Introduction

Endoscopic ultrasound (EUS) is the gold standard for evaluating pancreatic lesions, allowing for real-time imaging and biopsy sampling. Nevertheless, the differentiation between solid pancreatic lesions — such as pancreatic ductal adenocarcinoma (PDAC) and pancreatic neuroendocrine tumors (PNETs) — as well as cystic lesions is often troublesome. Specifically, identifying intraductal papillary mucinous neoplasms (IPMNs) with varying degrees of dysplasia is crucial for guiding clinical management. However, the diagnostic accuracy of current methods remains suboptimal. This multicenter study aimed to develop and validate convolutional neural networks (CNNs) to characterize solid and cystic pancreatic lesions and stratify IPMNs into high-grade dysplasia/carcinoma (HGD/C) and low-grade dysplasia (LGD).

Aims & Methods

This multicenter study included EUS images from 12 centers in Spain, Brazil, the United Kingdom and the United States of America. Solid lesion differentiation (PDAC vs. PNET) was achieved using a CNN trained on 49034 images from 95 patients (n=69 for PDAC and n=26 for PNET), with diagnoses confirmed via EUS-guided fine-needle biopsy or surgical specimen analysis. A second CNN was trained on 79395 images from 82 patients (n=64 for mucinous cystic lesions and n=18 for non-mucinous cystic lesions). Finally, a third model used the subset of IPMNs (n=51046 frames, 30 patients) to distinguish between HGD/C (n=5 patients) and LGD (n=25 patients). Histological confirmation was used as the gold standard. Performance metrics included sensitivity, specificity, accuracy, and area under the precision-recall curve (AUC-PR). To comprehensively determine the model's performance, we evaluated multiple thresholds for the confidence score and the IoU, between 0.45 and 0.55 with a step of 0.02 ([0.45, 0.47, 0.50, 0.52, 0.55]). The datasets were split into training (70%), validation (20%), and testing (10%) subsets.

Results

For solid lesions, the model differentiated PDAC from PNETs with an accuracy of 91.8%, with sensitivities of 96.2% and 97.8%, respectively. The AUC-PR was 0.982 for PDAC and 0.977 for PNET. Regarding cystic lesions the model detected mucinous cystic lesions with a sensitivity of 97.5%, an overall accuracy of 89.7% and an AUC-PR of 0.977. When the subset of IPMNs was specifically analyzed, the model distinguished IPMNs with HGD/C from those with LGD with a sensitivity of 97.5%, specificity of 94.3%, and an overall accuracy of 89.8%. The AUC was 0.988.

Conclusion

This is the first multicenter, transatlantic AI study aiming to provide a holistic approach to both solid and cystic pancreatic lesions, focusing on those with a significantly higher malignant potential. Our models achieved high accuracy in identifying and differentiating these conditions. Furthermore, to our knowledge this is the first integrative model to include the ability to stratify IPMNs into LGD and HGD/C, which has significant clinical implications, potentially reducing unnecessary surgeries and ensuring timely intervention for high-risk patients. The inclusion of data from diverse regions reduces demographic bias and enhances model generalizability. Real-time implementation of these solutions could significantly improve decision-making in EUS and optimize patient outcomes.

Introduction

​​​​​Pancreatic cancer (PC) has one of the poorest prognoses among malignancies. Early detection, particularly of stage 0 or stage 1 disease, is crucial to improving survival outcomes. However, conventional screening strategies based solely on family history or symptoms—as commonly practiced in Western countries—have shown limited sensitivity for early-stage PC. In Japan, more comprehensive approaches are being developed.

Aims & Methods

Low-grade relevant (LGR) factor	High-grade relevant (HGR) factor
・sporadic family history ・diabetes mellitus ・diabetes mellitus worsening ・stomach/back symptoms ・weight loss ・elevated serum pancreatic enzyme ・heavy alcohol consumption ・smoking history ・obesity	・familial PC ・hereditary PC syndrome/pancreatitis ・new-onset diabetes mellitus ・jaundice ・elevated serum tumor biomarkers ・chronic pancreatitis ・pancreatic cyst ・main pancreatic duct dilation
Score positive; 3 points or more	Score positive; 1 point or more

This nationwide, multicenter prospective study aimed to evaluate the utility of a novel scoring system for early PC detection among hospital outpatients. From August 2019 to May 2024, all outpatients presenting with symptoms, risk factors, subtle imaging abnormalities of the pancreas, or requesting pancreatobiliary screening at the Department of Gastroenterology in hospitals participating in the Early Pancreatic Cancer Screening Study (EPSS) were considered for inclusion. Consecutive patients who had no pancreatic tumors suspected by any imaging modalities were examined, no prior history of endoscopic ultrasound (EUS) examination for pancreatic disease, and/or no referrals from other hospitals specifically for PC diagnosis were prospectively enrolled. The system comprised low- and high-grade relevant (LGR/HGR) factors referring to both risk factors and diagnostic indicators, including symptoms and subtle imaging abnormalities associated with PC. Patients were classified as score-positive if they had ≥3 LGR or ≥1 HGR factor(s). Diagnostic yield for stage 0/1 and all-stage PC was compared between score-positive and score-negative groups. Diagnostic performance was also evaluated against previous large-scale Japanese data and Western screening methods based on family/genetic risk or symptoms. The sample size was determined based on a previous large-scale PC screening study in Japan.

Results

Of 3,287 patients, 2,531 were score-positive and 756 were score-negative. PC was diagnosed in 283 patients (8.6%), including 67 with stage 0/1 disease. The detection rate of stage 0/1 PC was significantly higher in score-positive than in score-negative patients (2.6% vs. 0.7%, P=.001). Compared to a previous Japanese study (0.78%), this study showed a significantly higher detection rate (P<.001). The sensitivity of the scoring system for stage 0/1 PC was 93.1%, significantly outperforming Western-style approaches (12.5% for family/genetic risk and 50.0% for symptom-based screening; both P<.001), while maintaining comparable accuracy. Even combining family/genetic risk and symptoms, sensitivity remained lower than that of the scoring system (56.9%, P<.001). For all-stage PC, both the accuracy and sensitivity of the diagnosis based on the scoring system were significantly higher than those based on family/genetic risk, symptom, or the combination of symptom and family/genetic risk (P = .030, .004, .002 for accuracy; and all P <.001 for sensitivity, respectively). Among the 283 PC cases, 23.7% were stage 0/1, 15.9% were ≤10 mm, and 45.6% underwent surgical resection. Multivariate logistic analysis identified older age, worsening diabetes, and MPD dilation as significant independent predictors of stage 0/1 PC.

Conclusion

The scoring system demonstrated superior sensitivity and comparable accuracy to traditional screening strategies for detecting early-stage PC. Its use in outpatient settings may facilitate earlier diagnosis and intervention, thereby improving resectability and prognosis.

References

Klein AP. Pancreatic cancer epidemiology: understanding the role of lifestyle and inherited risk factors. Nat Rev Gastroenterol Hepatol 2021;18:493-502.
Hanada K, Okazaki A, Hirano N, et al. Diagnostic strategies for early pancreatic cancer. J Gastroenterol 2015;50:147-54.
Sagami R, Hayasaka K, Ujihara T, et al. Role of EUS combined with a newly modified scoring system to detect pancreatic high-grade precancerous lesions. Endosc Ultrasound 2022.

Introduction

Intraductal papillary mucinous neoplasms (IPMNs) of the pancreas are the most frequently identified precursor lesions of pancreatic cancer (PDAC). Only a minority progress towards malignancy, making their identification a critical point in cancer prevention. The available guidelines are imprecise, commonly resulting in over treatment of indolent lesions.

Aims & Methods

The aim of this study (EMI-IPMN, NCT06706700) is to discover novel biological and radiological biomarkers that can distinguish malignant from benign IPMNs. We focused on Endocrine, Metabolic and Inflammatory (EMI) factors, some pathways that are characterized in PDAC but poorly investigated in IPMN progression.
Patients with a presumed diagnosis of IPMN with indication for surgical resection who underwent high-quality magnetic resonance imaging (MRI) and/or computed tomography (CT), were prospectively enrolled. Peripheral blood (PB) and cyst fluid (CF) samples were collected during surgery, and lesions were histologically classified as IPMN with low-grade dysplasia (LGD), high-grade dysplasia (HGD), or invasive cancer (IC). Malignant IPMNs were defined as those with HGD and IC. Cytokine and hormone levels were measured in both fluids using multiplex assays and compared across the diagnostic groups. Continuous variables were converted into categorical variables based on optimal cut-off values, and both univariate and multivariate logistic regression analyses were conducted.

Results

Among the 205 patients enrolled, 133 (58 females, 75 males, median age 69.2) had a histological diagnosis of IPMN: 49 (36.8%) had LGD, 44 (33.1%) HGD and 40 (30.1%) had IC. Analysis of the EMI profile revealed higher concentrations of several markers (IL-8, VEGF, GLP-1, glucagon, and C-peptide) in CF compared to PB. Specific cytokines such as MCP-1 IP-10, TNFα, and IL-8 were significantly elevated in the CF of HGD/IC cases compared to LGD (p=0.05, 0.041, 0.001 and 0.025 respectively). Similarly, IP-10, IL-8, and MDC levels in PB were higher in HGD/IC patients (p=0.006, 0.008 and 0.004 respectively).
Pancreatic fat content, assessed with mDixon Quant Fat Fraction MRI sequences, was notably higher in HGD/IC patients (13.89%) compared to LGD patients (8.38%, p<0.05), and positively correlated with MCP-1 levels in CF.
Among these biological and radiological markers TNFα in the CF demonstrated a substantial diagnostic accuracy for identifying malignant IPMN, with an area under the ROC curve (AUC) of 0.72. In the final multivariable analysis we demonstrate that high TNFα levels in CF and HbA1c were the two independent risk factors for the identification of malignant IPMN (OR 10.8 and 1.11 respectively).

Conclusion

The progression of IPMN to PDAC is associated with a proinflammatory shift in the tumor microenvironment, reflected by local (CF) and systemic (PB) elevations in key cytokines (TNFα, MCP-1, and IL-8) whose involvement in PDAC progression is well established. Elevated hormone levels in CF, along with the strong association between malignant IPMN and HbA1c, underscore the critical role of endocrine alterations in the early stages of pancreatic tumorigenesis. These findings may be harnessed to enable earlier detection of malignant transformation in IPMN. Moreover, the correlation between imaging markers and biological profiles suggests that MRI could serve as non-invasive proxies for underlying pathological changes. Together, these results offer new insights into the pathophysiology of IPMN progression and may imporve diagnostic strategies