Search

Focal liver lesions (FLL) are common incidental findings in abdominal imaging. While the majority of FLLs are benign and asymptomatic, some can be malignant or pre-malignant, and need accurate detection and classification. Current imaging techniques, such as computed tomography (CT) and magnetic resonance imaging (MRI), play a crucial role in assessing these lesions. Artificial intelligence (AI), particularly deep learning (DL), offers potential solutions by analyzing large data to identify patterns and extract clinical features that aid in the early detection and classification of FLLs. This manuscript reviews the diagnostic capacity of AI-based algorithms in processing CT and MRIs to detect benign and malignant FLLs, with an emphasis in the characterization and classification of these lesions and focusing on differentiating benign from pre-malignant and potentially malignant lesions. A comprehensive literature search from January 2010 to April 2024 identified 45 relevant studies. The majority of AI systems employed convolutional neural networks (CNNs), with expert radiologists providing reference standards through manual lesion delineation, and histology as the gold standard. The studies reviewed indicate that AI-based algorithms demonstrate high accuracy, sensitivity, specificity, and AUCs in detecting and characterizing FLLs. These algorithms excel in differentiating between benign and malignant lesions, optimizing diagnostic protocols, and reducing the needs of invasive procedures. Future research should concentrate on the expansion of data sets, the improvement of model explainability, and the validation of AI tools across a range of clinical setting to ensure the applicability and reliability of such tools., (© 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Objectives: Serous cystic neoplasm (SCN) is a cystic neoplasm of the pancreas whose natural history is poorly known. The purpose of the study was to attempt to describe the natural history of SCN, including the specific mortality., Design: Retrospective multinational study including SCN diagnosed between 1990 and 2014., Results: 2622 patients were included. Seventy-four per cent were women, and median age at diagnosis was 58 years (16-99). Patients presented with non-specific abdominal pain (27%), pancreaticobiliary symptoms (9%), diabetes mellitus (5%), other symptoms (4%) and/or were asymptomatic (61%). Fifty-two per cent of patients were operated on during the first year after diagnosis (median size: 40 mm (2-200)), 9% had resection beyond 1 year of follow-up (3 years (1-20), size at diagnosis: 25 mm (4-140)) and 39% had no surgery (3.6 years (1-23), 25.5 mm (1-200)). Surgical indications were (not exclusive) uncertain diagnosis (60%), symptoms (23%), size increase (12%), large size (6%) and adjacent organ compression (5%). In patients followed beyond 1 year (n=1271), size increased in 37% (growth rate: 4 mm/year), was stable in 57% and decreased in 6%. Three serous cystadenocarcinomas were recorded. Postoperative mortality was 0.6% (n=10), and SCN's related mortality was 0.1% (n=1)., Conclusions: After a 3-year follow-up, clinical relevant symptoms occurred in a very small proportion of patients and size slowly increased in less than half. Surgical treatment should be proposed only for diagnosis remaining uncertain after complete workup, significant and related symptoms or exceptionally when exists concern with malignancy. This study supports an initial conservative management in the majority of patients with SCN., Trial Registration Number: IRB 00006477., (Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/)