Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features

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%.     

Transarterial Chemoembolization vs Radioembolization for Neuroendocrine Liver Metastases: A Multi-Institutional Analysis

1. Download : Download high-res image (207KB)
2. Download : Download full-size image

     

Outcomes of coronary artery bypass grafting in patients with heart failure with a midrange ejection fraction

BackgroundCoronary artery bypass grafting (CABG) improves survival in patients with heart failure and severely reduced left ventricular systolic function (LVEF). Limited data exist regarding adverse cardiovascular event rates after CABG in patients with heart failure with midrange ejection fraction (HFmrEF; LVEF > 40% and < 55%).MethodsWe analyzed data on isolated CABG patients from the Veterans Affairs national database (2010-2019). We stratified patients into control (normal LVEF and no heart failure), HFmrEF, and heart failure with reduced LVEF (HFrEF) groups. We compared all-cause mortality and heart failure hospitalization rates between groups with a Cox model and recurrent events analysis, respectively.ResultsIn 6533 veterans, HFmrEF and HFrEF was present in 1715 (26.3%) and 566 (8.6%) respectively; the control group had 4252 (65.1%) patients. HFrEF patients were more likely to have diabetes mellitus (59%), insulin therapy (36%), and previous myocardial infarction (31%). Anemia was more prevalent in patients with HFrEF (49%) as was a lower serum albumin (mean, 3.6 mg/dL). Compared with the control group, a higher risk of death was observed in the HFmrEF (hazard ratio [HR], 1.3 [1.2-1.5)] and HFrEF (HR, 1.5 [1.2-1.7]) groups. HFmrEF patients had the higher risk of myocardial infarction (subdistribution HR, 1.2 [1-1.6]; P = .04). Risk of heart failure hospitalization was higher in patients with HFmrEF (HR, 4.1 [3.5-4.7]) and patients with HFrEF (HR, 7.2 [6.2-8.5]).ConclusionsHeart failure with midrange ejection fraction negatively affects survival after CABG. These patients also experience higher rates myocardial infarction and heart failure hospitalization.     

In Vitro-In Vivo Extrapolation and Hepatic Clearance-Dependent Underprediction

Accurately predicting the hepatic clearance of compounds using in vitro to in vivo extrapolation (IVIVE) is crucial within the pharmaceutical industry. However, several groups have recently highlighted the serious error in the process. Although empirical or regression-based scaling factors may be used to mitigate the common underprediction, they provide unsatisfying solutions because the reasoning behind the underlying error has yet to be determined. One previously noted trend was intrinsic clearance-dependent underprediction, highlighting the limitations of current in vitro systems. When applying these generated in vitro intrinsic clearance values during drug development and making first-in-human dose predictions for new chemical entities though, hepatic clearance is the parameter that must be estimated using a model of hepatic disposition, such as the well-stirred model. Here, we examine error across hepatic clearance ranges and find a similar hepatic clearance-dependent trend, with high clearance compounds not predicted to be so, demonstrating another gap in the field.     

Risk communication in a patient decision aid for radiotherapy in breast cancer: How to deal with uncertainty?

Background and aimPatient decision aids for oncological treatment options, provide information on the effect on recurrence rates and/or survival benefit, and on side-effects and/or burden of different treatment options. However, often uncertainty exists around the probability estimates for recurrence/survival and side-effects which is too relevant to be ignored. Evidence is lacking on the best way to communicate these uncertainties. The aim of this study is to develop a method to incorporate uncertainties in a patient decision aid for breast cancer patients to support their decision on radiotherapy.MethodsFirstly, qualitative interviews were held with patients and health care professionals. Secondly, in the development phase, thinking aloud sessions were organized with four patients and 12 health care professionals, individual and group-wise.ResultsConsensus was reached on a pictograph illustrating the whole range of uncertainty for local recurrence risks, in combination with textual explanation that a more exact personalized risk would be given by their own physician. The pictograph consisted of 100 female icons in a 10 x 10 array. Icons with a stepwise gradient color indicated the uncertainty margin. The prevalence and severity of possible side-effects were explained using verbal labels.ConclusionsWe developed a novel way of visualizing uncertainties in recurrence rates in a patient decision aid. The effect of this way of communicating risk uncertainty is currently being tested in the BRASA study (NCT03375801).