Focal cystic pancreatic lesions: assessing variation in radiologists' management recommendations

Recommendations for Additional Imaging on Head and Neck Imaging Examinations: Interradiologist Variation and Associated Factors

BACKGROUND. A paucity of relevant guidelines may lead to pronounced variation among radiologists in issuing recommendations for additional imaging (RAI) for head and neck imaging. OBJECTIVE. The purpose of this article was to explore associations of RAI for head and neck imaging examinations with examination, patient, and radiologist factors and to assess the role of individual radiologist-specific behavior in issuing such RAI. METHODS. This retrospective study included 39,200 patients (median age, 58 years; 21,855 women, 17,315 men, 30 with missing sex information) who underwent 39,200 head and neck CT or MRI examinations, interpreted by 61 radiologists, from June 1, 2021, through May 31, 2022. A natural language processing (NLP) tool with manual review of NLP results was used to identify RAI in report impressions. Interradiologist variation in RAI rates was assessed. A generalized mixed-effects model was used to assess associations between RAI and examination, patient, and radiologist factors. RESULTS. A total of 2943 (7.5%) reports contained RAI. Individual radiologist RAI rates ranged from 0.8% to 22.0% (median, 7.1%; IQR, 5.2-10.2%), representing a 27.5-fold difference between minimum and a maximum values and 1.8-fold difference between 25th and 75th percentiles. In multivariable analysis, RAI likelihood was higher for CTA than for CT examinations (OR, 1.32), for examinations that included a trainee in report generation (OR, 1.23), and for patients with self-identified race of Black or African American versus White (OR, 1.25); was lower for male than female patients (OR, 0.90); and was associated with increasing patient age (OR, 1.09 per decade) and inversely associated with radiologist years since training (OR, 0.90 per 5 years). The model accounted for 10.9% of the likelihood of RAI. Of explainable likelihood of RAI, 25.7% was attributable to examination, patient, and radiologist factors; 74.3% was attributable to radiologist-specific behavior. CONCLUSION. Interradiologist variation in RAI rates for head and neck imaging was substantial. RAI appear to be more substantially associated with individual radiologist-specific behavior than with measurable systemic factors. CLINICAL IMPACT. Quality improvement initiatives, incorporating best practices for incidental findings management, may help reduce radiologist preference-sensitive decision-making in issuing RAI for head and neck imaging and associated care variation.

International evidence-based Kyoto guidelines for the management of intraductal papillary mucinous neoplasm of the pancreas

This study group aimed to revise the 2017 international consensus guidelines for the management of intraductal papillary mucinous neoplasm (IPMN) of the pancreas, and mainly focused on five topics; the revision of high-risk stigmata (HRS) and worrisome features (WF), surveillance of non-resected IPMN, surveillance after resection of IPMN, revision of pathological aspects, and investigation of molecular markers in cyst fluid. A new development from the prior guidelines is that systematic reviews were performed for each one of these topics, and published separately to provide evidence-based recommendations. One of the highlights of these new "evidence-based guidelines" is to propose a new management algorithm, and one major revision is to include into the assessment of HRS and WF the imaging findings from endoscopic ultrasound (EUS) and the results of cytological analysis from EUS-guided fine needle aspiration technique, when this is performed. Another key element of the current guidelines is to clarify whether lifetime surveillance for small IPMNs is required, and recommends two options, "stop surveillance" or "continue surveillance for possible development of concomitant pancreatic ductal adenocarcinoma", for small unchanged BD-IPMN after 5 years surveillance. Several other points are also discussed, including identifying high-risk features for recurrence in patients who underwent resection of non-invasive IPMN with negative surgical margin, summaries of the recent observations in the pathology of IPMN. In addition, the emerging role of cyst fluid markers that can aid in distinguishing IPMN from other pancreatic cysts and identify those IPMNs that harbor high-grade dysplasia or invasive carcinoma is discussed.

Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application

Radiomics allows the extraction of quantitative imaging features from clinical magnetic resonance imaging (MRI) and computerized tomography (CT) studies. The advantages of radiomics have primarily been exploited in oncological applications, including better characterization and staging of oncological lesions and prediction of patient outcomes and treatment response. The potential introduction of radiomics in the clinical setting requires the establishment of a standardized radiomics pipeline and a quality assurance program. Radiomics and texture analysis of the liver have improved the differentiation of hypervascular lesions such as adenomas, focal nodular hyperplasia, and hepatocellular carcinoma (HCC) during the arterial phase, and in the pretreatment determination of HCC prognostic factors (e.g., tumor grade, microvascular invasion, Ki-67 proliferation index). Radiomics of pancreatic CT and MR images has enhanced pancreatic ductal adenocarcinoma detection and its differentiation from pancreatic neuroendocrine tumors, mass-forming chronic pancreatitis, or autoimmune pancreatitis. Radiomics can further help to better characterize incidental pancreatic cystic lesions, accurately discriminating benign from malignant intrapancreatic mucinous neoplasms. Nonetheless, despite their encouraging results and exciting potential, these tools have yet to be implemented in the clinical setting. This non-systematic review will describe the essential steps in the implementation of the radiomics and feature extraction workflow from liver and pancreas CT and MRI studies for their potential clinical application. A succinct overview of reported radiomics applications in the liver and pancreas and the challenges and limitations of their implementation in the clinical setting is also discussed, concluding with a brief exploration of the future perspectives of radiomics in the gastroenterology field.

Surveillance of Pancreatic Cystic Neoplasms

Pancreatic cystic neoplasms (PCNs) are increasingly detected because of the widespread use of cross-sectional imaging and overall aging population. While the majority of these cysts are benign, some can progress to advanced neoplasia (defined as high-grade dysplasia and invasive cancer). As the only widely accepted treatment for PCNs with advanced neoplasia is surgical resection, accurate preoperative diagnosis, and stratification of malignant potential for deciding about surgery, surveillance or doing nothing remains a clinical challenge. Surveillance strategies for pancreatic cysts (PCNs) combine clinical evaluation and imaging to assess changes in cyst morphology and symptoms that may indicate advanced neoplasia. PCN surveillance heavily relies on various consensus clinical guidelines that focus on high-risk morphology, surgical indications, and surveillance intervals and modalities. This review will focus on current concepts in the surveillance of newly diagnosed PCNs, especially on low-risk presumed intraductal papillary mucinous neoplasms (those without worrisome features and high-risk stigmata), and appraise current clinical surveillance guidelines.

Natural language processing in radiology: Clinical applications and future directions

Natural language processing (NLP) is a wide range of techniques that allows computers to interact with human text. Applications of NLP in everyday life include language translation aids, chat bots, and text prediction. It has been increasingly utilized in the medical field with increased reliance on electronic health records. As findings in radiology are primarily communicated via text, the field is particularly suited to benefit from NLP based applications. Furthermore, rapidly increasing imaging volume will continue to increase burden on clinicians, emphasizing the need for improvements in workflow. In this article, we highlight the numerous non-clinical, provider focused, and patient focused applications of NLP in radiology. We also comment on challenges associated with development and incorporation of NLP based applications in radiology as well as potential future directions.

Deep Learning to Detect Pancreatic Cystic Lesions on Abdominal Computed Tomography Scans: Development and Validation Study

BACKGROUND

Pancreatic cystic lesions (PCLs) are frequent and underreported incidental findings on computed tomography (CT) scans and can evolve to pancreatic cancer-the most lethal cancer, with less than 5 months of life expectancy.

OBJECTIVE

The aim of this study was to develop and validate an artificial deep neural network (attention gate U-Net, also named "AGNet") for automated detection of PCLs. This kind of technology can help radiologists to cope with an increasing demand of cross-sectional imaging tests and increase the number of PCLs incidentally detected, thus increasing the early detection of pancreatic cancer.

METHODS

We adapted and evaluated an algorithm based on an attention gate U-Net architecture for automated detection of PCL on CTs. A total of 335 abdominal CTs with PCLs and control cases were manually segmented in 3D by 2 radiologists with over 10 years of experience in consensus with a board-certified radiologist specialized in abdominal radiology. This information was used to train a neural network for segmentation followed by a postprocessing pipeline that filtered the results of the network and applied some physical constraints, such as the expected position of the pancreas, to minimize the number of false positives.

RESULTS

Of 335 studies included in this study, 297 had a PCL, including serous cystadenoma, intraductal pseudopapillary mucinous neoplasia, mucinous cystic neoplasm, and pseudocysts . The Shannon Index of the chosen data set was 0.991 with an evenness of 0.902. The mean sensitivity obtained in the detection of these lesions was 93.1% (SD 0.1%), and the specificity was 81.8% (SD 0.1%).

CONCLUSIONS

This study shows a good performance of an automated artificial deep neural network in the detection of PCL on both noncontrast- and contrast-enhanced abdominal CT scans.

Incidence and Prevalence of Intraductal Papillary Mucinous Neoplasms in Individuals With BRCA1 and BRCA2 Pathogenic Variant

BACKGROUND

The natural history of branch-duct intraductal papillary neoplasm (BD-IPMN) in BRCA1/2 patients is unknown. Our goal was to estimate the incidence and prevalence of BD-IPMN and other pancreatic lesions in BRCA1/2 patients and compare it to that for average-risk individuals.

METHODS

We identified a cohort of BRCA1/2 patients followed at our institution between 1995 and 2020. Medical records and imaging results were reviewed to determine prevalence of pancreatic lesions. We then identified those who had undergone follow-up imaging and determined the incidence of new pancreatic lesions. We categorized pancreatic lesions as low, intermediate, or high-risk based on their malignant potential.

RESULTS

During the study period, 359 eligible BRCA1/2 patients were identified. Average patient age was 56.8 years, 88.3% were women, and 51.5% had BRCA1 . The prevalence of low-risk pancreatic lesions was 14.4%, intermediate-risk 13.9%, and high-risk 3.3%. The prevalence of BD-IPMN was 13.6% with mean cyst size 7.7 mm (range: 2 to 34 mm). The prevalence of pancreatic cancer was 3.1%. Subsequent imaging was performed in 169 patents with mean follow-up interval of 5.3 years (range: 0 to 19.7 y). The incidence of BD-IPMN was 20.1%, with median cyst size 5.5 mm (range: 2 to 30 mm). The incidence of pancreatic cancer was 2.9%. BRCA2 patients were almost 4-times more likely to develop pancreatic cancer than BRCA1 patients, however, there was no difference in incidence or prevalence of BD-IPMN.

CONCLUSIONS

Incidence and prevalence of BD-IPMNs in BRCA1/2 patients was similar to that reported for average-risk individuals. BRCA2 patients were more likely than BRCA1 patients to develop pancreatic cancer but had similar rates of BD-IPMN.

Transforming epilepsy research: A systematic review on natural language processing applications

Despite improved ancillary investigations in epilepsy care, patients' narratives remain indispensable for diagnosing and treatment monitoring. This wealth of information is typically stored in electronic health records and accumulated in medical journals in an unstructured manner, thereby restricting complete utilization in clinical decision-making. To this end, clinical researchers increasing apply natural language processing (NLP)-a branch of artificial intelligence-as it removes ambiguity, derives context, and imbues standardized meaning from free-narrative clinical texts. This systematic review presents an overview of the current NLP applications in epilepsy and discusses the opportunities and drawbacks of NLP alongside its future implications. We searched the PubMed and Embase databases with a "natural language processing" and "epilepsy" query (March 4, 2022) and included original research articles describing the application of NLP techniques for textual analysis in epilepsy. Twenty-six studies were included. Fifty-eight percent of these studies used NLP to classify clinical records into predefined categories, improving patient identification and treatment decisions. Other applications of NLP had structured clinical information retrieval from electronic health records, scientific papers, and online posts of patients. Challenges and opportunities of NLP applications for enhancing epilepsy care and research are discussed. The field could further benefit from NLP by replicating successes in other health care domains, such as NLP-aided quality evaluation for clinical decision-making, outcome prediction, and clinical record summarization.

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Pancreatic cancer (PC) is one of the deadliest cancers, and it is responsible for a number of deaths almost equal to its incidence. The high mortality rate is correlated with several explanations; the main one is the late disease stage at which the majority of patients are diagnosed. Since surgical resection has been recognised as the only curative treatment, a PC diagnosis at the initial stage is believed the main tool to improve survival. Therefore, patient stratification according to familial and genetic risk and the creation of screening protocol by using minimally invasive diagnostic tools would be appropriate. Pancreatic cystic neoplasms (PCNs) are subsets of lesions which deserve special management to avoid overtreatment. The current PC screening programs are based on the annual employment of magnetic resonance imaging with cholangiopancreatography sequences (MR/MRCP) and/or endoscopic ultrasonography (EUS). For patients unfit for MRI, computed tomography (CT) could be proposed, although CT results in lower detection rates, compared to MRI, for small lesions. The actual major limit is the incapacity to detect and characterize the pancreatic intraepithelial neoplasia (PanIN) by EUS and MR/MRCP. The possibility of utilizing artificial intelligence models to evaluate higher-risk patients could favour the diagnosis of these entities, although more data are needed to support the real utility of these applications in the field of screening. For these motives, it would be appropriate to realize screening programs in research settings.

Online calculator for predicting the risk of malignancy in patients with pancreatic cystic neoplasms: A multicenter, retrospective study

BACKGROUND

Efficient and practical methods for predicting the risk of malignancy in patients with pancreatic cystic neoplasms (PCNs) are lacking.

AIM

To establish a nomogram-based online calculator for predicting the risk of malignancy in patients with PCNs.

METHODS

In this study, the clinicopathological data of target patients in three medical centers were analyzed. The independent sample t-test, Mann–Whitney U test or chi-squared test were used as appropriate for statistical analysis. After univariable and multivariable logistic regression analysis, five independent factors were screened and incorporated to develop a calculator for predicting the risk of malignancy. Finally, the concordance index (C-index), calibration, area under the curve, decision curve analysis and clinical impact curves were used to evaluate the performance of the calculator.

RESULTS

Enhanced mural nodules [odds ratio (OR): 4.314; 95% confidence interval (CI): 1.618–11.503, P = 0.003], tumor diameter ≥ 40 mm (OR: 3.514; 95%CI: 1.138–10.849, P = 0.029), main pancreatic duct dilatation (OR: 3.267; 95%CI: 1.230–8.678, P = 0.018), preoperative neutrophil-to-lymphocyte ratio ≥ 2.288 (OR: 2.702; 95%CI: 1.008–7.244, P = 0.048], and preoperative serum CA19-9 concentration ≥ 34 U/mL (OR: 3.267; 95%CI: 1.274–13.007, P = 0.018) were independent risk factors for a high risk of malignancy in patients with PCNs. In the training cohort, the nomogram achieved a C-index of 0.824 for predicting the risk of malignancy. The predictive ability of the model was then validated in an external cohort (C-index: 0.893). Compared with the risk factors identified in the relevant guidelines, the current model showed better predictive performance and clinical utility.

CONCLUSION

The calculator demonstrates optimal predictive performance for identifying the risk of malignancy, potentially yielding a personalized method for patient selection and decision-making in clinical practice.

Pancreatic CT density is an optimal imaging biomarker for earlier detection of malignancy in the pancreas with intraductal papillary mucinous neoplasm

BACKGROUND

Intraductal papillary mucinous neoplasms (IPMNs) are typically detected as incidental findings by computed tomography (CT); however, the conventional surveillance is not valid for the early detection of concomitant pancreatic cancer. The pancreas of IPMN is often accompanied by fatty infiltration in the parenchyma, and pancreatic fatty infiltration could be evaluated by pancreatic CT density (pancreatic index, PI). We aimed to investigate whether PI could be an imaging biomarker for the early prediction of malignancies in the pancreas with IPMN.

METHODS

Two different cohorts were investigated. (Investigation cohort): A total of 1137 patients with initially low-risk IPMN were compensated by initial IPMN findings, and 2 groups (malignancy/possible benign, 50 cases each) were investigated for yearly changes in PI and for the cutoff value of PI indicating the development of malignancies. (Validation cohort): To validate the cutoff value, 256 patients radiologically suspected of having IPMNs were investigated.

RESULTS

(Investigation-cohort): The malignancy group showed a gradual decrease in PI every year, and PI significantly differed among the 2 groups 1 year prior to the last investigation. The cutoff value of PI was set at 0.65. (Validation-cohort): A total of 55% of the patients with a PI below the cutoff value had malignancy in the pancreas, including concomitant pancreatic cancer, and the cutoff value was the most significant risk factors for the development of malignancies in the pancreas compared to the conventional risk factors for IPMN.

CONCLUSIONS

Decreasing PI would be an optimal imaging biomarker for earlier detection of malignancies in the pancreas with IPMN.

Automated Identification and Measurement Extraction of Pancreatic Cystic Lesions from Free-Text Radiology Reports Using Natural Language Processing

Purpose

To automatically identify a cohort of patients with pancreatic cystic lesions (PCLs) and extract PCL measurements from historical CT and MRI reports using natural language processing (NLP) and a question answering system.

Materials and Methods

Institutional review board approval was obtained for this retrospective Health Insurance Portability and Accountability Act-compliant study, and the requirement to obtain informed consent was waived. A cohort of free-text CT and MRI reports generated between January 1991 and July 2019 that covered the pancreatic region were identified. A PCL identification model was developed by modifying a rule-based information extraction model; measurement extraction was performed using a state-of-the-art question answering system. The system's performance was evaluated against radiologists' annotations.

Results

For this study, 430 426 free-text radiology reports from 199 783 unique patients were identified. The NLP model for identifying PCL was applied to 1000 test samples. The interobserver agreement between the model and two radiologists was almost perfect (Fleiss κ = 0.951), and the false-positive rate and true-positive rate were 3.0% and 98.2%, respectively, against consensus of radiologists' annotations as ground truths. The overall accuracy and Lin concordance correlation coefficient for measurement extraction were 0.958 and 0.874, respectively, against radiologists' annotations as ground truths.

Conclusion

An NLP-based system was developed that identifies patients with PCLs and extracts measurements from a large single-institution archive of free-text radiology reports. This approach may prove valuable to study the natural history and potential risks of PCLs and can be applied to many other use cases.Keywords: Informatics, Abdomen/GI, Pancreas, Cysts, Computer Applications-General (Informatics), Named Entity Recognition Supplemental material is available for this article. © RSNA, 2022See also commentary by Horii in this issue.

Role of endoscopic ultrasound in anticancer therapy: Current evidence and future perspectives

The digestive system is one of the most common sites of malignancies in humans. Since gastrointestinal tumors represent a massive global health burden both in terms of morbidity and health care expenditures, scientists continuously develop novel diagnostic and therapeutic methods to ameliorate the detrimental effects of this group of diseases. Apart from the well-established role of the endoscopic ultrasound (EUS) in the diagnostic course of gastrointestinal and hepatobiliary malignancies, we have recently become acquainted with a vast array of its therapeutic possibilities. A multitude of previously established, evidence-based methods that might now be guided by the EUS emerged: Radiofrequency ablation, brachytherapy, fine needle injection, celiac plexus neurolysis, and endoscopic submucosal dissection. In this review we endeavored to provide a comprehensive overview of the role of these methods in different malignancies of the digestive system, primarily in the treatment and symptom control in pancreatic cancer, and additionally in the management of hepatic, gastrointestinal tumors, and pancreatic cysts.

Pancreatic Cystic Lesions and Malignancy: Assessment, Guidelines, and the Field Defect

The widespread use of high-spatial-resolution cross-sectional imaging has led to an increase in detection of incidental pancreatic cystic lesions. These lesions are a diverse group, ranging from indolent and premalignant lesions to invasive cancers. The diagnosis of several of these lesions can be suggested on the basis of their imaging appearance, while many other lesions require follow-up imaging and/or aspiration. The smaller cystic lesions, often branch-duct intraductal papillary mucinous neoplasms, have overlapping imaging characteristics that make diagnostic assessment of the natural history and malignancy risk confusing. Expert panels have developed societal guidelines, based on a consensus, for surveillance of these lesions. However, these guidelines are often inconsistent and are constantly evolving as additional scientific data are accumulated. Identification of features associated with increased risk of malignancy is important for proper management. The concept of field defect, whereby pancreatic adenocarcinoma develops at a site different from the site of the pancreatic cyst, adds to the complexity of screening guidelines. As a result of the differences in guidelines, key stakeholders (eg, radiologists, gastroenterologists, and surgeons) must review and come to a consensus regarding which guideline, or combination of guidelines, to follow at their individual institutions. Standardized reporting and macros are helpful for ensuring the uniformity of interpretations. Radiologists play a critical role in the detection and characterization of pancreatic cystic lesions, in the follow-up recommendations for these lesions, and in the detection of associated cancer. An invited commentary by Zaheer is available online. Online supplemental material is available for this article. ^©RSNA, 2021.

Variation in Radiologists' Follow-Up Imaging Recommendations for Small Cystic Pancreatic Lesions

OBJECTIVE

This study aimed to determine the incidence, identify imaging and patient factors, and measure individual radiologist variation associated with follow-up recommendations for small focal cystic pancreatic lesions (FCPLs), a common incidental imaging finding.

METHODS

This institutional review board-approved retrospective study analyzed 146,709 reports from abdominal CTs and MRIs performed in a large academic hospital from July 1, 2016, to June 30, 2018. A trained natural language processing tool identified 4,345 reports with FCPLs, which were manually reviewed to identify those containing one or more <1.5-cm pancreatic cysts. For these patients, patient, lesion, and radiologist features and follow-up recommendations for FCPL were extracted. A nonlinear random-effects model estimated degree of variation in follow-up recommendations across radiologists at department and division levels.

RESULTS

Of 2,872 reports with FCPLs < 1.5 cm, 708 (24.7%) had FCPL-related follow-up recommendations. Average patient age was 67 years (SD ± 11). In all, 1,721 (60.0%) reports were for female patients; 59.3% of patients had only one cyst. In multivariable analysis, older patients had slightly lower follow-up recommendation rates (odds ratio [OR]: 0.98 [0.98-1.00] per additional year), and lesions associated with main duct dilatation and septation were more likely to have a follow-up recommendation (ORs: 1.93 [1.11-3.36] and 2.88 [1.89-4.38], respectively). Radiologist years in practice (P = .51), trainee presence (P = .21), and radiologist gender (P = .52) were not associated with increased follow-up recommendations. There was significant interradiologist variation in the Abdominal Imaging Division (P = .04), but not in Emergency Radiology (P = .31) or Cancer Imaging Divisions (P = .29).

DISCUSSION

Interradiologist variation significantly contributes to variability in follow-up imaging recommendations for FCPLs.

Focal Pancreatic Lesions: Role of Contrast-Enhanced Ultrasonography

The introduction of contrast-enhanced ultrasonography (CEUS) has led to a significant improvement in the diagnostic accuracy of ultrasound in the characterization of a pancreatic mass. CEUS, by using a blood pool contrast agent, can provide dynamic information concerning macro- and micro-circulation of focal lesions and of normal parenchyma, without the use of ionizing radiation. On the basis of personal experience and literature data, the purpose of this article is to describe and discuss CEUS imaging findings of the main solid and cystic pancreatic lesions with varying prevalence.

Society of Abdominal Radiology Disease Focused Panel Survey on Clinical Utilization of Incidental Pancreatic Cyst Management Recommendations and Template Reporting

OBJECTIVE

To assess current practice patterns with respect to protocols used for incidental pancreatic cyst follow-up, management guidelines, and template reporting.

METHODS

The Society of Abdominal Radiology Disease Focused Panel on intraductal pancreatic neoplasms distributed an anonymous 14-question survey to its members in June 2018 that focused on current utilization of incidental pancreatic cyst guidelines, protocols, and template reporting.

RESULTS

Among the 1,390 email invitations, 323 responded, and 94.7% (306 of 323) completed all questions. Respondents were mainly radiologists (93.8%, 303 of 323) from academic institutions (74.7%, 227 of 304) in North America (93.7%, 286 of 305). Of respondents, 42.5% (136 of 320) preferred 2017 ACR recommendations, 17.8% (57 of 320) homegrown systems, 15.0% (48 of 320) Fukuoka guidelines, and 7.8% (25 of 320) American Gastroenterological Association guidelines. The majority (68.7%, 222 of 323) agreed or strongly agreed that developing a single international consensus recommendation for management was important, and most radiologists preferred to include them in reports (231 of 322, 71.7%); yet only half included recommendations in >75% of reports (161 of 321). MR cholangiopancreatography was the modality of choice for follow-up of <2.5 cm cysts. Intravenous contrast was routinely used by 69.7% (212 of 304). Standardized reporting templates were rarely used in practice (12.8% 39 of 306).

CONCLUSIONS

Nearly 7 of 10 radiologists desire a unified international consensus recommendation for management of incidental cystic pancreatic lesions; ACR 2017 recommendations are most commonly used, followed by homegrown systems and Fukuoka guidelines. The majority of radiologists routinely use MR cholangiopancreatography with intravenous contrast for follow-up of incidental cystic lesions, but template reporting is rarely used.

Long-term follow-up of Branch-Duct Intraductal Papillary Mucinous Neoplasms with negative Sendai Criteria: the therapeutic challenge of patients who convert to positive Sendai Criteria

BACKGROUND

The management of Branch-Duct Intraductal Papillary Mucinous Neoplasm (BD-IPMN) is still controversial. Our objective was to assess the long-term follow-up (FU) of patients with "low-risk" BD-IPMN according to the Sendai-International Consensus Guidelines (ICG-I).

METHODS

We retrospectively analyzed a cohort of patients with BD-IPMN and Negative Sendai-Criteria (NSC) from January 2004 to October 2019. A univariate analysis was performed to determine factors associated with conversion to Positive Sendai-Criteria (PSC) and malignancy. Positive Predictive Value (PPV) and Negative Predictive Value (NPV) of the IGC-I were assessed for the development of malignancy.

RESULTS

A total of 219 patients were selected and underwent a median 58-month FU. Thirty-seven (17%) patients developed PSC during FU including 12 (5.5%) with malignant lesions. Conversely, 182 patients (83%) did not develop malignancy. The NPV and PPV of ICG-I for malignancy were 100% and 32.4%, respectively. Among patients who developed PSC, those with cancer were >65years (OR = 3.57;p = 0.015) and had significantly higher serum CA-19-9 levels (OR = 5.27;p = 0.007).

CONCLUSION

The ICG-I is a safe strategy for FU of patients with BD-IPMN. The absence of PSC exclude malignancy. Among patients who develops PSC, the risk of cancer remains low and surgery should be decided according to their surgical risk and life expectancy.

Closing the Loop on Unscheduled Diagnostic Imaging Orders: A Systems-Based Approach

Objective:

To: 1) describe a System for Coordinating Orders for Radiology Exams (SCORE) which aims to manage unscheduled orders for outpatient diagnostic imaging in an electronic health record (EHR) with embedded computerized physician order entry (CPOE), 2) assess the impact of SCORE and other related factors (e.g., demographics) on rate of unscheduled orders, and 3) assess the clinical necessity of orders canceled, expired, scheduled and performed.

Methods:

This Institutional Review Board-approved retrospective study was conducted in a large academic institution between 10/1/2017–7/1/2019. The design and implementation of SCORE is described, including people (e.g., competencies), processes (e.g., standardized procedures) and tools (e.g., EHR interfaces, dashboard). Rate of unscheduled imaging orders was compared pre-SCORE (10/1/17–9/30/18) and post-SCORE (10/1/18–6/30/19) using chi-square analysis. For 447 randomly selected orders, mode of resolution was obtained from the EHR and factors related to order resolution were assessed via multivariable analysis. Finally, clinical necessity was manually assessed by two physicians.

Results:

Pre-SCORE, 52,204/607,020 exam orders were unscheduled (8.6% of orders), compared to 20,900/475,000 exam orders (4.4% of orders) post-SCORE (χ², p<0.00001), a 49% reduction in unscheduled orders. Among 447 randomly selected orders, orders were addressed via cancellation (57%), expiration (21%), scheduling (1%) and performance (11%). Order resolution was not significantly associated with other factors. 31.9% of cancellations and 27.7% of expired orders remained clinically necessary and were attributed to scheduling and patient-related factors.

Conclusion:

SCORE significantly reduced unscheduled diagnostic imaging orders. This patient safety initiative may help reduce errors resulting from diagnostic delays due to unscheduled exam orders.

[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.

A Contrast-Enhanced Computed Tomography Based Radiomics Approach for Preoperative Differentiation of Pancreatic Cystic Neoplasm Subtypes: A Feasibility Study

Background: Serous cystadenoma (SCA), mucinous cystadenoma (MCN), and intraductal papillary mucinous neoplasm (IPMN) are three subtypes of pancreatic cystic neoplasm (PCN). Due to the potential of malignant-transforming, patients with MCN and IPMN require radical surgery while patients with SCA need periodic surveillance. However, accurate pre-surgery diagnosis between SCA, MCN, and IPMN remains challenging in the clinic. Methods: This study enrolled 164 patients including 76 with SCA, 40 with MCN and 48 with IPMN. Patients were randomly split into a training cohort (n = 115) and validation cohort (n = 41). We performed statistical analysis and Boruta method to screen significantly distinct clinical factors and radiomics features extracted on pre-surgery contrast-enhanced computed tomography (CECT) images among three subtypes. Three reliable machine-learning algorithms, support vector machine (SVM), random forest (RF) and artificial neural network (ANN), were utilized to construct classifiers based on important radiomics features and clinical parameters. Precision, recall, and F1-score were calculated to assess the performance of the constructed classifiers. Results: Nine of 547 radiomics features and eight clinical factors showed a significant difference among SCA, MCN, and IPMN. Five radiomics features (Histogram_Entropy, Histogram_Skeweness, LLL_GLSZM_GLV, Histogram_Uniformity, HHL_Histogram_Kurtosis), and four clinical factors, including serum carbohydrate antigen 19-9, sex, age, and serum carcinoembryonic antigen, were identified important by Boruta method. The SVM classifier achieved an overall accuracy of 73.04% in training cohort and 71.43% in validation cohort, respectively. The RF classifier achieved overall accuracy of 84.35 and 79.59%, respectively. The constructed ANN model showed an overall accuracy of 77.39% in the training dataset and 71.43% in the validation dataset. All the three classifiers showed high F1 score for differentiation among the three subtypes. Conclusion: Our study proved the feasibility and translational value of CECT-based radiomics classifiers for differentiation among SCA, MCN, and IPMN.

Abdominal Imaging of Pancreatic Cysts and Cyst-Associated Pancreatic Cancer in BRCA1/2 Mutation Carriers: A Retrospective Cross-Sectional Study

BACKGROUND

Direct-to-consumer BRCA testing will increase BRCA diagnoses and subsequent abdominal imaging. It is unclear whether BRCA carriers are at higher risk of developing pancreatic cysts (PCs) or cyst-associated pancreatic ductal adenocarcinoma (PDAC). We investigated the prevalence of PCs in BRCA-tested patients, and whether BRCA-carriers have higher rates of PDAC when PCs are found.

STUDY DESIGN

This is a retrospective cross-sectional study of patients with BRCA testing and abdominal imaging between 1996 and 2018. Pancreatic cysts were identified on original imaging reports. Prevalence and risk characteristics of PCs, as well as incidence of PDAC, were compared between BRCA+, BRCA-, and BRCA-untested patients.

RESULTS

Pancreatic cysts were identified in 4,045 patients among 128,164 unique patients with abdominal imaging, including 33 patients with PCs in 1,113 BRCA-tested patients. There was no difference in PC prevalence between BRCA+, BRCA-, and untested patients (3.6%, 2.6%, 3.2%, respectively; p = 0.64). Pancreatic cysts were diagnosed in BRCA+ patients at a younger age (57.1 vs 65.3 years, p < 0.001); however, there was no difference in risk stratification compared with BRCA- or untested patients by consensus criteria. Across the population of imaged patients, patients with PCs had significantly higher rates of PDAC compared with those without PCs (18.2% vs 2.4%, p < 0.001). Incidence of cyst-associated PDAC was similar in BRCA+ and BRCA- patients (13.3% vs 22.2%, p = 0.84).

CONCLUSIONS

BRCA+ patients have similar rates of PCs, high-risk features in their cysts, and PDAC as BRCA- and untested patients. BRCA+ patients likely do not require dedicated abdominal imaging to evaluate for PCs and should follow management guidelines similar to those as the untested general population if an incidental PC is identified.

Role of transabdominal ultrasonography in the diagnosis of pancreatic cystic lesions

Pancreatic cystic lesions (PCLs) are incidental findings that are being increasingly identified because of recent advancements in abdominal imaging technologies. PCLs include different entities, with each of them having a peculiar biological behavior, and they range from benign to premalignant or malignant neoplasms. Therefore, accurate diagnosis is important to determine the best treatment strategy. As transabdominal ultrasonography (US) is noninvasive, inexpensive, and widely available, it is considered to be the most appropriate imaging modality for the initial evaluation of abdominal diseases, including PCLs, and for follow-up assessment. We present a review of the possibilities and limits of US in the diagnosis of PCLs, the technical development of US, and the ultrasonographic characteristics of PCLs.

The Surveillance Patterns of Incidentally Detected Pancreatic Cysts Vary Widely and Infrequently Adhere to Guidelines

OBJECTIVES

We aimed to determine incidental pancreatic cyst ("cyst") surveillance patterns, predictors of receiving surveillance, and guideline adherence.

METHODS

We performed a retrospective cohort study of all patients receiving longitudinal care at a single tertiary care center with a newly diagnosed incidental pancreatic cyst over a 2-year period (2010-2011). All follow-up care was abstracted over a 5-year period.

RESULTS

Of 3241 eligible imaging studies reviewed, 100 patients with newly diagnosed incidental cysts eligible for surveillance were identified. A majority (53%) received no follow-up. We identified 4 predictors of cyst surveillance: radiology report conclusion mentioning the cyst (odds ratio [OR], 14.9; 95% confidence interval [CI], 1.9-119) and recommending follow-up (OR, 5.5; 95% CI, 2.1-13.9), pancreas main duct dilation (OR, 10.7; 95% CI, 1.3-89), and absence of multiple cysts (OR, 2.5; 95% CI, 1.1-10.0). Of the 47 patients who received surveillance, 66% met minimum surveillance imaging intervals of at least one guideline. Conversely, 21% of patients met the criteria for overutilization in at least one guideline.

CONCLUSIONS

Although guidelines recommend that surgically fit patients with incidental cysts undergo surveillance, most patients receive no follow-up. When follow-up occurs, surveillance patterns vary widely and infrequently conform to guidelines. Interventions to reduce care variation require study.

[Basics and applications of Natural Language Processing (NLP) in radiology]

BACKGROUND

Due to the increasing demands in radiology, applications that enable quality assurance and continuous process optimization are required.

OBJECTIVE

The principles of Natural Language Processing (NLP) as a computer-based method for structuring of free text reports are explained and application scenarios are sketched.

MATERIALS UND METHODS

The structuring of free texts succeeds by several theories, linguistic techniques (word meanings, word context, negations), statistical methods with rules and currently with deep learning approaches. Medical encyclopedias, such as RadLex®, are suitable for coding findings. NLP was used in our own radiology clinic to check the quality of 3756 CT reports.

RESULTS

In our case study, NLP proved to be a helpful, automated tool for internal quality testing.

DISCUSSION

NLP offers numerous application scenarios for decision support and for quality management in radiology.

An osteoclast-like giant cell tumor embedded in the mural nodule of a pancreatic mucinous cystic neoplasm: A case report and literature review

RATIONALE

Mucinous cystic neoplasms (MCNs) are relatively rare lesions, accounting for 2%-5% of all exocrine pancreatic neoplasms. MCNs mainly occur in women (female:male ratio = 20:1), with a peak incidence in the 5th decade of life. Osteoclast-like giant cell tumors (OGCTs) are rare and relatively aggressive neoplasms, comprising <1% of all pancreatic carcinomas. Herein, we present a rare "combination tumor" case and discuss the impact of mural nodules in pancreatic MCNs considering malignant transformation.

PATIENT CONCERNS

A 54-year-old Mongolian man, without vomiting, nausea or jaundice, presented with abdominal distention since 3 months. He had a 7-year history of diabetes. Physical examinations indicated slight middle abdominal tenderness without rebound tenderness or rigidity. Laboratory results revealed that the level of carcinoembryonic antigen (CEA) was 1.16 ng/ml (normal: <5 ng/ml); CA-199: 30.02 U/ml (normal: <27 U/ml); hemoglobin: 143 g/L; fasting glucose: 7.71 mmol/L; and albumin: 43 g/L. Abdominal enhanced computed tomography revealed a 7 × 6 cm solid neoplasm in the pancreatic body with partial enhancement and heterogeneity. Endoscopic ultrasound revealed a solid-cystic space-occupying lesion in the pancreatic body.

DIAGNOSIS

The preoperative preliminary diagnosis was pancreatic solid-cystic tumor, possibly a solid pseudopapillary tumor. Postoperative pathological findings revealed a pancreatic borderline MCN with an OGCT embedded in a mural nodule of the capsule. Immunohistochemical results indicated a simultaneous dual origin from the epithelium and stroma.

INTERVENTIONS

The patient underwent open distal pancreatectomy and splenectomy. Postoperative blood glucose levels were closely monitored and regulated. We intravenously administered single-agent gemcitabine (1400 mg on day 1) as the first-time chemotherapy, 1 month after surgery. After the first chemotherapy, the patient refused to receive further treatment owing to personal reasons.

OUTCOMES

The patient showed uneventful recovery and was discharged 13 days after the initial surgery. Follow-up was performed 1, 3 and 6 months after surgery. At 6 months, abdominal computed tomography scan showed no signs of recurrence, regional lymphadenopathy, or other abnormalities. And laboratory tests showed a platelet count of 301 × 10/L, postprandial blood glucose of 12.9 mmol/L and CA-199 level of 20 U/ml. The patient had no obvious discomfort.

LESSONS

Although pancreatic MCNs are widely accepted as borderline tumors, malignant transformations may occur due to various risk factors (cyst size, mural nodules, septations, and tumor location). The combination tumor in this case was more likely to increase the possibility of malignant biological behavior, thereby worsening overall prognosis. Therefore, long-term follow-up must be maintained with strict monitoring.

Use of Machine Learning to Identify Follow-Up Recommendations in Radiology Reports

PURPOSE

The aims of this study were to assess follow-up recommendations in radiology reports, develop and assess traditional machine learning (TML) and deep learning (DL) models in identifying follow-up, and benchmark them against a natural language processing (NLP) system.

METHODS

This HIPAA-compliant, institutional review board-approved study was performed at an academic medical center generating >500,000 radiology reports annually. One thousand randomly selected ultrasound, radiography, CT, and MRI reports generated in 2016 were manually reviewed and annotated for follow-up recommendations. TML (support vector machines, random forest, logistic regression) and DL (recurrent neural nets) algorithms were constructed and trained on 850 reports (training data), with subsequent optimization of model architectures and parameters. Precision, recall, and F1 score were calculated on the remaining 150 reports (test data). A previously developed and validated NLP system (iSCOUT) was also applied to the test data, with equivalent metrics calculated.

RESULTS

Follow-up recommendations were present in 12.7% of reports. The TML algorithms achieved F1 scores of 0.75 (random forest), 0.83 (logistic regression), and 0.85 (support vector machine) on the test data. DL recurrent neural nets had an F1 score of 0.71; iSCOUT also had an F1 score of 0.71. Performance of both TML and DL methods by F1 scores appeared to plateau after 500 to 700 samples while training.

CONCLUSIONS

TML and DL are feasible methods to identify follow-up recommendations. These methods have great potential for near real-time monitoring of follow-up recommendations in radiology reports.

Pancreatic cancer screening in patients with presumed branch-duct intraductal papillary mucinous neoplasms

Because delayed diagnosis is one of the causes of poor prognosis in pancreatic ductal adenocarcinoma (PDAC), early detection is a key for overall improvement of prognosis. Towards this end, periodic screening is recommended for individuals considered high-risk for PDAC. Advances in diagnostic imaging modalities have increased the frequency of incidental findings of pancreatic cysts, including the intraductal papillary mucinous neoplasm (IPMN) - a major risk factor of PDAC, having 1% annual prevalence of concomitance with IPMN. Proper retainment of patients with IPMN and regular follow-up by routine imaging examination will likely improve early detection and better prognosis of PDAC. Unfortunately, current guidelines only address management of PDAC derived from IPMN and overlook PDAC concomitant with IPMN. Screening of patients with IPMN, by endoscopic ultrasonography (currently the most reliable modality for detecting small PDAC), may facilitate early detection of both IPMN-derived and -concomitant PDAC. Prospective studies to evaluate the usefulness of endoscopic ultrasonography in screening of IPMN-concomitant PDAC will also help in determining the optimal surveillance strategy for more widespread applications.

Systematic review and meta-analysis: Prevalence of incidentally detected pancreatic cystic lesions in asymptomatic individuals

BACKGROUND & AIMS

Pancreatic cystic lesions (PCLs) are frequent incidental findings. As most PCLs require costly diagnostic evaluation and active surveillance, it is important to clarify their prevalence in asymptomatic individuals. We therefore aimed at performing a systematic review and meta-analysis to determine it.

METHODS

a systematic search was conducted and studies meeting inclusion criteria were included. The prevalence of PCLs was pooled across studies. A random effect model was used with assessment of heterogeneity.

RESULTS

17 studies, with 48,860 patients, were included. Only 3 were prospective; 5 studies were conducted in the US, 7 in Europe, 4 in Asia and 1 in Brazil. The pooled prevalence of PCLs was 8% (95% CI 4-14) with considerable heterogeneity (I² = 99.5%). This prevalence was higher in studies of higher quality, examining older subjects, smaller cohorts, and employing MRCP (24.8% vs 2.7% with CT-scan). The pooled rate of PCLs was four times higher in studies conducted in the US than in Asia (12.6% vs 3.1%). 7 studies reported the prevalence of mucinous lesions, with a pooled rate of 4.3% (95% CI 2-10; I² = 99.2%), but of 0.7% only for worrisome features or high risk stigmata.

CONCLUSION

The rate of incidentally detected PCLs is of 8%. Mucinous lesions are the most common incidentally detected PCLs, although they rarely present with potential indication for surgery. The observed different rates in the US and other geographic Areas suggest that different protocols might be necessary to help balancing costs and effectiveness of follow-up investigations in asymptomatic subjects.

Subspecialized radiology review at multidisciplinary pancreas conference: impact on patient management

PURPOSE

At our tertiary medical center, multidisciplinary subspecialists meet twice a week during a CME-accredited conference to discuss oncologic and non-oncologic patients with pancreatic diseases at which time a subspecialized abdominal staff radiologist reinterprets the patient's relevant imaging studies. This study assesses the changes in patient management due to imaging reinterpretation during multidisciplinary pancreas conference (MPC).

MATERIALS AND METHODS

In this retrospective, IRB-approved, HIPAA-compliant study, imaging studies of all patients discussed at MPC between July 1 and December 31, 2015 were assessed for technical adequacy, and original reports analyzed for congruency with reinterpretation. Management measures included change in diagnosis, clinical stage, treatment, or workup. Additional data were obtained on referring services affected and their resultant change in practice. Changes in surgical resectability, surgical approach, or delayed operative dates were noted for surgeons. Changes in chemotherapeutic or radiation oncology regimens as well as decisions for additional imaging, laboratory workup, or histologic evaluation were also recorded.

RESULTS

A total of 252 patients were included (54.4% males, 45.6% females, mean age 63.71 years). Relevant imaging consisted of 142 abdominal CT scans, 112 abdominal MRI scans, 1 abdominal ultrasound, and 1 nuclear medicine octreotide study of which 69.4% were performed in-house. Image quality was deemed appropriate in 95.2%. Cases presented included solid pancreatic malignancies (n = 140; 55.6%), cystic pancreatic lesions (n = 41; 16.3%), acute and chronic inflammatory conditions (n = 52; 20.6%), and miscellaneous entities (n = 10; 4.0%); 9 (3.6%) cases were normal. Image reinterpretation was congruent with original reports in 56.7%, with minor, moderate, and major discrepancies occurring in 9.5, 26.2%, and 7.5% of cases, respectively. Incongruent reinterpretation was predominantly due to perceptional errors (false-negative reports due to missed findings) and interpretative errors (false-positive results due to over-reporting or misclassification of diagnoses). Services most commonly affected included surgical oncology, radiology, and gastroenterology at 16.7%, 13.1%, and 12.7% of cases, respectively. Management changes included a change in diagnosis in 8.7%, change in clinical stage in 8.7%, change in treatment in 17.9%, and further workup needed in 19.0% of patients, respectively. No change in management occurred in the remaining 61.5% of cases.

CONCLUSIONS

Subspecialized abdominal radiologist reinterpretation in the context of more comprehensive patient information heavily impacts the multidisciplinary management of patients with pancreatic disorders. Further efforts are needed to solidify the abdominal radiologist's role in the multidisciplinary clinical setting.

Managing Incidental Pancreatic Cysts

PURPOSE OF REVIEW

The goal of this review is to critically analyze the current literature regarding the management of incidental pancreatic cysts. Given their increased rates of detection due to the frequent use of cross-sectional imaging, correctly identifying the subset of high risk lesions that are appropriate for surgical resection is critical. However, the existing consensus and societal guidelines discussed in this review lack high quality data to create evidence-based recommendations, making achieving this important aim challenging.

RECENT FINDINGS

Several recent studies have focused on the natural history of pancreatic cysts and defining the role of endoscopic ultrasound, which remains unclear. EUS-guided diagnostic tools include molecular analysis of obtained fluid; EUS-guided FNA, FNB, and intracystic forceps biopsy of the cyst wall; and confocal endomicroscopy. While their precise role in diagnosing pancreatic cystic neoplasms remains to be defined, they represent promising innovations that may play a future role in cyst assessment and management. Large, long-term, prospective studies of incidentally identified pancreatic cysts are essential to fully understand their natural history and potential for neoplastic progression. Given the absence of such data at present, an individualized patient approach is recommended.

Pancreatic Cystic Neoplasms: Different Types, Different Management, New Guidelines

Pancreatic cystic neoplasms (PCN) include different types of cysts with various biological behavior. The most prevalent PCN are intraductal papillary mucinous neoplasm (IPMN), mucinous cystic neoplasm (MCN), and serous cystic neoplasm (SCN). Management of PCN should focus on the prevention of malignant progression, while avoiding unnecessary morbidity of surgery. This requires specialized centers with dedicated multidisciplinary PCN teams. The malignant potential of PCN varies enormously between the various types of PCN. A combination of computed tomography, magnetic resonance imaging/magnetic resonance cholangiopancreatography, and endoscopic ultrasound with or without fine needle aspiration is typically needed before a reliable diagnosis can be made. Several guidelines discuss the management of PCN; however, most of these are non-evidence-based without clear consensus on the optimal treatment and follow-up strategy. The 2018 European guidelines on PCN are the first evidence-based guidelines to include IPMN, MCN, SCN, and all other PCN. This guideline advises a more conservative approach to side-branch IPMN and MCN smaller than 40 mm and more often a surgical approach in IPMN with a main duct dilatation beyond 5 mm. The goal of this review is to summarize the different types and management of the most common PCN based on the current literature and guidelines.

European evidence-based guidelines on pancreatic cystic neoplasms

Evidence-based guidelines on the management of pancreatic cystic neoplasms (PCN) are lacking. This guideline is a joint initiative of the European Study Group on Cystic Tumours of the Pancreas, United European Gastroenterology, European Pancreatic Club, European-African Hepato-Pancreato-Biliary Association, European Digestive Surgery, and the European Society of Gastrointestinal Endoscopy. It replaces the 2013 European consensus statement guidelines on PCN. European and non-European experts performed systematic reviews and used GRADE methodology to answer relevant clinical questions on nine topics (biomarkers, radiology, endoscopy, intraductal papillary mucinous neoplasm (IPMN), mucinous cystic neoplasm (MCN), serous cystic neoplasm, rare cysts, (neo)adjuvant treatment, and pathology). Recommendations include conservative management, relative and absolute indications for surgery. A conservative approach is recommended for asymptomatic MCN and IPMN measuring <40 mm without an enhancing nodule. Relative indications for surgery in IPMN include a main pancreatic duct (MPD) diameter between 5 and 9.9 mm or a cyst diameter ≥40 mm. Absolute indications for surgery in IPMN, due to the high-risk of malignant transformation, include jaundice, an enhancing mural nodule >5 mm, and MPD diameter >10 mm. Lifelong follow-up of IPMN is recommended in patients who are fit for surgery. The European evidence-based guidelines on PCN aim to improve the diagnosis and management of PCN.

Incidental, Small (< 3 cm), Unilocular, Pancreatic Cysts: Factors That Predict Lesion Progression during Imaging Surveillance

OBJECTIVE

To explore the features that predict size increase and development of potential malignant features in incidentally detected, unilocular cystic pancreatic lesions (CPLs) less than 3 cm in diameter, during subsequent follow-up.

MATERIALS AND METHODS

We retrieved data of patients diagnosed with unilocular CPLs less than 3 cm in diameter during the period from November 2003 through December 2014, using a computerized search. All serial CT and MR images were analyzed to identify the number, size, and location of CPLs; dilatation of the main pancreatic duct; and occurrence of worrisome features and high-risk stigmata of malignancy in the lesion. The characteristics of CPLs were compared between the increase (i.e., size increase during subsequent follow-up) and no-increase groups. For CPLs in the increase group, subgroup analysis was performed according to the lesion size at the last follow-up (< 3 cm vs. ≥ 3 cm).

RESULTS

Among 553 eligible patients, 132 (23.9%) had CPLs that increased in size, and 421 (76.1%) had CPLs that did not, during follow-up. Of the 132, 12 (9.1%) CPLs increased to diameters ≥ 3 cm at the final follow-up. Among the various factors, follow-up duration was a significant independent factor for an interval size increase of CPLs (p < 0.001). In the increase group, initial cyst size was a significant independent factor to predict later size increase to or beyond 3 cm in diameter (p < 0.001), and the initial cyst diameter ≥ 1.5 cm predicted such a growth with a sensitivity and specificity of 83% and 72%, respectively. No significant factors to predict the development of potential malignant features were identified.

CONCLUSION

Follow-up duration was associated with an interval size increase of CPLs. Among the growing CPLs, initial cyst size was associated with future lesion growth to and beyond 3 cm.

MDCT vs. MRI for incidental pancreatic cysts: measurement variability and impact on clinical management

PURPOSE

To investigate incidental pancreatic cysts (IPCs) size discrepancy in a cohort of patients receiving both computed tomography (CT) and magnetic resonance imaging (MRI) and its impact on clinical management based on the 2010 American College of Radiology (ACR) guidelines.

METHODS

This was a HIPAA-compliant, retrospective, IRB-approved study. Informed consent was waived. Patients with known IPCs and at least one case-pair, consisting of an abdominal CT and MRI examination within 180 days between 05/1999 and 12/2011, were included. Maximum diameter of cysts was measured in both the CT and MR examinations. A subset of 30 patients was measured by three radiologists independently to assess inter-observer variability. Absolute difference in diameter measurements between CT and MRI was calculated. Influence of cyst size, cyst location, and patient characteristics such as weight, height, and body mass index (BMI) on variability of size measurements were evaluated. Clinical impact in terms of current ACR guidelines was assessed.

RESULTS

Overall, 267 case-pairs of cysts in 113 patients were included in this study. 59/267 cysts were visualized on MRI but not on CT (22.1%, 95% CI 17.1%-27.1%; 32 patients, 64.6 ± 11.7 years, BMI 28.5 ± 4.8 kg/m²), with a median MRI cyst size of 7.8 mm, IQR 6.0-9.0 mm, range 2-17.8 mm. 208 case-pairs in 113 patients with a mean BMI of 26.9 ± 5.1 kg/m² (range 16.9-39.5 kg/m²) and mean cysts size of 13.4 ± 8.1 mm (range 3-49 mm) were seen in both CT and MRI. The mean absolute size difference for IPCs measured on MRI and CT was 2.1 ± 1.8 mm (median 1.5 mm, IQR 0.9-2.9 mm, range 0-9 mm). Absolute size difference between CT and MRI measurements increased with size of the cyst (r = 0.31, p < 0.001), whereas location of the cyst did not influence the absolute difference between CT and MRI measurements (p = 0.44). Patient weight and BMI had a negative correlation with the difference in cyst size between CT and MRI (weight r = -0.17, p = 0.023; BMI r = -0.17, p = 0.027), with cyst measurements being larger on MRI in thin patients and on CT in obese patients. Inter-reader variability was excellent (ICC = 0.99). In 12/208 (5.7%, 95% CI 2.7%-9.1%), variability between CT and MRI would have changed ACR-based follow-up recommendation.

CONCLUSION

There was a median difference of 1.5 mm between measurements of IPCs on CT vs. MRI. If imaging modality was switched during follow-up, variability of measurements may lead to inappropriate change of follow-up regimen in 6% of all cases. A single follow-up CT for incidental IPCs does not seem sufficient due to a high number (22%) of missed IPCs on CT.

Pancreatic cysts in general population on ultrasonography: Prevalence and development of risk score

BACKGROUND

Pancreatic cysts are related to the presence of ductal adenocarcinomas elsewhere in the pancreas, and are also associated with an increased risk of pancreatic adenocarcinoma in the future. Most of the previous studies that investigated the prevalence of pancreatic cysts focused on patients within a hospital or out-patient setting, which may not be representative of the general population. We investigated the prevalence and predictive factors for the presence of pancreatic cysts within a large number of subjects via general health examination.

METHODS

Between December 2007 and December 2013, a total of 5198 subjects were enrolled that underwent ultrasonography (US) on general health examination. We established a scoring system for predicting the presence of one or more pancreatic cysts using a split-sample method.

RESULTS

Among the enrolled subjects, the prevalence of a pancreatic cyst was 3.5 %. In multivariate analysis, the prevalence was significantly increased with older age, female sex, and the presence of gall bladder adenomyomatosis (GB-ADM). Based on multivariate analysis in the training sample (n = 2,599), we established the scoring system consisting of age, sex, and the presence of GB-ADM to predict the presence of pancreatic cysts. This scoring system was validated in the testing sample (n = 2,599) and produced an area under the curve of 0.711.

CONCLUSIONS

The prevalence of pancreatic cyst detected by US was 3.5 % in the general population, and increased with age, female sex, and the presence of GB-ADM. A new scoring system developed in the present study may help to identify better candidates for further examination when the pancreas is not visible by US.

Natural Language Processing in Radiology: A Systematic Review

Radiological reporting has generated large quantities of digital content within the electronic health record, which is potentially a valuable source of information for improving clinical care and supporting research. Although radiology reports are stored for communication and documentation of diagnostic imaging, harnessing their potential requires efficient and automated information extraction: they exist mainly as free-text clinical narrative, from which it is a major challenge to obtain structured data. Natural language processing (NLP) provides techniques that aid the conversion of text into a structured representation, and thus enables computers to derive meaning from human (ie, natural language) input. Used on radiology reports, NLP techniques enable automatic identification and extraction of information. By exploring the various purposes for their use, this review examines how radiology benefits from NLP. A systematic literature search identified 67 relevant publications describing NLP methods that support practical applications in radiology. This review takes a close look at the individual studies in terms of tasks (ie, the extracted information), the NLP methodology and tools used, and their application purpose and performance results. Additionally, limitations, future challenges, and requirements for advancing NLP in radiology will be discussed.

Prevalence, Diagnosis and Management of Pancreatic Cystic Neoplasms: Current Status and Future Directions

Cystic neoplasms of the pancreas are found with increasing prevalence, especially in elderly asymptomatic individuals. Although the overall risk of malignancy is very low, the presence of these pancreatic cysts is associated with a large degree of anxiety and further medical investigation due to concerns about malignancy. This review discusses the different cystic neoplasms of the pancreas and reports diagnostic strategies based on clinical features and imaging data. Surgical and nonsurgical management of the most common cystic neoplasms, based on the recently revised Sendai guidelines, is also discussed, with special reference to intraductal papillary mucinous neoplasm (IPMN; particularly the branch duct variant), which is the lesion most frequently identified incidentally. IPMN pathology, its risk for development into pancreatic ductal adenocarcinoma, the pros and cons of current guidelines for management, and the potential role of endoscopic ultrasound in determining cancer risk are discussed. Finally, surgical treatment, strategies for surveillance of pancreatic cysts, and possible future directions are discussed.

Measurement of pancreatic cystic lesions on magnetic resonance imaging: efficacy of standards in reducing inter-observer variability

PURPOSE

The purpose of this study is to assess inter-observer variability in the measurement of pancreatic cystic lesions with MRI and to determine the impact of measurement standards.

MATERIALS AND METHODS

In this IRB-approved, HIPAA-compliant study with waiver of informed consent, 144 MRI examinations, containing pancreatic cystic lesions measuring between 5 and 35 mm, were reviewed independently by two radiology attendings and two abdominal imaging fellows. Measurements were repeated by the same reviewers 12 weeks later after the introduction of measurement standards. Results were analyzed using within-subject standard deviation, intraclass correlation coefficient, and kappa.

RESULTS

Prior to standardization, the within-subject standard deviation, showing measurement variability in each cyst, was 4.0 mm, which was reduced to 3.3 mm after introduction of measurement standards (p < 0.01). Overall inter-observer agreement, kappa, improved from 0.59 to 0.65 (p = 0.04). The frequency of all four reviewers agreeing on size category increased from 51% to 60%. The intraclass correlation coefficient increased from 0.81 to 0.86.

CONCLUSIONS

There is significant and frequent inter-observer variability in the measurement of pancreatic cystic lesions with MRI which could affect clinical management. Implementation of measurement standards reduces measurement variability and aids in preventing erroneous reporting of growth and potentially unwarranted changes in management.

The actionable imaging report

The goal of a diagnostic imaging examination is to provide the referring provider with an actionable imaging report that can be used to impart information to determine optimal clinical management for the patient. An actionable imaging report not only conveys the findings of the examination accurately, but does so in a timely and safe manner for an imaging examination that was performed appropriately and using the correct technique. The use of information technology tools has been paramount in improving the value of the imaging report and continues to play a prominent role in this process. The diversity of abdominal imaging, in both the variety of imaging modalities available and the organ systems evaluated, makes it well-suited to adopt these information technology solutions to improve report quality, including increased consistency in reports and in follow-up recommendations. This review discusses the components of the imaging chain involved in optimizing the imaging report with specific emphasis on the role of information technology applications to address the challenges that are frequently encountered. Specific abdominal imaging examples are presented to provide practical guidance and clinical context.

Current therapeutic strategies for advanced pancreatic cancer: A review for clinicians

Pancreatic cancer (PC) would become the second leading cause of cancer death in the near future, despite representing only 3% of new cancer diagnosis. Survival improvement will come from a better knowledge of risk factors, earlier diagnosis, better integration of locoregional and systemic therapies, as well as the development of more efficacious drugs rising from a deeper understanding of disease biology. For patients with unresectable, non-metastatic disease, combined strategies encompassing primary chemotherapy and radiation seems to be promising. In fit patients, new polychemotherapy regimens can lead to better outcomes in terms of slight but significant survival improvement associated with a positive impact on quality of life. The upfront use of these regimes can also increase the rate of radical resections in borderline resectable and locally advanced PC. Second line treatments showed to positively affect both overall survival and quality of life in fit patients affected by metastatic disease. At present, oxaliplatin-based regimens are the most extensively studied. Nonetheless, other promising drugs are currently under evaluation. Presently, in addition to surgery and conventional radiation therapy, new locoregional treatment techniques are emerging as alternative options in the multimodal approach to patients or diseases not suitable for radical surgery. As of today, in contrast with other types of cancer, targeted therapies failed to show relevant activity either alone or in combination with chemotherapy and, thus, current clinical practice does not include them. Up to now, despite the fact of extremely promising results in different tumors, also immunotherapy is not in the actual therapeutic armamentarium for PC. In the present paper, we provide a comprehensive review of the current state of the art of clinical practice and research in PC aiming to offer a guide for clinicians on the most relevant topics in the management of this disease.

Assessment of Malignant Potential in Intraductal Papillary Mucinous Neoplasms of the Pancreas: Comparison between Multidetector CT and MR Imaging with MR Cholangiopancreatography

PURPOSE

To compare the diagnostic performance of multidetector computed tomography (CT) and magnetic resonance (MR) imaging with MR cholangiopancreatography (MRCP) in identifying the malignant potential of pancreatic intraductal papillary neoplasms (IPMNs) and evaluate their intermodality agreement.

MATERIALS AND METHODS

Institutional review board approval was obtained, and the requirement for informed consent was waived for this retrospective study. In 129 patients with pathologically proved pancreatic IPMNs, three reviewers independently evaluated their preoperative CT and MR imaging with MRCP findings. Intermodality agreement between multidetector CT and MR imaging with MRCP, as well as interobserver agreement of each imaging modality, for depicting high-risk stigmata and worrisome features were assessed. Diagnostic values of other signs of overt malignancy, including the presence of a parenchymal mass and local-regional extension, were analyzed. Diagnostic performance and intermodality agreement were assessed by using receiver operating characteristics (ROC) curve analysis and weighted κ statistics.

RESULTS

Overall, multidetector CT and MR imaging with MRCP were similar in their ability to depict signs suspicious or indicative of malignancy in patients with IPMN (area under the ROC curve [AUC] = 0.82 for both), with good intermodality agreement (κ = 0.75) and moderate interobserver agreement (κ = 0.47-0.59) when high-grade dysplasia was used as the cutoff for malignancy. When parenchymal masses and local-regional extensions were also considered as overt signs of malignancy, the ability to identify invasive IPMNs significantly increased (AUC = 0.87 for CT and AUC = 0.88 for MR imaging), with high sensitivity (94.3%), while maintaining specificity (69.1%).

CONCLUSION

The diagnostic performance of multidetector CT and MR imaging with MRCP for identifying the malignant potential of pancreatic IPMNs was similar and showed good intermodality agreement, suggesting that follow-up with either modality may be used.

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.

Incidental pancreatic cysts: natural history and diagnostic accuracy of a limited serial pancreatic cyst MRI protocol

OBJECTIVES

To examine the natural history of incidentally detected pancreatic cysts and whether a simplified MRI protocol without gadolinium is adequate for lesion follow-up.

METHODS

Over a 10-year period, 301-patients with asymptomatic pancreatic cysts underwent follow-up (45 months ± 30). The magnetic resonance imaging (MRI) protocol included axial, coronal T2-weighted images, MR cholangiopancreatographic and fat suppressed T1-weighted sequences before and after gadolinium. Three radiologists independently reviewed the initial MRI, the follow-up studies using first only unenhanced images, then secondly gadolinium-enhanced-sequences. Lesion changes during follow-up were recorded and the added value of gadolinium-enhanced sequences was determined by classifying the lesions into risk categories.

RESULTS

Three hundred and one patients (1,174 cysts) constituted the study population. Only 35/301 patients (12 %) showed significant lesion change on follow-up. Using multivariate analysis the only independent factor of lesion growth (OR = 2.4; 95 % CI, 1.7-3.3; P < 0.001) and mural nodule development (OR = 1.9; 95 % CI, 1.1-3.4, P = 0.03) during follow-up was initial lesion size. No patient with a lesion initial size less than 2 cm developed cancer during follow-up. Intra-observer agreement with and without gadolinium enhancement ranged from 0.86 to 0.97. After consensus review of discordant cases, gadolinium-enhanced sequences demonstrated no added value.

CONCLUSION

Most incidental pancreatic cystic lesions did not demonstrate change during follow-up. The addition of gadolinium-enhanced-sequences had no added-value for risk assignment on serial follow-up.

KEY POINTS

Significant growth of pancreatic cysts occurred in a minority of patients only. No lesion <2 cm demonstrated any change during the first year of follow-up. Intra-observer agreement between MR pancreatic protocols with and without gadolinium was excellent. Gadolinium application had limited value for follow-up of asymptomatic pancreatic cystic lesions.