automatic approach to extract the primary pancreatic duct, a machine learning based automatic classification of lesions into four prominent types, and specialized 3D and 2D exploratory visualizations of the pancreas, lesions and surrounding anatomy. We combine volume rendering with pancreas- and lesion-centric visualizations and measurements for effective diagnosis. We designed VP through close collaboration and feedback from expert radiologists, and evaluated it on multiple real-world CT datasets with various pancreatic lesions and case studies examined by the expert radiologists.

Multi-Phase CT-Based Radiomics Nomogram for Discrimination Between Pancreatic Serous Cystic Neoplasm From Mucinous Cystic Neoplasm

Purpose

This study aimed to develop and verify a multi-phase (MP) computed tomography (CT)-based radiomics nomogram to differentiate pancreatic serous cystic neoplasms (SCNs) from mucinous cystic neoplasms (MCNs), and to compare the diagnostic efficacy of radiomics models for different phases of CT scans.

Materials and Methods

A total of 170 patients who underwent surgical resection between January 2011 and December 2018, with pathologically confirmed pancreatic cystic neoplasms (SCN=115, MCN=55) were included in this single-center retrospective study. Radiomics features were extracted from plain scan (PS), arterial phase (AP), and venous phase (VP) CT scans. Algorithms were performed to identify the optimal features to build a radiomics signature (Radscore) for each phase. All features from these three phases were analyzed to develop the MP-Radscore. A combined model comprised the MP-Radscore and imaging features from which a nomogram was developed. The accuracy of the nomogram was evaluated using receiver operating characteristic (ROC) curves, calibration tests, and decision curve analysis.

Results

For each scan phase, 1218 features were extracted, and the optimal ones were selected to construct the PS-Radscore (11 features), AP-Radscore (11 features), and VP-Radscore (12 features). The MP-Radscore (14 features) achieved better performance based on ROC curve analysis than any single phase did [area under the curve (AUC), training cohort: MP-Radscore 0.89, PS-Radscore 0.78, AP-Radscore 0.83, VP-Radscore 0.85; validation cohort: MP-Radscore 0.88, PS-Radscore 0.77, AP-Radscore 0.83, VP-Radscore 0.84]. The combination nomogram performance was excellent, surpassing those of all other nomograms in both the training cohort (AUC, 0.91) and validation cohort (AUC, 0.90). The nomogram also performed well in the calibration and decision curve analyses.

Conclusions

Radiomics for arterial and venous single-phase models outperformed the plain scan model. The combination nomogram that incorporated the MP-Radscore, tumor location, and cystic number had the best discriminatory performance and showed excellent accuracy for differentiating SCN from MCN.

Pancreatic cystic neoplasms and post-inflammatory cysts: interobserver agreement and diagnostic performance of MRI with MRCP

PURPOSE

We aimed to answer several clinically relevant questions; (1) the interobserver agreement, (2) diagnostic performance of MRI with MRCP for (a) branch duct intraductal papillary mucinous neoplasms (BD-IPMN), mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN), (b) distinguishing mucinous (BD-IPMN and MCN) from non-mucinous cysts, and (c) distinguishing three pancreatic cystic neoplasms (PCN) from post-inflammatory cysts (PIC).

METHODS

A retrospective analysis was performed at a tertiary referral center for pancreatic diseases on 71 patients including 44 PCNs and 27 PICs. All PCNs were confirmed by surgical pathology to be 17 BD-IPMNs, 13 MCNs, and 14 SCNs. Main duct and mixed type IPMNs were excluded. Two experienced abdominal radiologists blindly reviewed all the images.

RESULTS

Sensitivity of two radiologists for BD-IPMN, MCN and SCN was 88-94%, 62-69% and 57-64%, specificity of 67-78%, 67-78% and 67-78%, and accuracy of 77-82%, 65-75% and 63-73%, respectively. There was 80% sensitivity, 63-73% specificity, 70-76% accuracy for distinguishing mucinous from non-mucinous neoplasms, and 73-75% sensitivity, 67-78% specificity, 70-76% accuracy for distinguishing all PCNs from PICs. There was moderate-to-substantial interobserver agreement (Cohen's kappa: 0.65).

CONCLUSION

Two experienced abdominal radiologists had moderate-to-high sensitivity, specificity, and accuracy for BD-IPMN, MCN, and SCN. The interobserver agreement was moderate-to-substantial. MRI with MRCP can help workup of incidental pancreatic cysts by distinguishing PCNs from PICs, and premalignant mucinous neoplasms from cysts with no malignant potential.

Computed tomography-based radiomics approach in pancreatic tumors characterization

Radiomics (or texture analysis) is a new imaging analysis technique that allows calculating the distribution of texture features of pixel and voxel values depend on the type of ROI (3D or 2D), their relationships in the image. Depending on the software, up to several thousand texture elements can be obtained. Radiomics opens up wide opportunities for differential diagnosis and prognosis of pancreatic neoplasias. The aim of this review was to highlight the main diagnostic advantages of texture analysis in different pancreatic tumors. The review describes the diagnostic performance of radiomics in different pancreatic tumor types, application methods, and problems. Texture analysis in PDAC is able to predict tumor grade and associates with lymphovascular invasion and postoperative margin status. In pancreatic neuroendocrine tumors, texture features strongly correlate with differentiation grade and allows distinguishing it from the intrapancreatic accessory spleen. In pancreatic cystic lesions, radiomics is able to accurately differentiate MCN from SCN and distinguish clinically insignificant lesions from IPMNs with advanced neoplasia. In conclusion, the use of the CT radiomics approach provides a higher diagnostic performance of CT imaging in pancreatic tumors differentiation and prognosis. Future studies should be carried out to improve accuracy and facilitate radiomics workflow in pancreatic imaging.

Cystic pancreatic lesions: MR imaging findings and management

Cystic pancreatic lesions (CPLs) are frequently casual findings in radiological examinations performed for other reasons in patients with unrelated symptoms. As they require different management according to their histological nature, differential diagnosis is essential. Radiologist plays a key role in the diagnosis and management of these lesions as imaging is able to correctly characterize most of them and thus address to a correct management. The first step for a correct characterization is to look for a communication between the CPLs and the main pancreatic duct, and then, it is essential to evaluate the morphology of the lesions. Age, sex and a history of previous pancreatic pathologies are important information to be used in the differential diagnosis. As some CPLs with different pathologic backgrounds can show the same morphological findings, differential diagnosis can be difficult, and thus, the final diagnosis can require other techniques, such as endoscopic ultrasound, endoscopic ultrasound-fine needle aspiration and endoscopic ultrasound-through the needle biopsy, and multidisciplinary management is important for a correct management.

Application of CT-Based Radiomics in Discriminating Pancreatic Cystadenomas From Pancreatic Neuroendocrine Tumors Using Machine Learning Methods

Objectives

The purpose of this study aimed at investigating the reliability of radiomics features extracted from contrast-enhanced CT in differentiating pancreatic cystadenomas from pancreatic neuroendocrine tumors (PNETs) using machine-learning methods.

Methods

In this study, a total number of 120 patients, including 66 pancreatic cystadenomas patients and 54 PNETs patients were enrolled. Forty-eight radiomic features were extracted from contrast-enhanced CT images using LIFEx software. Five feature selection methods were adopted to determine the appropriate features for classifiers. Then, nine machine learning classifiers were employed to build predictive models. The performance of the forty-five models was evaluated with area under the curve (AUC), accuracy, sensitivity, specificity, and F1 score in the testing group.

Results

The predictive models exhibited reliable ability of differentiating pancreatic cystadenomas from PNETs when combined with suitable selection methods. A combination of DC as the selection method and RF as the classifier, as well as Xgboost+RF, demonstrated the best discriminative ability, with the highest AUC of 0.997 in the testing group.

Conclusions

Radiomics-based machine learning methods might be a noninvasive tool to assist in differentiating pancreatic cystadenomas and PNETs.

Visual Analytics of a Computer-Aided Diagnosis System for Pancreatic Lesions

Machine learning is a powerful and effective tool for medical image analysis to perform computer-aided diagnosis (CAD). Having great potential in improving the accuracy of a diagnosis, CAD systems are often analyzed in terms of the final accuracy, leading to a limited understanding of the internal decision process, impossibility to gain insights, and ultimately to skepticism from clinicians. We present a visual analytics approach to uncover the decision-making process of a CAD system for classifying pancreatic cystic lesions. This CAD algorithm consists of two distinct components: random forest (RF), which classifies a set of predefined features, including demographic features, and a convolutional neural network (CNN), which analyzes radiological (imaging) features of the lesions. We study the class probabilities generated by the RF and the semantical meaning of the features learned by the CNN. We also use an eye tracker to better understand which radiological features are particularly useful for a radiologist to make a diagnosis and to quantitatively compare with the features that lead the CNN to its final classification decision. Additionally, we evaluate the effects and benefits of supplying the CAD system with a case-based visual aid in a second-reader setting.

Artificial intelligence for the management of pancreatic diseases

Novel artificial intelligence techniques are emerging in all fields of healthcare, including gastroenterology. The aim of this review is to give an overview of artificial intelligence applications in the management of pancreatic diseases. We performed a systematic literature search in PubMed and Medline up to May 2020 to identify relevant articles. Our results showed that the development of machine-learning based applications is rapidly evolving in the management of pancreatic diseases, guiding precision medicine in clinical, endoscopic and radiologic settings. Before implementation into clinical practice, further research should focus on the external validation of novel techniques, clarifying the accuracy and robustness of these models.

Diagnostic approaches for pancreatic cystic lesions

BACKGROUND

Cystic lesions of the pancreas (PCLs) may be inflammatory or proliferative and making an accurate and timely pre-operative diagnosis remains a significant clinical challenge. This is principally due to the heterogeneity of the pathological processes involved. PCLs constitute an entity with diverse histology and although infrequent, the possible potential for malignant transformation of these lesions and the opportunity for curative surgery mandates that our diagnostic approaches are up to date and evidence based. In addition, improved diagnostic accuracy is crucial to prevent unnecessary surgical procedures with the inevitable associated morbidity.

METHODS

This narrative review examines the current diagnostic benchmarks and identifies novel diagnostic techniques that warrant further consideration, a number of which are beginning to be included in routine clinical practice when these PCLs are being investigated. A computerized search was made of MEDLINE, EMBASE and PubMed using the search words 'diagnostic approaches to pancreatic cystic lesions'. All relevant articles in English language or with an English abstract were retrieved and additionally cross referenced.

CONCLUSION

The increasing accuracy of available imaging techniques together with the wider availability of endoluminal ultrasound and the development of additional novel methods to assess PCLs presents an opportunity to significantly improve the pre-operative diagnosis rate. This is essential to classify the type of PCL and hence guide the management particularly with lesions where there is a likelihood of progression to more serious pathology. We have highlighted the need for a comprehensive and standardized algorithm for the diagnosis and management of PCLs.

[Indications for the Surgical Management of Pancreatic Cystic Lesions]

A steady improvement in modern imaging as well as increasing age in society have led to an increasing number of cystic pancreatic tumours being detected. Pancreatic cysts are a clinically challenging entity because they span a broad biological spectrum and their differentiation is often difficult, especially in small tumours. Therefore, they require a differentiated indication for indication of surgery. To determine recommendations for the surgical indication in cystic tumours of the pancreas, a quality committee for pancreatic diseases of the German Society for General and Visceral Surgery performed a systematic literature search and created this review. Based on the current evidence, signs of malignancy and high-risk criteria (icterus due to cystic pancreatic duct obstruction in the bile duct, enhancing mural nodules ≥ 5 mm or solid components in the cyst or pancreatic duct ≥ 10 mm), as well as symptoms, are a surgical indication, independently of the cyst entity (except pseudocysts). If the entity of the pancreatic cyst is detectable by diagnostic imaging, all main duct IPMN and IPMN of the mixed type, all MCN > 4 cm and all SPN should be resected. SCN and branch-duct IPMN without worrisome features do not constitute an indication for surgery. The indication of operation in branch-duct IPMN with relative risk criteria and MCN < 4 cm is the subject of current discussions and should be individualised. By defining indication recommendations, the present work aims to improve the indication quality in cystic pancreatic tumours. However, the surgical indication should always be individualised, taking into account age, comorbidities and the patient's wishes.

Comparative Diagnostic Evaluation with Contrast-Enhanced Ultrasound, Computed Tomography and Magnetic Resonance Imaging in Patients with Pancreatic Cystic Neoplasms

Purpose

The purpose of our study was to evaluate the role of contrast-enhanced ultrasound (CEUS) with magnetic resonance imaging (MRI) and computed tomography (CT) in the pathological diagnosis of pancreatic cystic neoplasms (PCNs).

Methods

A total of 90 patients (66 women, 24 men) aged 18–71 years were studied prospectively. CEUS was performed in all patients, whereas MRI was performed in 85 patients and CT in 69 patients. We analyzed the sensitivity and accuracy of these three imaging modalities to diagnose the PCNs. Neoplasm size, location, shape, intralesional mural nodules, septa and duct dilatation were also assessed by different radiologists.

Results

There were no significant differences in sensitivity for discriminating PCNs from pancreatic cystic lesions between CEUS and MRI (p=0.614) or between CEUS and CT (p=0.479). The diagnostic accuracy of CEUS for classifying PCNs was 64.4% (58/90), which was higher than that of CT (53.6%, 37/69, P=0.017), and lower than that of MRI (70.6%, 60/85, p=0.791). Regarding tumor size for lesions larger than 3 cm, CEUS was superior to CT in differentiating the specific type of PCN (p=0.041), and CEUS had the same value as MRI (p=0.774). Furthermore, CEUS is valuable for precisely characterizing internal structures, for instance, septa (p=0.003, compared with CT; p=0.443, compared with MRI) and nodules (p= 0.018, compared with CT; p=0.033, compared with MRI). The number of septa (p=0.033) and cyst morphology (p=0.016) were meaningful indicators in differentiating serous and mucinous adenoma. There was no significant difference in evaluating size and detecting duct dilatation among the three imaging methods.

Conclusion

CEUS compares favorably with MRI in displaying the inner structure of PCNs and offers advantages over CT. CEUS can contribute in an important way to the diagnosis of pancreatic cystic neoplasms.

Radiomics in stratification of pancreatic cystic lesions: Machine learning in action

Pancreatic cystic lesions (PCLs) are well-known precursors of pancreatic cancer. Their diagnosis can be challenging as their behavior varies from benign to malignant disease. Precise and timely management of malignant pancreatic cysts might prevent transformation to pancreatic cancer. However, the current consensus guidelines, which rely on standard imaging features to predict cyst malignancy potential, are conflicting and unclear. This has led to an increased interest in radiomics, a high-throughput extraction of comprehensible data from standard of care images. Radiomics can be used as a diagnostic and prognostic tool in personalized medicine. It utilizes quantitative image analysis to extract features in conjunction with machine learning and artificial intelligence (AI) methods like support vector machines, random forest, and convolutional neural network for feature selection and classification. Selected features can then serve as imaging biomarkers to predict high-risk PCLs. Radiomics studies conducted heretofore on PCLs have shown promising results. This cost-effective approach would help us to differentiate benign PCLs from malignant ones and potentially guide clinical decision-making leading to better utilization of healthcare resources. In this review, we discuss the process of radiomics, its myriad applications such as diagnosis, prognosis, and prediction of therapy response. We also discuss the outcomes of studies involving radiomic analysis of PCLs and pancreatic cancer, and challenges associated with this novel field along with possible solutions. Although these studies highlight the potential benefit of radiomics in the prevention and optimal treatment of pancreatic cancer, further studies are warranted before incorporating radiomics into the clinical decision support system.

Computer-Aided Diagnosis of Pancreas Serous Cystic Neoplasms: A Radiomics Method on Preoperative MDCT Images

OBJECTIVE

Our aim was to propose a preoperative computer-aided diagnosis scheme to differentiate pancreatic serous cystic neoplasms from other pancreatic cystic neoplasms, providing supportive opinions for clinicians and avoiding overtreatment.

MATERIALS AND METHODS

In this retrospective study, 260 patients with pancreatic cystic neoplasm were included. Each patient underwent a multidetector row computed tomography scan and pancreatic resection. In all, 200 patients constituted a cross-validation cohort, and 60 patients formed an independent validation cohort. Demographic information, clinical information, and multidetector row computed tomography images were obtained from Picture Archiving and Communication Systems. The peripheral margin of each neoplasm was manually outlined by experienced radiologists. A radiomics system containing 24 guideline-based features and 385 radiomics high-throughput features was designed. After the feature extraction, least absolute shrinkage selection operator regression was used to select the most important features. A support vector machine classifier with 5-fold cross-validation was applied to build the diagnostic model. The independent validation cohort was used to validate the performance.

RESULTS

Only 31 of 102 serous cystic neoplasm cases in this study were recognized correctly by clinicians before the surgery. Twenty-two features were selected from the radiomics system after 100 bootstrapping repetitions of the least absolute shrinkage selection operator regression. The diagnostic scheme performed accurately and robustly, showing the area under the receiver operating characteristic curve = 0.767, sensitivity = 0.686, and specificity = 0.709. In the independent validation cohort, we acquired similar results with receiver operating characteristic curve = 0.837, sensitivity = 0.667, and specificity = 0.818.

CONCLUSION

The proposed radiomics-based computer-aided diagnosis scheme could increase preoperative diagnostic accuracy and assist clinicians in making accurate management decisions.

Role of Radiological Imaging in the Diagnosis and Characterization of Pancreatic Cystic Lesions: A Systematic Review

The evidence on the ability of radiological tests to predict a specific diagnosis and also their aptitude in identifying pathological markers indicative of malignancy in cystic lesions of the pancreas remains inconclusive. We conducted a systematic review on MEDLINE for the use of computed tomography (CT), magnetic resonance imaging, and positron emission tomography/CT (PET/CT) in the diagnosis and characterization of these cysts. The accuracy of CT scan for reaching a specific diagnosis was 39% to 61.4%, whereas its accuracy for differentiating benign from malignant lesions was 61.9% to 80%. Magnetic resonance imaging showed a better accuracy in identifying a specific diagnosis of 50% to 86%, whereas its accuracy in differentiating benign from malignant lesions was 55.6% to 87%. The use of magnetic resonance imaging was superior to CT scan in identifying septations, mural nodules, and ductal communication. The sensitivity of PET/CT in diagnosing malignancy was 85.7% to 100% with a reported accuracy of 88% to 95%. The evidence gathered from this review suggests that the adequacy of CT imaging in full characterization of pancreatic cysts is suboptimal, and therefore a low threshold for supplementary imaging is advised. The use of PET/CT should be considered in high-risk patients with equivocal findings.

Current concepts in molecular genetics and management guidelines for pancreatic cystic neoplasms: an essential update for radiologists

Cystic neoplasms in the pancreas are encountered frequently on imaging, often detected incidentally during evaluation for other conditions. They can have a variety of clinical and imaging presentations, and similarly, wide-ranging prognostic and treatment implications. In the majority, imaging helps in diagnosis of pancreatic cystic neoplasms (PCNs) and guides management decisions. But, a significant minority of the PCNs remain indeterminate. There have been multiple recent advances in biomarkers and molecular genetics which will likely prove helpful in risk stratification of PCNs. Several prominent national and international societies, as well as consensus groups have put forth recommendations to help guide management of PCNs. The purpose of this article is to discuss the role of imaging in evaluation of PCNs, review the recent advances in molecular genetics and pancreatic cyst fluid analysis, and analyze the pros and cons of major evidence-based and consensus guidelines for management of PCNs.

New horizons in the endoscopic ultrasonography-based diagnosis of pancreatic cystic lesions

Pancreatic cystic lesions (PCLs) are increasingly being identified because of the widespread use of high-resolution abdominal imaging. These cysts encompass a spectrum from malignant disease to benign lesions, and therefore, accurate diagnosis is crucial to determine the best management strategy, either surgical resection or surveillance. However, the current standard of diagnosis is not accurate enough due to limitations of imaging and tissue sampling techniques, which entail the risk of unnecessary burdensome surgery for benign lesions or missed opportunities of prophylactic surgery for potentially malignant PCLs. In the last decade, endoscopic innovations based on endoscopic ultrasonography (EUS) imaging have emerged, aiming to overcome the present limitations. These new EUS-based technologies are contrast harmonic EUS, needle-based confocal endomicroscopy, through-the-needle cystoscopy and through-the needle intracystic biopsy. Here, we present a comprehensive and critical review of these emerging endoscopic tools for the diagnosis of PCLs, with a special emphasis on feasibility, safety and diagnostic performance.

Radiological Workup of Cystic Neoplasms of the Pancreas

Pancreatic cystic lesions are being detected with increasing frequency because of increased use and improved quality of cross-sectional imaging techniques. Pancreatic cystic lesions encompass non-neoplastic lesions (such as pancreatitis-related collections) and neoplastic tumors. Common cystic pancreatic neoplasms include serous cystadenomas, mucinous cystic neoplasms, intraductal papillary mucinous neoplasms, and solid pseudopapillary tumors. These cystic pancreatic neoplasms may have typical morphology, but at times show overlapping imaging features on cross-sectional examinations. This article reviews the classical and atypical imaging features of commonly encountered cystic pancreatic neoplasms and presents the limitations of current cross-sectional imaging techniques in accurately classifying pancreatic cystic lesions.

Advances in Pancreatic CT Imaging

OBJECTIVE

The purpose of this article is to discuss the advances in CT acquisition and image postprocessing as they apply to imaging the pancreas and to conceptualize the role of radiogenomics and machine learning in pancreatic imaging.

CONCLUSION

CT is the preferred imaging modality for assessment of pancreatic diseases. Recent advances in CT (dual-energy CT, CT perfusion, CT volumetry, and radiogenomics) and emerging computational algorithms (machine learning) have the potential to further increase the value of CT in pancreatic imaging.

Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms

Intraductal papillary mucinous neoplasms (IPMNs) are pancreatic cancer precursors incidentally discovered by cross-sectional imaging. Consensus guidelines for IPMN management rely on standard radiologic features to predict pathology, but they lack accuracy. Using a retrospective cohort of 38 surgically-resected, pathologically-confirmed IPMNs (20 benign; 18 malignant) with preoperative computed tomography (CT) images and matched plasma-based ‘miRNA genomic classifier (MGC)’ data, we determined whether quantitative ‘radiomic’ CT features (+/- the MGC) can more accurately predict IPMN pathology than standard radiologic features ‘high-risk’ or ‘worrisome’ for malignancy. Logistic regression, principal component analyses, and cross-validation were used to examine associations. Sensitivity, specificity, positive and negative predictive value (PPV, NPV) were estimated. The MGC, ‘high-risk,’ and ‘worrisome’ radiologic features had area under the receiver operating characteristic curve (AUC) values of 0.83, 0.84, and 0.54, respectively. Fourteen radiomic features differentiated malignant from benign IPMNs (p<0.05) and collectively had an AUC=0.77. Combining radiomic features with the MGC revealed an AUC=0.92 and superior sensitivity (83%), specificity (89%), PPV (88%), and NPV (85%) than other models. Evaluation of uncertainty by 10-fold cross-validation retained an AUC>0.80 (0.87 (95% CI:0.84-0.89)). This proof-of-concept study suggests a noninvasive radiogenomic approach may more accurately predict IPMN pathology than ‘worrisome’ radiologic features considered in consensus guidelines.

Intraductal Papillary Mucinous Neoplasms of the Pancreas: Strategic Considerations

Intraductal papillary mucinous neoplasms (IPMN) are cystic neoplasms with the potential for progression to pancreatic cancer. Recognized by the global medical community just over two decades ago, IPMN have gained great epidemiological and clinical relevance thanks to the widespread use of cross-sectional abdominal imaging, which has led to a surge in the number of incidental pancreatic cysts being diagnosed. As our understanding of this disease has improved, we now know that some IPMN have a very elevated risk of cancer and require surgical resection, while others are low-risk lesions and can be followed. The approach to IPMN must therefore strike a balance between preventing the over-utilization of surgery and the timely recognition and treatment of patients with high-risk lesions. Several clinical, radiographic, and laboratory parameters have been proposed to risk-stratify IPMN, leading to the publication of management guidelines that do not always converge in their recommendations. The goal of this clinical therapeutic review is to describe the strategic approach to IPMN at the Massachusetts General Hospital, and how our current understanding, management algorithm, and future directions have been informed by research efforts at our institution and other centers.

Imaging and Screening of Pancreatic Cancer

Given the low disease prevalence of both exocrine and endocrine cancers in the general population, screening is not recommended. However, in as many as 25% of cases there is a precursor lesion or an identifiable genetic predisposition. For these patients at increased risk, screening with imaging is recommended. Multidetector computed tomography, MR imaging or magnetic resonance cholangiopancreatography, and endoscopic ultrasound examination can be used as screening modalities. Recent advances in dual energy CT and total body MR imaging have increased the suitability of these noninvasive modalities as first-line imaging screening options.

Appropriate Interval for Imaging Follow-up of Small Simple Pancreatic Cysts

CONTEXT

The frequency at which patients should undergo follow-up imaging of small pancreatic cysts is problematic because different medical societies have different follow-up guidelines.

OBJECTIVE

To determine whether short-term follow-up of small pancreatic cysts is necessary to detect pancreatic cancer or cystic neoplasia.

DESIGN

We retrospectively reviewed all abdominal magnetic resonance imaging (MRI) studies obtained in a geographically isolated health maintenance organization between January 1, 2012, and December 31, 2014, looking for pancreatic cysts. For each patient with one or more simple cysts, we recorded the size of the largest cyst. For patients with cysts, all their other computed tomography and MRI studies were reviewed to determine any change in size or morphology. The electronic medical record of every patient who underwent MRI was reviewed to determine development of pancreatic cancer.

MAIN OUTCOME MEASURES

Change in cyst size on images.

RESULTS

Of 1946 patients, 342 were found to have at least 1 pancreatic cyst. A total of 228 patients had additional imaging from which to determine rates of change. The mean rate (standard deviation) of change for these cysts was 0.1 ± 2.0 mm/y. None of those cysts measuring 2 cm or smaller on MRI grew more than 5 mm in 2 years.

CONCLUSION

Our data validate the clinical efficacy of obtaining follow-up imaging no sooner than 24 months after the initial detection of a simple pancreatic cyst 2 cm or smaller. Patients with cysts are more likely to have pancreatic cancer, but earlier follow-up imaging would not change their diagnosis of pancreatic cancer.

[Branch duct intraductal papillary mucinous neoplasm - contra resection]

Due to improvements in imaging modalities the diagnosis of branch duct intraductal papillary mucinous neoplasms (BD-IPMN) has been significantly increased in recent years. A BD-IPMN is frequently diagnosed as an incidental finding in asymptomatic patients. The optimal management of BD-IPMN is the subject of controversial discussions. Numerous studies have shown that an individualized therapeutic strategy with a follow-up observation of most BD-IPMNs is feasible and safe, considering age, comorbidities and patient preference. An accurate evaluation of BD-IPMN with a detailed anamnesis, high-resolution imaging techniques and endoscopic ultrasound is necessary. Symptomatic patients as well as patients with so-called high-risk stigmata should undergo resection. Asymptomatic patients with so-called worrisome features can either undergo surveillance or surgical resection, taking age and comorbidities into account. For BD-IPMN patients without high-risk stigmata and worrisome features and showing no symptoms, surveillance of the pancreatic lesion is the preferred approach. The high prevalence of BD-IPMN, limitations in differential diagnostics, an overestimation of the risk of malignancy due to an overrepresentation of symptomatic and suspected BD-IPMN in resected cohorts, an overestimated role of BD-IPMN as precursor lesions for pancreatic carcinoma and evidence of the safety of follow-up surveillance, underline the enormous importance of surveillance. Based on this and considering the background of a notable mortality and morbidity of pancreatic surgery, aggressive management with prophylactic surgical resection is not justified for all BD-IPMN, in particular for low-risk lesions.

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%.

Endoscopic ultrasonography evaluation for pancreatic cysts: Necessity or overkill?

Incidental pancreatic cysts have become gradually more recognized in clinical practice as a result of increased use of transabdominal ultrasound, computed tomography (CT) and magnetic resonance imaging (MRI). These lesions consist of inflammatory cysts (pseudocysts) and pancreatic cystic neoplasms (PCN) which have been classified as benign, premalignant and malignant. The diagnosis and management strategy of incidentally discovered pancreatic cysts can be challenging as the majority of them are PCN and CT or MRI alone may not be sufficient to provide an accurate diagnosis. Endoscopic ultrasound (EUS)-guided fine-needle aspiration provides a method to obtain cyst fluid for analysis and the recently developed EUS-based technology including contrast-enhanced ultrasound, cystoscopy and needle-based confocal laser endomicroscopy allows endosonographers to gain additional useful information. The current data suggest that EUS evaluation of pancreatic cysts offers some benefits especially in cases of inconclusive CT or MRI.

Impact of CT enterography on the diagnosis of small bowel gastrointestinal stromal tumors

OBJECTIVE

Our purpose is to determine the impact of CT enterography on small bowel gastrointestinal stromal tumor (GIST) detection and biologic aggressiveness, and to identify any imaging findings that correlate with biologic aggressiveness.

METHODS

Records of patients with histologically confirmed small bowel GISTs who underwent CT imaging were reviewed. Biologic aggressiveness was based on initial histologic grading (very low, low, intermediate, high grade; or malignant), with upgrade to malignant category if local or distant metastases developed during clinical follow-up. Imaging indications, findings, and type of CT exam were compared with the biologic aggressiveness.

RESULTS

111 small bowel GISTs were identified, with suspected small bowel bleeding being the most common indication (45/111; 40.5%). While the number of malignant GISTs diagnosed by CT remained relatively constant (2-3 per year), the number of non-malignant GISTs increased substantially (mean 1.5/year, 1998-2005; 8.4/year, 2006-2013). In patients with suspected small bowel bleeding, CT enterography identified 33 GISTs (7/33, 21% malignant) compared to 12 GISTs by abdominopelvic CT (6/12, 50% malignant; p < 0.03). Tumor size (p < 0.0001), internal necrosis (p = 0.005), internal air or enteric contrast (p ≤ 0.021), and ulceration (p ≤ 0.021) were significantly associated with high-grade and malignant tumors, and irregular or invasive tumor borders (p < 0.01) was associated with malignant tumors.

CONCLUSION

The detection of small bowel GISTs can increase due to the use of CT enterography in patients with suspected small bowel bleeding. The large majority of small bowel GISTs detected by CT enterography are not malignant.

Imaging modalities for characterising focal pancreatic lesions

BACKGROUND

Increasing numbers of incidental pancreatic lesions are being detected each year. Accurate characterisation of pancreatic lesions into benign, precancerous, and cancer masses is crucial in deciding whether to use treatment or surveillance. Distinguishing benign lesions from precancerous and cancerous lesions can prevent patients from undergoing unnecessary major surgery. Despite the importance of accurately classifying pancreatic lesions, there is no clear algorithm for management of focal pancreatic lesions.

OBJECTIVES

To determine and compare the diagnostic accuracy of various imaging modalities in detecting cancerous and precancerous lesions in people with focal pancreatic lesions.

SEARCH METHODS

We searched the CENTRAL, MEDLINE, Embase, and Science Citation Index until 19 July 2016. We searched the references of included studies to identify further studies. We did not restrict studies based on language or publication status, or whether data were collected prospectively or retrospectively.

SELECTION CRITERIA

We planned to include studies reporting cross-sectional information on the index test (CT (computed tomography), MRI (magnetic resonance imaging), PET (positron emission tomography), EUS (endoscopic ultrasound), EUS elastography, and EUS-guided biopsy or FNA (fine-needle aspiration)) and reference standard (confirmation of the nature of the lesion was obtained by histopathological examination of the entire lesion by surgical excision, or histopathological examination for confirmation of precancer or cancer by biopsy and clinical follow-up of at least six months in people with negative index tests) in people with pancreatic lesions irrespective of language or publication status or whether the data were collected prospectively or retrospectively.

DATA COLLECTION AND ANALYSIS

Two review authors independently searched the references to identify relevant studies and extracted the data. We planned to use the bivariate analysis to calculate the summary sensitivity and specificity with their 95% confidence intervals and the hierarchical summary receiver operating characteristic (HSROC) to compare the tests and assess heterogeneity, but used simpler models (such as univariate random-effects model and univariate fixed-effect model) for combining studies when appropriate because of the sparse data. We were unable to compare the diagnostic performance of the tests using formal statistical methods because of sparse data.

MAIN RESULTS

We included 54 studies involving a total of 3,196 participants evaluating the diagnostic accuracy of various index tests. In these 54 studies, eight different target conditions were identified with different final diagnoses constituting benign, precancerous, and cancerous lesions. None of the studies was of high methodological quality. None of the comparisons in which single studies were included was of sufficiently high methodological quality to warrant highlighting of the results. For differentiation of cancerous lesions from benign or precancerous lesions, we identified only one study per index test. The second analysis, of studies differentiating cancerous versus benign lesions, provided three tests in which meta-analysis could be performed. The sensitivities and specificities for diagnosing cancer were: EUS-FNA: sensitivity 0.79 (95% confidence interval (CI) 0.07 to 1.00), specificity 1.00 (95% CI 0.91 to 1.00); EUS: sensitivity 0.95 (95% CI 0.84 to 0.99), specificity 0.53 (95% CI 0.31 to 0.74); PET: sensitivity 0.92 (95% CI 0.80 to 0.97), specificity 0.65 (95% CI 0.39 to 0.84). The third analysis, of studies differentiating precancerous or cancerous lesions from benign lesions, only provided one test (EUS-FNA) in which meta-analysis was performed. EUS-FNA had moderate sensitivity for diagnosing precancerous or cancerous lesions (sensitivity 0.73 (95% CI 0.01 to 1.00) and high specificity 0.94 (95% CI 0.15 to 1.00), the extremely wide confidence intervals reflecting the heterogeneity between the studies). The fourth analysis, of studies differentiating cancerous (invasive carcinoma) from precancerous (dysplasia) provided three tests in which meta-analysis was performed. The sensitivities and specificities for diagnosing invasive carcinoma were: CT: sensitivity 0.72 (95% CI 0.50 to 0.87), specificity 0.92 (95% CI 0.81 to 0.97); EUS: sensitivity 0.78 (95% CI 0.44 to 0.94), specificity 0.91 (95% CI 0.61 to 0.98); EUS-FNA: sensitivity 0.66 (95% CI 0.03 to 0.99), specificity 0.92 (95% CI 0.73 to 0.98). The fifth analysis, of studies differentiating cancerous (high-grade dysplasia or invasive carcinoma) versus precancerous (low- or intermediate-grade dysplasia) provided six tests in which meta-analysis was performed. The sensitivities and specificities for diagnosing cancer (high-grade dysplasia or invasive carcinoma) were: CT: sensitivity 0.87 (95% CI 0.00 to 1.00), specificity 0.96 (95% CI 0.00 to 1.00); EUS: sensitivity 0.86 (95% CI 0.74 to 0.92), specificity 0.91 (95% CI 0.83 to 0.96); EUS-FNA: sensitivity 0.47 (95% CI 0.24 to 0.70), specificity 0.91 (95% CI 0.32 to 1.00); EUS-FNA carcinoembryonic antigen 200 ng/mL: sensitivity 0.58 (95% CI 0.28 to 0.83), specificity 0.51 (95% CI 0.19 to 0.81); MRI: sensitivity 0.69 (95% CI 0.44 to 0.86), specificity 0.93 (95% CI 0.43 to 1.00); PET: sensitivity 0.90 (95% CI 0.79 to 0.96), specificity 0.94 (95% CI 0.81 to 0.99). The sixth analysis, of studies differentiating cancerous (invasive carcinoma) from precancerous (low-grade dysplasia) provided no tests in which meta-analysis was performed. The seventh analysis, of studies differentiating precancerous or cancerous (intermediate- or high-grade dysplasia or invasive carcinoma) from precancerous (low-grade dysplasia) provided two tests in which meta-analysis was performed. The sensitivity and specificity for diagnosing cancer were: CT: sensitivity 0.83 (95% CI 0.68 to 0.92), specificity 0.83 (95% CI 0.64 to 0.93) and MRI: sensitivity 0.80 (95% CI 0.58 to 0.92), specificity 0.81 (95% CI 0.53 to 0.95), respectively. The eighth analysis, of studies differentiating precancerous or cancerous (intermediate- or high-grade dysplasia or invasive carcinoma) from precancerous (low-grade dysplasia) or benign lesions provided no test in which meta-analysis was performed.There were no major alterations in the subgroup analysis of cystic pancreatic focal lesions (42 studies; 2086 participants). None of the included studies evaluated EUS elastography or sequential testing.

AUTHORS' CONCLUSIONS

We were unable to arrive at any firm conclusions because of the differences in the way that study authors classified focal pancreatic lesions into cancerous, precancerous, and benign lesions; the inclusion of few studies with wide confidence intervals for each comparison; poor methodological quality in the studies; and heterogeneity in the estimates within comparisons.

Incidental pancreatic cystic neoplasms in an asymptomatic healthy population of 21,745 individuals: Large-scale, single-center cohort study

Although incidental pancreatic cystic neoplasms are being diagnosed with increasing frequency, little is known about the accurate prevalence of pancreatic cysts in the general population. The aims of this study were to evaluate the crude prevalence rate of pancreatic cystic neoplasms in asymptomatic healthy adults, and calculate the age- and sex-adjusted nationwide prevalence rate.A total of 21,745 asymptomatic individuals who underwent abdominal computed tomography (CT) as a health screening examination were enrolled between 2003 and 2013 at the Seoul National University Hospital Healthcare System Gangnam Center. Nationwide population data of 2010 were collected from the National Statistical Office, Korea.Incidental pancreatic cystic neoplasms were found in 457 individuals whose mean age was 58.7 years. The types of neoplasms were reviewed by 2 separate designated radiologists and the final diagnosis was made as follows: intraductal papillary mucinous neoplasm: 376 (82%), serous cystic neoplasm: 19 (4%), mucinous cystic neoplasm: 7 (2%), and indeterminate cysts: 55 (12%). Eight cases underwent operation. The crude prevalence rate was 2.1% and the age- and sex-adjusted expected nationwide prevalence was 2.2%. The prevalence increased with age.Here, we reported the first large-scale study among the healthy population to find out the prevalence rate of pancreatic cystic neoplasms; the age- and sex-adjusted prevalence was 2.2%, and increased with age. Further investigations regarding the clinical implications of incidental pancreatic neoplasms are necessary.

Association Between Advances in High-Resolution Cross-Section Imaging Technologies and Increase in Prevalence of Pancreatic Cysts From 2005 to 2014

BACKGROUND & AIMS

Increasingly, pancreatic cysts are discovered incidentally in patients undergoing cross-sectional imaging for nonpancreatic reasons. It is unclear whether this increase is caused by improved detection by progressively more sophisticated cross-sectional imaging techniques or by a true increase in prevalence. We aimed to determine the prevalence of incidental pancreatic cysts in patients undergoing magnetic resonance imaging (MRI) for nonpancreatic indications on successive, increasingly sophisticated MRI systems. Also, we compared prevalence based on the demographic characteristics of the patients.

METHODS

We collected data from MRIs performed at the Mayo Clinic in Florida during the sample months of January and February, from 2005 to 2014. Each patient's clinical chart was reviewed in chronological order to include the first 50 MRIs of each year (500 total). Patients were excluded if they had pancreatic disease including cysts, pancreatic surgery, pancreatic symptoms, pancreatic indication for the imaging study, or previous abdominal MRIs. An expert pancreatic MRI radiologist reviewed each image, looking for incidental pancreatic cysts.

RESULTS

Of the 500 patients analyzed, 208 patients (41.6%) were found to have an incidental cyst. A significant relationship was observed between pancreatic cysts and patient age (P < .0001), diabetes mellitus (P = .001), and nonpancreatic cancer (P = .01), specifically nonmelanoma skin cancer (P = .03) or hepatocellular carcinoma (P = .02). The multivariable model showed a strong association between hardware and software versions and detection of cysts (P < .0001); the old hardware detected pancreatic cysts in 30.3% of patients, whereas the newest hardware detected cysts in 56.3% of patients.

CONCLUSIONS

Based on an analysis of data collected from 2005 through 2014, newer versions of MRI hardware and software corresponded with higher numbers of pancreatic cysts detected. Older age, diabetes, and the presence of nonpancreatic cancer (specifically nonmelanoma skin cancer and hepatocarcinoma) were also associated with the presence of cysts.

Imaging patterns of intraductal papillary mucinous neoplasms of the pancreas: an illustrated discussion of the International Consensus Guidelines for the Management of IPMN

Intraductal papillary mucinous neoplasms (IPMN) are being diagnosed with increasing frequency, necessitating an algorithm to help stratify patients into low- and high-risk groups, for follow-up versus more invasive evaluation. New evidence concerning their natural history and overall risk of malignancy has emerged since the 2006 International Association of Pancreatology consensus guidelines, prompting an update in 2012, that distinguishes radiologic 'worrisome features' from 'high-risk stigmata'. The aim of this article is to illustrate, with case examples, the variable imaging patterns of IPMN and how their radiologic features, such as cyst size and mural nodules, are interpreted in the context of the new 2012 guidelines. The 2012 and 2006 guidelines will be compared and discussed with reference to additional studies that have since been published. Despite these guidelines, lingering uncertainty remains about the natural history of IPMN, a source of unease to both radiologists and referring clinicians alike, mandating further refinement of clinical and radiologic parameters predictive of malignancy. Emerging data regarding the risk of extrapancreatic malignancy, as well as synchronous or metachronous pancreatic ductal adenocarcinoma remote in location from a branch duct IPMN are also reviewed. With the expanding research and evolving understanding of this clinicopathologic entity across the globe, radiologists will continue to play an important role in the management of patients with IPMN.

What Is the Best Way to Identify Malignant Transformation Within Pancreatic IPMN: A Systematic Review and Meta-Analyses

OBJECTIVES

Pancreatic intraductal papillary mucinous neoplasias (IPMNs) represent 25% of all cystic neoplasms and are precursor lesions for pancreatic ductal adenocarcinoma. This study aims to identify the best imaging modality for detecting malignant transformation in IPMN, the sensitivity and specificity of risk features on imaging, and the usefulness of tumor markers in serum and cyst fluid to predict malignancy in IPMN.

METHODS

Databases were searched from November 2006 to March 2014. Pooled sensitivity and specificity of diagnostic techniques/imaging features of suspected malignancy in IPMN using a hierarchical summary receiver operator characteristic (HSROC) approach were performed.

RESULTS

A total of 467 eligible studies were identified, of which 51 studies met the inclusion criteria and 37 of these were incorporated into meta-analyses. The pooled sensitivity and specificity for risk features predictive of malignancy on computed tomography/magnetic resonance imaging were 0.809 and 0.762 respectively, and on positron emission tomography were 0.968 and 0.911. Mural nodule, cyst size, and main pancreatic duct dilation found on imaging had pooled sensitivity for prediction of malignancy of 0.690, 0.682, and 0.614, respectively, and specificity of 0.798, 0.574, and 0.687. Raised serum carbohydrate antigen 19-9 (CA19-9) levels yielded sensitivity of 0.380 and specificity of 0903. Combining parameters yielded a sensitivity of 0.743 and specificity of 0.906.

CONCLUSIONS

PET holds the most promise in identifying malignant transformation within an IPMN. Combining parameters increases sensitivity and specificity; the presence of mural nodule on imaging was the most sensitive whereas raised serum CA19-9 (>37 KU/l) was the most specific feature predictive of malignancy in IPMNs.

Management of Incidental Pancreatic Cystic Lesions

BACKGROUND

Pancreatic cystic lesions (PCL) are common. They are increasingly detected as an incidental finding of transabdominal ultrasound or cross-sectional imaging. In contrast to other parenchymal organs, dysontogenetic pancreatic cysts are extremely rare. In symptomatic patients the most frequent PCL are acute and chronic pseudocysts. The majority of incidental cystic lesions, however, are neoplasias which have different risks of malignancy.

METHODS

PubMed was searched for studies, reviews, meta-analyses, and guidelines using the following key words: ('pancreatic cystic lesions' OR 'cystic pancreatic lesions' OR 'intraductal papillary mucinous neoplasia' OR 'mucinous cystic neoplasia' OR 'pancreatic cyst' OR 'pancreatic pseudocyst') AND (management OR treatment OR outcome OR prognosis OR diagnosis OR imaging OR 'endoscopic ultrasound' EUS-FNA OR EUS OR 'endoscopic ultrasonography' OR CT OR MRI). Retrieved papers were reviewed with regard to the diagnostic and therapeutic management of incidental PCL.

RESULTS

In addition to clinical criteria, transabdominal ultrasonography including contrast-enhanced ultrasonography, cross-sectional radiological imaging, and endoscopic ultrasound (EUS) are used for diagnostic characterization and risk assessment. EUS plays an outstanding role in differential diagnosis and prognostic characterization of incidental PCL. In a single examination it is possible to perform high-resolution morphological description, perfusion imaging, as well as fine-needle aspiration of cyst content, cyst wall, and solid components. An international consensus guideline has defined worrisome and high-risk criteria for the risk assessment of mucinous pancreatic cysts, which are mainly based on the results of EUS and cross-sectional imaging. Nevertheless, despite diagnostic progress and guideline recommendations, differential diagnosis and management decisions remain difficult. This review will discuss problems in and approaches to the diagnosis of incidental PCL.

CONCLUSION

An evidence-based algorithm for the diagnosis of incidental PCL is proposed.

Accuracy of 18F-FDG PET/CT, Multidetector CT, and MR Imaging in the Diagnosis of Pancreatic Cysts: A Prospective Single-Center Study

Accurate diagnosis of the nature of pancreatic cysts is challenging but more important than ever, in part because of the increasing number of incidental cystic findings in the pancreas. Preliminary data suggest that (18)F-FDG PET/CT may have a significant influence on clinical decision making, although its role is still evolving. Our aim was to prospectively compare the accuracy of combined (18)F-FDG PET and contrast-enhanced CT ((18)F-FDG PET/CT), multidetector CT (MDCT), and MR imaging in differentiating malignant from benign pancreatic cysts.

METHODS

Thirty-one consecutive patients with pancreatic cysts were enrolled in the study. They underwent a protocol including (18)F-FDG PET/CT, MDCT, and MR imaging combined with MR cholangiopancreatography, all of which were evaluated in a masked manner. The findings were confirmed macroscopically at surgery or histopathologic analysis (n = 22) or at follow-up (n = 9).

RESULTS

Of the 31 patients, 6 had malignant and 25 had benign lesions. The diagnostic accuracy was 94% for (18)F-FDG PET/CT, compared with 77% and 87% for MDCT (P < 0.05) and MR imaging, respectively. (18)F-FDG PET/CT had a negative predictive value of 100% and a positive predictive value of 75% for pancreatic cysts. The maximum standardized uptake value was significantly higher in malignant (7.4 ± 2.6) than in benign lesions (2.4 ± 0.8) (P < 0.05). When the maximum standardized uptake value was set at 3.6, the sensitivity and specificity were 100% and 88%, respectively. Furthermore, when compared with MDCT and MR imaging, respectively, (18)F-FDG PET/CT altered the clinical management of 5 and 3 patients, respectively.

CONCLUSION

(18)F-FDG PET/CT is an accurate imaging modality for differentiating between benign and malignant pancreatic cysts. We recommend the use of (18)F-FDG PET/CT in the evaluation of diagnostically challenging pancreatic cysts.

Interobserver agreement for detection of malignant features of intraductal papillary mucinous neoplasms of the pancreas on MDCT

OBJECTIVE

The purpose of this retrospective study was to measure interobserver agreement in the assessment of malignant imaging features of intraductal papillary mucinous neoplasms (IPMNs) on MDCT.

MATERIALS AND METHODS

Pancreatic protocol CT studies were reviewed for 84 patients with resected IPMNs. Maximal diameter of the dominant cyst, presence of a mural nodule, presence of a solid component, and diameters of the main pancreatic duct (MPD) and common bile duct (CBD) were measured by four radiologists independently. In each patient, the IPMN was classified into one of three types: main duct, branch duct, or mixed IPMN. Interobserver agreement of lesion features was examined using the intraclass correlation coefficient (ICC) for continuous features and Fleiss kappa for categorical features.

RESULTS

The final dataset included 55 branch duct IPMNs, nine main duct IPMNs, and 20 mixed IPMNs. Moderate agreement (ĸ = 0.458; 95% CI, 0.345-0.564) was observed in assigning branch duct, main duct, or mixed IPMN subtypes. Measurement agreement was substantial to excellent for dominant cyst (ICC = 0.852; 95% CI, 0.777-0.907), MPD (0.753, 0.655-0.837), and CBD (0.608, 0.463-0.724) but only fair to moderate for the detection of the presence of mural nodule (ĸ = 0.284, 0.125-0.432) or solid component (ĸ = 0.405, 0211-0.577).

CONCLUSION

Substantial to excellent interobserver agreement in the measurement of cyst diameter, MPD, and CBD support their use for characterizing malignant features of IPMN on MDCT. However, the subjective interpretation of the presence of solid components and mural nodules by individual radiologists was more variable.

Diagnostic Accuracy of 256-Detector Row Computed Tomography in Detection and Characterization of Incidental Pancreatic Cystic Lesions

Purpose. To assess the diagnostic value of 256-detector row MDCT in the characterization of incidentally detected pancreatic cystic lesions (PCLs). Materials and Methods. We retrospectively reviewed 6389 studies performed on a 256-row detector scanner, wherein ≥1 PCLs were incidentally detected. Images from a total of 192 patients (99 females; age range 31-90 years) were analysed referring to morphologic predictive signs of malignancy, including multifocality, inner septa, wall thickening, and mural enhancing nodules. Results. We evaluated 292 PCLs in 192 patients (solitary in 145 and ≥2 in 47; incidence 2.05%). Size ranged from 3 to 145 mm (mean 15 mm); body was the most common location (87/292; 29.8%). Intralesional septa were detected in 52/292 lesions (17.8%), wall thickening >2 mm in 13 (4.5%), enhancing wall and mural nodules in 15 (5.1%) and 12 (4.1%), respectively. Communication with ductal system was evident in 45 cases. The most common diagnoses, established by histology or imaging analysis, were IPMNs (about 86%), while serous cystic neoplasia (3.7%) and metastases (0.5%) were the less common. Conclusion. MDCT provides detailed features for characterization of PCLs, which are incidentally discovered with increased frequency due to the widespread use of cross-sectional imaging.

Incidental pancreatic cysts: role of magnetic resonance imaging

The widespread adoption of multidetector computed tomography and magnetic resonance imaging (MRI) for evaluation of intraabdominal pathology has resulted to a steady increase in the number of incidentally discovered pancreatic cysts in clinical practice during the last decades. The differential diagnosis of these cysts is broad including pseudocysts, serous cystic neoplasms, mucinous cystic neoplasms, and intraductal papillary mucinous neoplasms. The MRI has an important role both in the initial characterization of incidentally detected pancreatic cysts and the follow-up of these lesions and has become an integral part of the diagnostic algorithm for pancreatic cysts at many institutions. The inherent soft-tissue contrast of magnetic resonance cholangiopancreatography provides the vehicle for providing a specific diagnosis in many pancreatic cysts. Furthermore, an MRI-based characterization of pancreatic cysts allows for selection of those cysts that are more likely to benefit from endoscopic ultrasound and fine-needle aspiration for analysis of the fluid contents. Moreover, small asymptomatic incidental pancreatic cysts without concerning MRI features such as internal septae and/or nodularity may be safely followed with serial imaging. The lack of risk associated to repeated exposure to ionizing radiation and its ability to characterize pancreatic cysts are strong arguments for selecting MRI as the preferred imaging modality for following up these lesions. However, the recommendations for imaging follow-up continue to evolve, and several of the proposed guidelines are reviewed in this manuscript.

Is it safe to follow side branch IPMNs?

Management of Bd-IPMN remains challenging. Critical appraisal of the published literature reveals that the actual treatment of what is presumed to be Bd-IPMN remains unsatisfactory, with a high rate of surgically overtreated patients. Until we accrue more precise knowledge of the natural history of Bd-IPMN, management of patients with this presumed diagnosis should be individually tailored and preferably carried out in centers with a high expertise. For now, the authors strongly think that the old guidelines should be followed in most patients because these have proven to correctly identify lesions that can be safely followed. Although the new guidelines allow for follow-up of lesions greater than 3 cm, and for the most part this is safe, they should be used cautiously in younger patients because very close surveillance would be required for their long remaining lifespan.

Moving beyond morphology: new insights into the characterization and management of cystic pancreatic lesions

The frequency of detection of cystic pancreatic lesions with cross-sectional imaging, particularly with multidetector computed tomography, magnetic resonance (MR) imaging, and MR cholangiopancreatography, is increasing, and many of these cystic pancreatic lesions are being detected incidentally in asymptomatic patients. Because there is considerable overlap in the cross-sectional imaging findings of cystic pancreatic lesions, and because many of these lesions being detected are smaller than 3 cm in diameter and lack any specific cross-sectional imaging features, it has become difficult to make informed decisions about patient management when the precise diagnosis remains uncertain. This article presents the limitations of cross-sectional imaging in patients with cystic pancreatic lesions, details advances in knowledge of the genomic and epigenomic changes that lead to progression of carcinogenesis, outlines the current understanding of the natural history of mucinous cystic lesions, and includes the current use and future potential of novel tumor markers and molecular analysis to characterize cystic pancreatic lesions more precisely. The need to move beyond cross-sectional imaging morphology and toward the use of new techniques to diagnose these lesions accurately is emphasized. An algorithm that uses these techniques is proposed and will hopefully lead to improved patient management.