Malignant Intraductal Papillary Mucinous Neoplasms Research Articles

Histological Subtypes Might Help Risk Stratification in Different Morphological Types of IPMNs: Back to the Future?

Background: Intraductal papillary mucinous neoplasms (IPMNs) display four histological subtypes: gastric foveolar, pancreaticobiliary, intestinal, and oncocytic. All of these subtypes harbor a different risk of cancer development. The clinical impact of these subtypes concerning the occurrence of high-grade dysplasia (HGD)/cancer (C) in specific morphological types, such as branch-duct (BD), main-duct (MD), and mixed-type (MT) IPMNs, has been less investigated. Hence, our aim was to investigate the prevalence of histological subtypes and their possible association with HGD/C concerning morphologically different IPMNs. Methods: This was a retrospective review of demographics, risk factors, and histological features in a surgical cohort of patients having undergone resection for suspect malignant IPMNs at a high-volume tertiary center from 2007 to 2017. Results: A total of 273 patients were resected for IPMNs from during the study period, of which 188 were included in the final analysis. With sex- and age-adjusted multivariable logistic regression analysis across the entire cohort, gastric foveolar subtypes were associated with a reduced prevalence of HGD/C (OR = 0.30; 0.11–0.81, 95% CI, 95%CI; p = 0.01). With univariable logistic regression analysis, in the BD-IPMN subgroup, the pancreaticobiliary subtype was associated with an increased prevalence of HGD/C (OR = 18.50, 1.03–329.65, 95% CI; p = 0.04). In MD- and MT-IPMNs, the gastric foveolar subtype was associated with a decreased prevalence of HGD/cancer (OR = 0.30, 0.13–0.69, 95% CI; p = 0.004). Conclusions: In MD and MT-IPMNs, the gastric-foveolar subtype is associated with a lower prevalence of HGD/C, possibly identifying in such a high-risk group, a subgroup with more indolent behavior. In BD-IPMNs, the pancreaticobiliary subtype is associated with a higher prevalence of HGD/C, conversely identifying among those patients, a subgroup deserving special attention.

Development of an intraductal papillary mucinous neoplasm malignancy prediction scoring system.

Despite the presence of various guidelines, diagnosing malignant intraductal papillary mucinous neoplasm (IPMN) continues to pose challenges. Furthermore, although endoscopic ultrasonography (EUS) offers high-resolution images, it has not yet recognized as the primary tool for malignancy diagnosis. The study objective was to develop a simplified and user-friendly scoring system to improve the diagnostic accuracy of malignant IPMNs. Additionally, the utility of EUS and its effect on diagnostic accuracy were assessed. We retrospectively collected the clinical data on 160 cases of resected IPMN at Tokyo Medical and Dental University Hospital from January 2008 to December 2022. We examined clinical features, computed tomography (CT) and magnetic resonance imaging (MRI) findings, and EUS results if available. We then calculated the odds ratio of malignancy for these factors and developed an IPMN malignancy prediction (IMAP) scoring system. There were 89 (55.6%) cases of benign IPMNs and 71 (44.4%) of malignant IPMNs. Eight clinical and imaging findings, including age, diabetes mellitus status, jaundice, CA19-9 level, enhancing mural nodules ≥5mm, thickened wall, and main duct dilatation, were significantly associated with malignancy. The IMAP score was calculated by assigning 0 to 2 points to these factors based on the odds ratio. The area under the receiver operating characteristic curve for the IMAP score was 0.78 [95% confidence interval (CI): 0.71-0.85] based on CT/MRI alone and improved to 0.81 (95% CI: 0.74-0.87) when EUS was added. When the total exceeds 5 points, the positive predictive value becomes 100% (95% CI: 95.9-100). In conclusion, the IMAP scoring system has demonstrated promise as a clinically useful tool, offering both simplicity and sufficient accuracy. It holds potential as an important decision criterion for determining the treatment approach for IPMN. Additionally, EUS contributes to enhancing the diagnostic accuracy of the IMAP scoring system, thereby enabling more precise decision-making.

Diagnostic Performance of Surgical Indication for Branch-duct or Mixed-type Intraductal Papillary Mucinous Neoplasms of the Revised International Association of Pancreatology (IAP) 2023 Guidelines.

To evaluate the diagnostic performance of surgical indications of the revised International Association of Pancreatology (IAP) 2023 guidelines compared to the IAP 2017 and European 2018 guidelines. The revised IAP guidelines for surgical indications for branch duct (BD) intraductal papillary mucinous neoplasms (IPMN) include the presence of at least two worrisome features without mandatory endoscopic ultrasound. Among 663 patients who underwent resection for pathologically confirmed IPMN in a tertiary hospital between 2013 and 2023, 556 patients with BD or mixed-type IPMN were retrospectively reviewed. Diagnostic performances of the three guidelines for predicting high-grade dysplasia or IPMN with invasive carcinoma were compared. The primary outcome was the malignancy rate. Clinicopathological and radiological imaging data were analyzed. A total of 540, 451, and 490 patients met the surgical indications of the IAP, 2017, 2023, and European guidelines, respectively. Malignant IPMN was observed in 229 (41.2%) patients (high-grade dysplasia, n=99; invasive carcinoma, n=130). Surgical indication by the IAP 2023 guidelines showed higher specificity (29.1 vs. 4.9%, P<0.001), positive predictive value (48.6 vs. 42.4%, P=0.031), and accuracy (55.5 vs. 44.1%, P<0.001) than the IAP 2017 guidelines. It also had higher specificity than the European guidelines (18.7%, P=0.024). The IAP 2023 guidelines showed a superior AUC of surgical indication (0.623 vs. 0.582 for the European guidelines, P<0.001; and 0.524 for the IAP guidelines, P=0.008). The IAP 2023 guidelines showed better malignancy prediction than the IAP 2017 and European guidelines, potentially reducing unnecessary surgeries.

Comprehensive analysis of clinical data and radiomic features from contrast enhanced CT for differentiating benign and malignant pancreatic intraductal papillary mucinous neoplasms

The primary aim of this investigation was to leverage radiomics features derived from contrast-enhanced abdominal computed tomography (CT) scans to devise a predictive model to discern the benign and malignant nature of intraductal papillary mucinous neoplasms (IPMNs). Radiomic signatures were meticulously crafted to delineate benign from malignant IPMNs by extracting pertinent features from contrast-enhanced CT images within a designated training cohort (n = 84). Subsequent validation was conducted with data from an independent test cohort (n = 37). The discriminative ability of the model was quantitatively evaluated through receiver operating characteristic (ROC) curve analysis, with the integration of carefully selected clinical features to improve the comparative analysis. Arterial-phase images were utilized to construct a model comprising 8 features for distinguishing between benign and malignant cases. The model achieved an accuracy of 0.891 [95% confidence interval (95% CI), 0.816–0.996] in the cross-validation set and 0.553 (95% CI 0.360–0.745) in the test set. Conversely, employing 9 features from the venous-phase resulted in a model with a cross-validation accuracy of 0.862 (95%CI 0.777–0.946) and a test set accuracy of 0.801 (95% CI 0.653–0.950).Integrating the identified clinical features with imaging features yielded a model with a cross-validation accuracy of 0.934 (95% CI 0.879–0.990) and a test set accuracy of 0.904 (95% CI 0.808–0.999), thereby further improving its discriminatory ability. Our findings distinctly illustrate that venous-phase radiomics features eclipse arterial-phase radiomic features in terms of predictive accuracy regarding the nature of IPMNs. Furthermore, the synthesis and meticulous screening of clinical features with radiomic data significantly increased the diagnostic efficacy of our model, underscoring the pivotal importance of a comprehensive and integrated approach for accurate risk stratification in IPMN management.

Optimization of Endoscopic Ultrasound Characteristics in the Diagnosis of Malignant Intraductal Papillary Mucinous Neoplasm.

Endoscopic ultrasound (EUS) is an excellent diagnostic tool that provides high-resolution images of pancreatic cystic lesions. However, its role in the diagnosis of malignant intraductal papillary mucinous neoplasm (IPMN) remains limited and unclear. We aimed to determine the usefulness of this modality for such diagnosis. Overall, 246 patients who underwent EUS for IPMN after computed tomography (CT)/magnetic resonance imaging (MRI) from April 2018 to June 2021 were followed up until March 2022. We assessed the added value of performing EUS after CT or MRI for diagnosing malignant IPMN, using receiver operating characteristic curve analysis. Walls as thick as 2 mm were considered thickened in this study if they were highly uneven. EUS clearly enhanced accuracy in identifying enhancing nodules and thickened walls. The areas under the receiver operating characteristic curve and corresponding 95% confidence intervals were 0.655 (0.549-0.760) and 0.566 (0.478-0.654) upon CT/MRI but 0.853 (0.763-0.942) and 0.725 (0.634-0.817) when observed using EUS. The combination of nodule size, thickened wall, and main duct size yielded the highest area under the receiver operating characteristic curve (0.944 [0.915-0.973]). EUS more accurately detects malignant IPMN, as uneven wall thickening and certain nodules cannot be identified with CT/MRI.

Intraductal papillary mucinous neoplasms of the pancreas: Cytologic-histologic correlation study and evaluation of the cytologic accuracy in identifying high-grade dysplasia/invasive adenocarcinoma.

Intraductal papillary mucinous neoplasms (IPMNs) may be associated with invasive adenocarcinoma, low-grade dysplasia (LGD), or high-grade dysplasia (HGD). We aimed to review the cytologic-histologic correlation of cases with a histologic diagnosis of IPMN. A database search (January 2010-January 2021) was performed for resected IPMNs with preceding endoscopic ultrasound-guided fine-needle aspiration (FNA). Cytology slides were reviewed for the presence of benign, atypical, or malignant cells, and necrosis. Histologically, IPMNs were classified as benign (LGD) or malignant (HGD or adenocarcinoma). There were 41 patients with IPMN; 24 malignant and 17 benign. Sixteen of the 24 malignant IPMNs were accurately classified as malignant on cytology. There were eight false negatives and one false positive. Cytology yielded a sensitivity of 67% and a specificity of 94%. Among the 16 true positives with FNA diagnosis of adenocarcinoma, seven were IPMNs with HGD, and nine had invasive adenocarcinomas on histology. Cellular morphology and absence or presence of necrosis did not help distinguish HGD from adenocarcinoma on cytology (P > 0.5). Sampling errors and interpretative errors resulted in false-negative cases. Cytology yielded diagnoses related to IPMN in 73% of cases (30/41) and lack of identification of mucinous cells/mucinous background resulted in interpretative errors (9). This study shows that there is a good correlation between cytopathology and surgical pathology diagnoses of IPMNs and that cytology is mostly able to recognize IPMN with HGD/adenocarcinoma. However, heterogeneity in areas of IPMN with HGD/adenocarcinoma may result in sampling errors yielding false-negative cases. Mucinous cells/background should raise the suspicion of IPMN on cytology, even when no neoplastic epithelium is present for the evaluation of dysplasia.

Serum elastase-1 predicts malignancy in intraductal papillary mucinous neoplasm of the pancreas

BackgroundThe indication for surgical resection of intraductal papillary mucinous neoplasms (IPMNs) is defined by imaging features, such as mural nodules. Although carbohydrate antigen (CA) 19-9 was selected as a parameter for worrisome features, no serum biomarkers were considered when deciding on surgical indications in the latest international consensus guideline. In this study, we assessed whether clinical factors, imaging findings, and serum biomarkers are useful in predicting malignant IPMNs. MethodsA total of 234 resected IPMN cases in Chiba University Hospital from July 2005 to December 2021 were retrospectively analyzed. ResultsAmong the 234 patients with resected IPMNs diagnosed by preoperative imaging, 117 were diagnosed with malignant pathologies (high-grade dysplasia and invasive IPMNs) according to the histological classification. In the multivariate analysis, cyst diameter ≥30 mm; p = 0.035), enhancing mural nodules on multidetector computed tomography (≥5 mm; p = 0.018), and high serum elastase-1 (≥230 ng/dl; p = 0.0007) were identified as independent malignant predictors, while CA19-9 was not. Furthermore, based on the receiver operator characteristic curve analyses, elastase-1 was superior to CA19-9 for predicting malignant IPMNs. Additionally, high serum elastase-1 levels (≥230 ng/dl; p = 0.0093) were identified as independent predictors of malignant IPMNs in patients without mural nodules on multidetector computed tomography (MDCT) in multivariate analysis. ConclusionThe serum elastase-1 level was found to be a potentially useful biomarker for predicting malignant IPMNs.

Predictors of malignant intraductal papillary mucinous neoplasm of the pancreas

Intraductal papillary mucinous neoplasm (IPMN) is the most common pancreatic cystic neoplasm with a tendency to malignancy,and the 5-year survival rate of patients with invasive IPMN is less than 40%. Therefore,early detection of malignant cases and surgical intervention will significantly improve patient outcomes. The clinical guidelines recommended risk factors for IPMN malignancy according to imaging characteristics,clinical manifestations and serum tumor markers,among which dilation of the main pancreatic duct≥10 mm,the presence of solid components or enhanced mural nodules,and obstructive jaundice were recognized as high-risk factors. However,clinical practice has shown that the risk factors recommended by the current guidelines are not highly accurate in predicting IPMN malignancy,and the main problem is that the guidelines are less specific and allow follow-up cases to undergo unnecessary surgical resection. In recent years,the development of new technologies and methods such as genomics,radiomics,and artificial intelligence has greatly promoted the research progress of IPMN. Endoscopic ultrasound-guided fine needle aspiration of cystic fluid combined with molecular detection such as DNA and RNA,as well as radiomics combined with machine learning modeling,have shown superiority in improving the prediction accuracy of malignant IPMN,and will become an important tool to assist the diagnosis and treatment of IPMN in the future.

Malignant Intraductal Papillary Mucinous Neoplasm With Underlying Annular Pancreas

Malignant Intraductal Papillary Mucinous Neoplasm With Underlying Annular Pancreas

Radiomics model versus 2017 revised international consensus guidelines for predicting malignant intraductal papillary mucinous neoplasms.

To evaluate a CT-based radiomics model for identifying malignant pancreatic intraductal papillary mucinous neoplasms (IPMNs) and compare its performance with the 2017 international consensus guidelines (ICGs). We retrospectively included 194 consecutive patients who underwent surgical resection of pancreatic IPMNs between January 2008 and December 2020. Surgical histopathology was the reference standard for diagnosing malignancy. Using radiomics features from preoperative contrast-enhanced CT, a radiomics model was built with the least absolute shrinkage and selection operator by a five-fold cross-validation. CT and MR images were independently reviewed based on the 2017 ICGs by two abdominal radiologists, and the performances of the 2017 ICGs and radiomics model were compared. The areas under the curve (AUCs) were compared using the DeLong method. A total of 194 patients with pancreatic IPMNs (benign, 83 [43%]; malignant, 111 [57%]) were chronologically divided into training (n = 141; age, 65 ± 8.6years; 88 males) and validation sets (n = 53; age, 66 ± 9.7years; 31 males). There was no statistically significant difference in the diagnostic performance of the 2017 ICGs between CT and MRI (AUC, 0.71 vs. 0.71; p = 0.93) with excellent intermodality agreement (k = 0.86). In the validation set, the CT radiomics model had higher AUC (0.85 vs. 0.71; p = 0.038), specificity (84.6% vs. 61.5%; p = 0.041), and positive predictive value (84.0% vs. 66.7%; p = 0.044) than the 2017 ICGs. The CT radiomics model exhibited better diagnostic performance than the 2017 ICGs in classifying malignant IPMNs. Compared with the radiologists' evaluation based on the 2017 international consensus guidelines, the CT radiomics model exhibited better diagnostic performance in classifying malignant intraductal papillary mucinous neoplasms. • There is a paucity of comparisons between the 2017 international consensus guidelines (ICGs) and radiomics models for malignant intraductal papillary mucinous neoplasms (IPMNs). • The CT radiomics model developed in this study exhibited better diagnostic performance than the 2017 ICGs in classifying malignant IPMNs. • The radiomics model may serve as a valuable complementary tool to the 2017 ICGs, potentially allowing a more quantitative assessment of IPMNs.

Prediction of malignant intraductal papillary mucinous neoplasm: A nomogram based on clinical information and radiological outcomes.

Clinical practitioners face a significant challenge in maintaining a healthy balance between overtreatment and missed diagnosis in the management of intraductal papillary mucinous neoplasm (IPMN). The current study aimed to identify significant risk factors of malignant IPMN from a series of clinical and radiological parameters that are widely available and noninvasive and develop a method to individually predict the risk of malignant IPMN to improve its management. We retrospectively investigated 168 patients who were pathologically diagnosed with IPMN after individualized pancreatic resection between June, 2012 and December, 2020. Independent predictors determined using both univariate and multivariate analyses to construct a predictive model. The discriminatory power of the nomogram was assessed using the area under the receiver operating characteristic curve (AUC). Decision curve analysis was performed to demonstrate the clinical usefulness of the nomogram. Internal cross validation was performed to assess the validity of the predictive model. In the multivariate analysis, five significant independent risk factors were identified: increased serum CA19-9 level, low prognostic nutritional index (PNI), cyst size, enhancing mural nodule, and main pancreatic duct diameter. The nomogram based on the parameters mentioned above had outstanding performance in distinguishing malignancy, with an AUC of 0.907 (95% confidence interval: 0.859-0.956, p < 0.05), which remained 0.875 after internal cross-validation, and showed good clinical usefulness. A novel nomogram for predicting malignant IPMN first introducing PNI was developed, which may aid in improving IPMN management. Nevertheless, external validation is required to confirm its efficacy.

A comparative study between computed tomography and endoscopic ultrasound in the detection of a mural nodule in intraductal papillary mucinous neoplasm –Multicenter observational study in Japan

Background/objectivesThe detection of malignancy is a major concern in the management of intraductal papillary mucinous neoplasm (IPMN). The height of the mural nodule (MN), estimated using endoscopic ultrasound (EUS) and computed tomography (CT), has been considered crucial for predicting malignant IPMN. Currently, whether surveillance using CT or EUS alone is sufficient for detecting MNs remains unclear. This study aimed to compare the ability of CT and EUS to detect MNs in IPMN. MethodsThis multicenter, retrospective observational study was conducted in 11 Japanese tertiary institutions. Patients who underwent surgical resection of IPMN with MN after CT and EUS examinations were eligible to participate. The MN detection rates between CT and EUS were examined. ResultsTwo-hundred-and-forty patients who underwent preoperative EUS and CT had pathologically confirmed MNs. The MN detection rates of EUS and CT were 83% and 53%, respectively (p < 0.001). Additionally, the MN detection rate of EUS was significantly higher than that of CT regardless of morphological type (76% vs. 47% in branch-duct-type IPMN; 90% vs. 54% in mixed IPMN; 98% vs. 56% in main-duct-type IPMN; p < 0.001). Further, pathologically confirmed MNs ≥5 mm were more frequently observed on EUS than on CT (95% vs. 76%, p < 0.001). ConclusionsEUS was superior to CT for the detection of MN in IPMN. EUS surveillance is essential for the detection of MNs.

Surgery for intraductal papillary mucinous neoplasms in young patients: High-risk population

BackgroundIntraductal papillary mucinous neoplasms of the pancreas are uncommon in young individuals. Management of these patients is challenging because the risk of malignancy and recurrence after surgery remains unclear. The aim of the present study was to assess the long-term risk for intraductal papillary mucinous neoplasm recurrence after surgery for intraductal papillary mucinous neoplasms in patients ≤50 years of age. MethodsPerioperative and long-term follow-up data of patients who had undergone surgery for intraductal papillary mucinous neoplasms between 2004 and 2020 were extracted from a prospective unicentric database and retrospectively analyzed. ResultsSeventy-eight patients underwent surgical treatment for benign intraductal papillary mucinous neoplasms (low-grade n = 22 and intermediate-grade n = 21) and malignant intraductal papillary mucinous neoplasms (high-grade n = 16 and intraductal papillary mucinous neoplasm–associated carcinoma n = 19). Severe postoperative morbidity (Clavien–Dindo ≥III) was found in 14 patients (18%). The median length of hospital stay was 10 days. No perioperative mortality was observed. The median length of follow-up was 72 months. Recurrence of intraductal papillary mucinous neoplasm–associated carcinoma was found in 6 patients (19%) with malignant intraductal papillary mucinous neoplasm and 1 patient (3%) with benign intraductal papillary mucinous neoplasm. ConclusionSurgery for intraductal papillary mucinous neoplasm is safe and can be performed with low morbidity and potentially no mortality in young patients. Given the high rate of malignancy (45%), these patients with intraductal papillary mucinous neoplasms represent a high-risk population, and prophylactic surgical treatment should be considered in these patients with long life expectancies. Regular clinical and radiologic follow-up examinations are important to rule out disease recurrence, which is high, especially in patients with intraductal papillary mucinous neoplasm–associated carcinoma.

Research progress and future directions on intraductal papillary mucinous neoplasm: A bibliometric and visualized analysis of over 30 years of research.

Malignant change from low-grade dysplasia to high-grade dysplasia and invasive carcinoma following an adenoma-carcinoma sequence is becoming more common in intraductal papillary mucinous neoplasm (IPMN) of the pancreas. The aim of this study is to analyze their main characteristics and recent research trends in IPMNs and consequently create better understandings of the current situation and trends. A comprehensive search was performed in The Science Citation Index Expanded of the Web of Science. All articles between 1990 and 2021 were searched. VOS viewer (Leiden University, Leiden, Netherlands) was used for a qualitative and quantitative analysis of keywords, constituting maps based on co-occurrence matrix. A total of 1658 eligible articles were screened among the 3950 identified articles for this subject. Finally, 879 articles were included in this study. Many articles on IPMN have been published in Japan and South Korea. Tanaka published the highest number of articles (n = 26, citations = 11,143). The Pancreas published the highest number of articles. (n = 100, citations = 2533). These articles were grouped into 4 clusters including basic research, disease overview, management/prognosis and malignant IPMN by using bibliometric keywords network analysis. Overlay visualization demonstrates, a trend of the studies has been changed from basic research or disease to management or prognosis. In this study, we found and highlight the most cited and influential articles related to IPMN. Plus, this study analyzed global research trends in IPMN over the past 30 years and provides insight into the features and research hotspots of the articles in IPMN research.

The effectiveness of endoscopic ultrasonography findings to distinguish benign and malignant intraductal papillary mucinous neoplasm

Background and aimsAccurate evaluation of intraductal papillary mucinous neoplasm (IPMN) is necessary to inform clinical decision-making. But it is still difficult to distinguish benign and malignant IPMN preoperatively. This study aims to evaluate the utility of EUS to predict the pathology of IPMN.MethodsPatients with IPMN who underwent endoscopic ultrasound within 3 months before surgery were collected from six centers. Logistic regression model and random forest model were used to determine risk factors associated with malignant IPMN. In both models, 70% and 30% of patients were randomly assigned to the exploratory group and validation group, respectively. Sensitivity, specificity, and ROC were used in model assessment.ResultsOf the 115 patients, 56 (48.7%) had low-grade dysplasia (LGD), 25 (21.7%) had high-grade dysplasia (HGD), and 34 (29.6%) had invasive cancer (IC). Smoking history (OR = 6.95, 95%CI: 1.98–24.44, p = 0.002), lymphadenopathy (OR = 7.91, 95%CI: 1.60–39.07, p = 0.011), MPD > 7 mm (OR = 4.75, 95%CI: 1.56–14.47, p = 0.006) and mural nodules > 5 mm (OR = 8.79, 95%CI: 2.40–32.24, p = 0.001) were independent risk factors predicting malignant IPMN according to the logistic regression model. The sensitivity, specificity, and AUC were 0.895, 0.571, and 0.795 in the validation group. In the random forest model, the sensitivity, specificity, and AUC were 0.722, 0.823, and 0.773, respectively. In patients with mural nodules, random forest model could reach a sensitivity of 0.905 and a specificity of 0.900.ConclusionsUsing random forest model based on EUS data is effective to differentiate benign and malignant IPMN in this cohort, especially in patients with mural nodules.

Intraductal Papillary Mucinous Neoplasm of Pancreas with High-Risk Stigmata or Worrisome Features: What do You Do? Physician’s View

There are still debated about surveillance interval, duration, diagnostic modality and treatment for intraductal papillary mucinous neoplasm (IPMN) of the pancreas. In recent guidelines, ‘high risk stigmata (HRS)’ and ‘worrisome feature (WF)’ are defined as predictive factors for malignancy in IPMN. IPMNs with HRS and main duct- IPMN are more likely to accompany malignancies, thus require surgery. However, in the case of only WF, since the risk of malignancy is different for each factor, the management decision can be variable according to the number of overlapping WFs. In addition, for segmental main pancreatic duct dilatation without enhancing mural nodules, careful surveillance might be considered rather than immediate surgery. In IPMN patients with elderly or severe comorbidities, treatment strategy should be determined based on surgical and malignant risk assessment. To date, the natural course of IPMN patients with HRS and WF is not well understood, thus further studies with a large number of patients are needed.

ASO Visual Abstract: New Diagnostic Modality Combining Mass Spectrometry and Machine Learning for the Discrimination of Malignant Intraductal Papillary Mucinous Neoplasms.

ASO Visual Abstract: New Diagnostic Modality Combining Mass Spectrometry and Machine Learning for the Discrimination of Malignant Intraductal Papillary Mucinous Neoplasms.

A model for predicting degree of malignancy in patients with intraductal papillary mucinous neoplasm.

There is no predictive model available to address early stage malignant intraductal papillary mucinous neoplasm (IPMN) including high grade dysplasia (HGD) and pT1a (invasive component≤0.5 cm). The aim of this study was to establish an objective and sufficient model to predict the degree of malignancy in patients with IPMN, which can be easily applied in daily practice and adopted for any type of lesion. A retrospective cohort study of 309 patients who underwent surgical resection for IPMN was performed. Members of the cohort were randomly allocated to the training or testing set. A detection tree model and random forest model were used for a 3-class classification to distinguish low grade dysplasia (LGD), HGD/pT1a IPMN, and invasive intraductal papillary mucinous cancer (I-IPMC) beyond pT1a. Of the 309 patients, 54 (17.4%) had early stage malignancy (19 HGD, 35 pT1a), 49 (15.9%) had I-IPMC beyond pT1a, and 206 (66.7%) had LGD IPMN. We proposed a 3-class classification model using a random forest algorithm, and the model had an accuracy of 99.5% with the training set, and displayed an accuracy of 96.0% with the testing set. We used SHAP for interpretation of the model and showed the top five factors (mural nodule size, main pancreatic duct diameter, CA19-9 levels, lesion edge and common bile duct dilation) were most likely to influence the 3-class classification results in terms of interpretation of the random forest model. This predictive model will help assess an individual's risk for different stages of IPMN malignancy and may help identify patients with IPMN who require surgery.

New Diagnostic Modality Combining Mass Spectrometry and Machine Learning for the Discrimination of Malignant Intraductal Papillary Mucinous Neoplasms

BackgroundAn intraductal papillary mucinous neoplasm (IPMN) is a pancreatic tumor with malignant potential. Although we anticipate a sensitive method to diagnose the malignant conversion of IPMN, an effective strategy has not yet been established. The combination of probe electrospray ionization-mass spectrometry (PESI-MS) and machine learning provides a promising solution for this purpose.MethodsWe prospectively analyzed 42 serum samples obtained from IPMN patients who underwent pancreatic resection between 2020 and 2021. Based on the postoperative pathological diagnosis, patients were classified into two groups: IPMN-low grade dysplasia (n = 17) and advanced-IPMN (n = 25). Serum samples were analyzed by PESI-MS, and the obtained mass spectral data were converted into continuous variables. These variables were used to discriminate advanced-IPMN from IPMN-low grade dysplasia by partial least square regression or support vector machine analysis. The areas under receiver operating characteristics curves were obtained to visualize the difference between the two groups.ResultsPartial least square regression successfully discriminated the two disease classes. From another standpoint, we selected 130 parameters from the entire dataset by PESI-MS, which were fed into the support vector machine. The diagnostic accuracy was 88.1%, and the area under the receiver operating characteristics curve was 0.924 by this method. Approximately 10 min were required to perform each method.ConclusionPESI-MS combined with machine learning is an easy-to-use tool with the advantage of rapid on-site analysis. Here, we show the great potential of our system to diagnose the malignant conversion of IPMN, which would be a promising diagnostic tool in clinical settings.

Threshold of Main Pancreatic Duct Diameter in Identifying Malignant Intraductal Papillary Mucinous Neoplasm by Magnetic Resonance Imaging.

Objective: Intraductal papillary mucinous neoplasm (IPMN) is a rare pancreatic lesion. The identification of malignancy is critical for the establishment of treatment strategies. Main pancreatic duct (MPD) diameter is one critical feature for malignant IPMNs. However, the threshold of 1.0 cm is challenged. In this study, we explored independent risk factors and further calculated the threshold of MPD in identifying malignant IPMNs. Method: A total of 151 IPMN patients were included in this retrospective study. Demographic information, clinicopathological features, laboratory testing, and preoperative radiological characteristics by magnetic resonance imaging were collected. The receiver operating characteristic (ROC) curves were performed to determine the MPD diameter's cutoff levels and evaluate the predicted factors' diagnostic ability. Results: A cutoff value of 0.77 cm MPD (an area under the curve (AUC) = 0.746) in all IPMNs and 0.82 cm (AUC = 0.742) in the main duct involved IPMNs was obtained. MPD diameter (odds ratio (OR), 12.67; 95% confidence interval (CI), 4.80-33.48) and the mural nodule (OR, 12.98; 95% CI, 3.18-52.97) were the independent associated factors with high-risk IPMNs. The combined model with MPD and mural nodule showed a better predictive performance than mural nodule or MPD diameter alone (AUC = 0.803 vs 0.619, 0.746). A nomogram was developed and showed good performance (C index = 0.803). Conclusion: Our data show that mural nodule and MPD diameter are independent risk factors in identifying malignant intraductal papillary mucinous neoplasms. A cutoff value of 0.77 cm of MPD diameter may be a threshold value in identifying malignant intraductal papillary mucinous neoplasms or undergoing surgical resection.