Bagci, Ulas

Abstract Pancreatic cancer, projected to become the second-deadliest malignancy in Western societies by 2030, requires urgent innovations in early detection and risk stratification. Intraductal papillary mucinous neoplasms (IPMNs) represent critical precursor lesions, but current clinical guidelines demonstrate suboptimal accuracy in malignancy prediction, leading to either unnecessary surgeries or missed opportunities for early intervention. In this paper, we present Cyst-X, an artificial intelligence (AI) framework that accurately predicts IPMN malignant transformation using multicenter magnetic resonance imaging (MRI) data. Unlike most previous approaches that rely on computed tomography (CT), our method capitalizes on the superior soft tissue contrast of MRI, allowing for more precise identification of subtle imaging biomarkers. We developed and validated deep learning models on 723 T1-weighted and 738 T2-weighted MRI scans from 764 patients among seven international institutions, demonstrating significantly superior performance (AUC=0.82) compared to current clinical (Kyoto) guidelines (AUC=0.75) and expert radiologists. AI-based imaging features correlate strongly with clinically recognized malignancy markers, providing potential biologically relevant insights. This approach holds promise to significantly refine clinical decision-making, reduce unnecessary surgeries, and better identify high-risk IPMN patients for timely intervention. Our approach integrates a novel pancreas segmentation network with robust classification models that identify subtle imaging biomarkers associated with malignancy risk. Importantly, we demonstrate that these models retain high performance in a privacy-preserving federated learning setting, where institutions collaboratively train AI models without exchanging patient data to address key regulatory and ethical barriers. We publicly release the Cyst-X dataset--the first large-scale, multi-center pancreatic cyst MRI collection--to accelerate research in this field. This study addresses a critical clinical need while establishing technical foundations for privacy-preserving AI in radiology that could transform pancreatic cancer management through earlier intervention and reduced unnecessary procedures. The dataset can be accessed at https://osf.io/74vfs/, and the source code for our deep learning segmentation and classification models is available at https://github.com/NUBagciLab/Cyst-X.

Pancreatic cystic lesions (PCLs) represent a spectrum of non-neoplasms and neoplasms with varying malignant potential, posing significant challenges in diagnosis and management. While some PCLs are precursors to pancreatic cancer, others remain benign, necessitating accurate differentiation for optimal patient care. Conventional approaches to PCL management rely heavily on radiographic imaging, and endoscopic ultrasound (EUS) guided fine-needle aspiration (FNA), coupled with clinical and biochemical data. However, the observer-dependent nature of image interpretation and the complex morphology of PCLs can lead to diagnostic uncertainty and variability in patient management strategies. This review critically evaluates current PCL diagnosis and surveillance practices, showing features of the different lesions and highlighting the potential limitations of conventional methods. We then explore the potential of artificial intelligence (AI) to transform PCL management. AI-driven strategies, including deep learning algorithms for automated pancreas and lesion segmentation, and radiomics for analyzing heterogeneity, can improve diagnostic accuracy and risk stratification. These advanced techniques can provide more objective and reproducible assessments, aiding clinicians in decision-making regarding follow-up intervals and surgical interventions. Early results suggest that AI-driven methods can significantly improve patient outcomes by enabling earlier detection of high-risk lesions and reducing unnecessary procedures for benign cysts. Finally, this review emphasizes that AI-driven approaches could potentially reshape the landscape of PCL management, ultimately leading to improved pancreatic cancer prevention.

Objective This study aimed to evaluate a deep learning protocol to identify neoplasia in intraductal papillary mucinous neoplasia (IPMN) in comparison to current radiographic criteria. Methods A computer-aided framework was designed using convolutional neural networks to classify IPMN. The protocol was applied to magnetic resonance images of the pancreas. Features of IPMN were classified according to American Gastroenterology Association guidelines, Fukuoka guidelines, and the new deep learning protocol. Sensitivity and specificity were calculated using surgically resected cystic lesions or healthy controls. Results Of 139 cases, 58 (42%) were male; mean (standard deviation) age was 65.3 (11.9) years. Twenty-two percent had normal pancreas; 34%, low-grade dysplasia; 14%, high-grade dysplasia; and 29%, adenocarcinoma. The deep learning protocol sensitivity and specificity to detect dysplasia were 92% and 52%, respectively. Sensitivity and specificity to identify high-grade dysplasia or cancer were 75% and 78%, respectively. Diagnostic performance was similar to radiologic criteria. Areas under the receiver operating curves (95% confidence interval) were 0.76 (0.70–0.84) for American Gastroenterology Association, 0.77 (0.70–0.85) for Fukuoka, and 0.78 (0.71–0.85) for the deep learning protocol ( P = 0.90). Conclusions The deep learning protocol showed accuracy comparable to current radiographic criteria. Computer-aided frameworks could be implemented as aids for radiologists to identify high-risk IPMN.