Background and Aims: Focal liver lesions (FLLs) are defined as abnormal solid or liquid masses differentiated from normal liver, frequently being clinically asymptomatic. The aim of this systematic review is to provide a comprehensive overview of current artificial intelligence (AI) applications, deep learning systems and convolutional neural networks, capable of performing a completely automated diagnosis of FLLs. Methods: We searched PubMed, Cochrane Library, EMBASE, and WILEY databases using predefined keywords. Articles were screened for relevant publications about AI applications capable of automated diagnosis of FLLs. The search terms included: (focal liver lesions OR FLLs OR hepatic focal lesions OR liver focal lesions OR liver tumor OR hepatic tumor) AND (artificial intelligence OR machine learning OR neural networks OR deep learning OR automated diagnosis OR ultrasound OR US OR computer scan OR CT OR magnetic resonance imaging OR MRI OR computer-aided diagnosis OR automated computer tomography OR automated magnetic imaging). Results: Our search identified a total of 32 articles analyzing complete automated imagistic diagnosis of FLLs, out of which 14 studies analyzing liver ultrasound images, 8 studies analyzing computer tomography images and 10 studies analyzing images obtained from magnetic resonance imaging. Conclusions: We found significant evidence demonstrating that implementing a complete automated system for FLLs diagnosis using AI-based applications is currently feasible. Various automated AI-based applications have been analyzed. However, there is no clear evidence about the superiority of any of the systems.

Ampullary lesions, neoplasms originating in the papilla of Vater, represent a rare yet clinically significant group of tumors with diverse etiologies and management challenges. This comprehensive review aims to elucidate the pivotal role of endoscopic ultrasound (EUS) in the diagnosis, staging, and management of ampullary lesions. This review begins by providing an overview of ampullary lesions, their epidemiology, and associated risk factors. We delve into their clinical presentation, emphasizing the importance of early and accurate diagnosis. Furthermore, we explore the limitations of traditional diagnostic modalities and highlight the growing relevance of EUS in ampullary lesion evaluation. We discuss the superior spatial resolution of EUS in comparison with other imaging methods, and we present an in-depth analysis of EUS-guided sampling and its pivotal role in obtaining histological samples for accurate diagnosis. In addition to diagnosis, we examine the indispensable role of EUS in ampullary lesion staging and its clinical implications. Furthermore, we discuss the potential of EUS in the surveillance and follow-up of ampullary lesions, ensuring timely detection of recurrence and monitoring treatment response in sporadic cases and in the context of familial syndromes, such as familial adenomatous polyposis (FAP). In conclusion, this review underscores the indispensable role of endoscopic ultrasound in the multifaceted approach to ampullary lesion evaluation. EUS not only enhances diagnostic accuracy but also informs treatment decisions and minimally invasive therapeutic interventions. As our understanding of ampullary lesions continues to evolve, EUS remains an invaluable tool for the improvement of patient outcomes and quality of life.

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive disease with limited survival. Curative opportunities are only available for patients with resectable cancer. Palliative chemotherapy is the current standard of care for unresectable tumors. Numerous efforts have been made to investigate new therapeutic strategies for PDAC. Immunotherapy has been found to be effective in treating tumors with high microsatellite instability (MSI-H), including PDAC. The ability of the Endoscopic Ultrasound Fine Needle Biopsy (EUS-FNB) to reliably collect tissue could enhance new personalized treatment by permitting genomic alterations analysis. The aim of this study was to investigate the feasibility of obtaining adequate DNA for molecular analysis from EUS-FNB formalin-fixed-paraffin-embedded (FFPE) specimens. For this purpose, FFPE-DNA obtained from 43 PDAC archival samples was evaluated to verify adequacy in terms of quantity and quality and was tested to evaluate MSI-H status by droplet digital PCR (ddPCR). All samples were suitable for ddPCR analysis. Unlike the 1–2% MSI-H frequency found with traditional techniques, ddPCR detected this phenotype in 16.28% of cases. This study suggests the ddPCR ability to identify MSI-H phenotype, with the possibility of improving the selection of patients who may benefit from immunotherapy and who would be excluded by performing traditional diagnostic methods.

Pancreatic ductal adenocarcinoma (PDAC) is a lethal disease with a dismal prognosis; this is in part due to its late diagnosis at advanced stages. For many patients, medical treatment is the only practicable therapy. In recent years, the development of new technologies that investigate genomic biomarkers has improved the concept of precision medicine to treat patients with PDAC. Through endoscopic ultrasound–tissue acquisition (EUS-TA), tissue from pancreatic cancers can be collected; thus, it has the potential to advance personalized treatment by allowing the assessment of genomic alterations. In this review, we explore the role of EUS in genomic profiling and its strengths and pitfalls in obtaining samples for next-generation sequencing (NGS).