RESUMO
BACKGROUND & AIMS: Obesity is a risk factor for pancreatic ductal adenocarcinoma (PDAC), a deadly disease with limited preventive strategies. Lifestyle interventions to decrease obesity might prevent obesity-associated PDAC. Here, we examined whether decreasing obesity by increased physical activity (PA) and/or dietary changes would decrease inflammation in humans and prevent PDAC in mice. METHODS: Circulating inflammatory-associated cytokines of overweight and obese subjects before and after a PA intervention were compared. PDAC pre-clinical models were exposed to PA and/or dietary interventions after obesity-associated cancer initiation. Body composition, tumor progression, growth, fibrosis, inflammation, and transcriptomic changes in the adipose tissue were evaluated. RESULTS: PA decreased the levels of systemic inflammatory cytokines in overweight and obese subjects. PDAC mice on a diet-induced obesity (DIO) and PA intervention, had delayed weight gain, decreased systemic inflammation, lower grade pancreatic intraepithelial neoplasia lesions, reduced PDAC incidence, and increased anti-inflammatory signals in the adipose tissue compared to controls. PA had additional cancer prevention benefits when combined with a non-obesogenic diet after DIO. However, weight loss through PA alone or combined with a dietary intervention did not prevent tumor growth in an orthotopic PDAC model. Adipose-specific targeting of interleukin (IL)-15, an anti-inflammatory cytokine induced by PA in the adipose tissue, slowed PDAC growth. CONCLUSIONS: PA alone or combined with diet-induced weight loss delayed the progression of PDAC and reduced systemic and adipose inflammatory signals. Therefore, obesity management via dietary interventions and/or PA, or modulating weight loss related pathways could prevent obesity-associated PDAC in high-risk obese individuals.
RESUMO
BACKGROUND AND AIMS: EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) can differentiate high-grade dysplasia/adenocarcinoma (HGD-Ca) in intraductal papillary mucinous neoplasms (IPMNs) but requires manual interpretation. We sought to derive predictive computer-aided diagnosis (CAD) and artificial intelligence (AI) algorithms to facilitate accurate diagnosis and risk stratification of IPMNs. METHODS: A post hoc analysis of a single-center prospective study evaluating EUS-nCLE (2015-2019; INDEX study) was conducted using 15,027 video frames from 35 consecutive patients with histopathologically proven IPMNs (18 with HGD-Ca). We designed 2 CAD-convolutional neural network (CNN) algorithms: (1) a guided segmentation-based model (SBM), where the CNN-AI system was trained to detect and measure papillary epithelial thickness and darkness (indicative of cellular and nuclear stratification), and (2) a reasonably agnostic holistic-based model (HBM) where the CNN-AI system automatically extracted nCLE features for risk stratification. For the detection of HGD-Ca in IPMNs, the diagnostic performance of the CNN-CAD algorithms was compared with that of the American Gastroenterological Association (AGA) and revised Fukuoka guidelines. RESULTS: Compared with the guidelines, both n-CLE-guided CNN-CAD algorithms yielded higher sensitivity (HBM, 83.3%; SBM, 83.3%; AGA, 55.6%; Fukuoka, 55.6%) and accuracy (SBM, 82.9%; HBM, 85.7%; AGA, 68.6%; Fukuoka, 74.3%) for diagnosing HGD-Ca, with comparable specificity (SBM, 82.4%; HBM, 88.2%; AGA, 82.4%; Fukuoka, 94.1%). Both CNN-CAD algorithms, the guided (SBM) and agnostic (HBM) models, were comparable in risk stratifying IPMNs. CONCLUSION: EUS-nCLE-based CNN-CAD algorithms can accurately risk stratify IPMNs. Future multicenter validation studies and AI model improvements could enhance the accuracy and fully automatize the process for real-time interpretation.
