PurposeThe purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsEighty-nine patients with AIP (65 men, 24 women; mean age, 59.7 ± 13.9 [SD] years; range: 21–83 years) and 93 patients with PDAC (68 men, 25 women; mean age, 60.1 ± 12.3 [SD] years; range: 36–86 years) were retrospectively included. All patients had dedicated dual-phase pancreatic protocol CT between 2004 and 2018. Thin-slice images (0.75/0.5 mm thickness/increment) were compared with thick-slices images (3 or 5 mm thickness/increment). Pancreatic regions involved by PDAC or AIP (areas of enlargement, altered enhancement, effacement of pancreatic duct) as well as uninvolved parenchyma were segmented as three-dimensional volumes. Four hundred and thirty-one radiomics features were extracted and a random forest was used to distinguish AIP from PDAC. CT data of 60 AIP and 60 PDAC patients were used for training and those of 29 AIP and 33 PDAC independent patients were used for testing.ResultsThe pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52 (52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8–100%), 83.9% (52:67; 95% CI: 74.7–93.0%) and 77.4% (48/62; 95% CI: 67.0–87.8%) of the 62 test patients were correctly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6–100%) and 100% specificity (33/33; 95% CI: 93–100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8–100%) and area under the curve of 0.975 (95% CI: 0.936–1.0).ConclusionsRadiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%. 相似文献
Objective: Longitudinal data on cardiometabolic effects of egg intake during adolescence are lacking. The current analyses aim to evaluate the impact of usual adolescent egg consumption on lipid levels, fasting glucose, and insulin resistance during late adolescence (age 17–20?years).
Methods: Data from 1392 girls, aged 9 to 10 at baseline and followed for 10?years, in the National Heart, Lung, and Blood Institute’s National Growth and Health Study were used to examine the association between usual egg intake alone and in combination with other healthy lifestyle factors and late adolescent lipid levels, fasting glucose, and insulin resistance, measured as homeostasis model assessment of insulin resistance (HOMA-IR). Diet was assessed using 3-day food records during eight examination cycles. Girls were classified according to usual weekly egg intake, ages 9–17?years:?<1 egg/wk (n?=?361), 1 to <3 eggs/wk (n?=?703), and ≥3 eggs/wk (n?=?328). Analysis of covariance modeling was used to control for confounding by other behavioral and biological risk factors.
Results: Girls with low, moderate, and high egg intakes had adjusted low-density lipoprotein cholesterol levels of 99.7, 98.8, and 95.5 mg/dL, respectively (p?=?0.0778). In combination with higher intakes of fiber, dairy, or fruits and vegetables, these beneficial effects were stronger and statistically significant. There was no evidence that ≥3 eggs/wk had an adverse effect on lipids, glucose, or HOMA-IR. More active girls who consumed ≥3 eggs/wk had the lowest levels of insulin resistance.
Conclusion: These results suggest that eggs may be included as part of a healthy adolescent diet without adverse effects on glucose, lipid levels, or insulin resistance. 相似文献
The aim of this study was to analyse the effect of body mass index (BMI), both low and high values, on the perioperative complication rate in patients with oral squamous cell carcinoma (OSCC). The medical records of 259 patients operated between 2014 and 2017 for OSCC were reviewed. Univariate and multivariate analyses were performed. Sixty of the 259 patients developed 87 complications. Low or high BMI was not associated with the perioperative complication rate. A longer operating time and increased blood loss were associated with a higher perioperative complication rate and higher Clavien–Dindo grade. Low BMI, American Society of Anesthesiologists score 2 and 3, a longer operating time, and increased blood loss were associated with a longer hospital stay. Low BMI was associated with a longer hospital stay. Neither low nor high BMI was associated with the perioperative complication rate. A longer operating time and increased blood loss were associated with a higher perioperative complication rate and higher Clavien–Dindo grade. 相似文献