Enhanced endoscopic ultrasound imaging for pancreatic lesions: The road to artificial intelligence

Abstract

Early detection of pancreatic cancer has long eluded clinicians because of its insidious nature and onset. Often metastatic or locally invasive when symptomatic, most patients are deemed inoperable. In those who are symptomatic, multi-modal imaging modalities evaluate and confirm pancreatic ductal adenocarcinoma. In asymptomatic patients, detected pancreatic lesions can be either solid or cystic. The clinical implications of identifying small asymptomatic solid pancreatic lesions (SPLs) of < 2 cm are tantamount to a better outcome. The accurate detection of SPLs undoubtedly promotes higher life expectancy when resected early, driving the development of existing imaging tools while promoting more comprehensive screening programs. An imaging tool that has matured in its reiterations and received many image-enhancing adjuncts is endoscopic ultrasound (EUS). It carries significant importance when risk stratifying cystic lesions and has substantial diagnostic value when combined with fine needle aspiration/biopsy (FNA/FNB). Adjuncts to EUS imaging include contrast-enhanced harmonic EUS and EUS-elastography, both having improved the specificity of FNA and FNB. This review intends to compile all existing enhancement modalities and explore ongoing research around the most promising of all adjuncts in the field of EUS imaging, artificial intelligence.

Fractal nature of human gastrointestinal system: Exploring a new era

“…Fractal analysis revealed a significant difference in mean surface fractal dimensions between malignant lesions and neuroendocrine tumors, suggesting that combining EUS elastography with pSR and fractal-based analysis is a promising method for quantitatively characterizing SPLs[ 60 ].…”

Applications and Prospects of Artificial Intelligence-Assisted Endoscopic Ultrasound in Digestive System Diseases

“…PDAC is the most common type of PC, and the majority of diseases are diagnosed at an advanced stage with poor prognosis. Early detection of small lesions and timely excision could improve the five-year survival rate to 80.4% [61]. Traditional imaging techniques such as CT and MRI may not be able to discover smaller lesions, while EUS is the most sensitive modality for the recognition of small solid pancreatic lesions, especially for lesions smaller than 20 mm [62,63].…”

The Role of Endoscopic Ultrasound and Ancillary Techniques in the Diagnosis of Autoimmune Pancreatitis: A Comprehensive Review

“…Nowadays, the progress in terms of the resolution of conventional images and the development of ancillary techniques, such as elastography and contrast enhancement, has further increased the diagnostic yield of EUS. Data from artificial intelligence and EUS-based convolutional neural network models show promise in the differentiation of AIP and pancreatic masses, but their implementation in clinical practice is still in an early stage [ 40 , 41 ].…”