Neural Transformers for Intraductal Papillary Mucosal Neoplasms (IPMN) Classification in MRI images.

Early detection of precancerous cysts or neoplasms, i.e., Intraductal Papillary Mucosal Neoplasms (IPMN), in pancreas is a challenging and complex task, and it may lead to a more favourable outcome. Once detected, grading IPMNs accurately is also necessary, since low-risk IPMNs can be under surveillance program, while high-risk IPMNs have to be surgically resected before they turn into cancer. Current standards (Fukuoka and others) for IPMN classification show significant intra- and inter-operator variability, beside being error-prone, making a proper diagnosis unreliable. The established progress in artificial intelligence, through the deep learning paradigm, may provide a key tool for an effective support to medical decision for pancreatic cancer. In this work, we follow this trend, by proposing a novel AI-based IPMN classifier that leverages the recent success of transformer networks in generalizing across a wide variety of tasks, including vision ones. We specifically show that our transformer-based model exploits pre-training better than standard convolutional neural networks, thus supporting the sought architectural universalism of transformers in vision, including the medical image domain and it allows for a better interpretation of the obtained results.

Systematic review and meta-analysis on the prevalence of vitamin D deficiency in patients with chronic pancreatitis.

BACKGROUND/OBJECTIVES: Patients with chronic pancreatitis (CP) are at risk of malnutrition due to malabsorption, pain and/or alcohol consumption. This can cause vitamin D insufficiency or deficiency, which is associated with osteoporosis and increased risks of fractures. We aimed to perform a meta-analysis to determine the prevalence of vitamin D insufficiency and deficiency in CP patients. Furthermore, we compared these results with healthy controls. METHODS: We performed a systematic review and meta-analysis on the literature by searching PubMed and EMBASE (January 2000-December 2015) on CP and vitamin D. Primary outcome was prevalence of vitamin D insufficiency (<75 nmoL/L) and deficiency (<50 nmoL/L) in CP patients. When available, data of CP patients were compared with healthy controls. RESULTS: Nine studies were included in our meta-analysis, reporting on the prevalence of vitamin D insufficiency/deficiency in 465 patients (mean age 41 years (range 18-60), 81% male) and in 378 controls (mean age 40 years (range 18-67), 76% male). Pooled prevalence of vitamin D insufficiency and deficiency in CP patients was 83% and 65%, respectively. Calculated odds ratio (OR) of vitamin D insufficiency and deficiency between CP patients and controls was 1.34 (0.54-3.29) and 1.14 (0.70-1.85), respectively (p > 0.05). CONCLUSION: There is a high prevalence of vitamin D insufficiency and deficiency in CP patients. Nevertheless, there is no significant difference in prevalence of vitamin D insufficiency and deficiency compared to healthy controls. Further research should indicate the clinical relevance and consequences of these findings for clinical practice.