Application of Artificial Intelligence in the Management of Pancreatic Cystic Lesions

Abstract

The rate of incidentally detected pancreatic cystic lesions (PCLs) has increased over the past decade and was recently reported at 8%. These lesions pose a unique challenge, as each subtype of PCL carries a different risk of malignant transformation, ranging from 0% (pancreatic pseudocyst) to 34-68% (main duct intraductal papillary mucinous neoplasm). It is imperative to correctly risk-stratify the malignant potential of these lesions in order to provide the correct care course for the patient, ranging from monitoring to surgical intervention. Even with the multiplicity of guidelines (i.e., the American Gastroenterology Association guidelines and Fukuoka/International Consensus guidelines) and multitude of diagnostic information, risk stratification of PCLs falls short. Studies have reported that 25-64% of patients undergoing PCL resection have pancreatic cysts with no malignant potential, and up to 78% of mucin-producing cysts resected harbor no malignant potential on pathological evaluation. Clinicians are now incorporating artificial intelligence technology to aid in the management of these difficult lesions. This review article focuses on advancements in artificial intelligence within digital pathomics, radiomics, and genomics as they apply to the diagnosis and risk stratification of PCLs.

Keywords: IPMN; artificial intelligence; endoscopic ultrasound; genomics; pancreatic cystic lesions; radiomics.

Figure 1

EUS-nCLE image of IPMN. A: Left panel: IPMN epithelium and vascular core. Each linear marking corresponds to a different epithelial thickness, as shown in the adjacent measurement. B: Right panel: IPMN epithelium and vascular core, with measurements of epithelial density as proxied by pixel intensity in image, with corresponding histogram of mean pixel intensity.

Figure 2

A comparison of EUS-nCLE images. Top panel: IPMNs with low grade dysplasia. The thin and translucent epithelium is noted by red arrows on EUS-nCLE images. Bottom panel: IPMN with high grade dysplasia. The thicker and darker epithelium is noted by yellow arrows.

Figure 3

Integration of diagnostics for the prediction of HGD-Ca: Standard of care (SOC) variables: Demographics and patient characteristics; age, gender, onset of diabetes, family history symptoms, pancreatitis history, serum CA 19-9, and cyst fluid analysis (glucose, CEA, cytology). Cyst and pancreas morphology: CT/MRI/EUS: size, wall, thickness, mural nodules, growth rate, and pancreatic duct diameter. nCLE: needle-based confocal laser endomicroscopy. NGS: Next generation sequencing.