scikit-image is an image processing library that implements algorithms and utilities for use in research, education and industry applications. It is released under the liberal "Modified BSD" open source license, provides a well-documented API in the Python programming language, and is developed by an active, international team of collaborators. In this paper we highlight the advantages of open source to achieve the goals of the scikit-image library, and we showcase several real-world image processing applications that use scikit-image.

scikit-image is an image processing library that implements algorithms and utilities for use in research, education and industry applications. It is released under the liberal "Modified BSD" open source license, provides a well-documented API in the Python programming language, and is developed by an active, international team of collaborators. In this paper we highlight the advantages of open source to achieve the goals of the scikit-image library, and we showcase several real-world image processing applications that use scikit-image.

Introduction: The effects of coronary anatomy, lesion complexity, and comorbidities on outcomes of elective percutaneous coronary intervention (PCI) in high-risk patients with left main (LM) and/or multivessel coronary artery disease (CAD) are not well studied, as these patients are typically underrepresented in the clinical trials.Methods: This cohort study involved 33,568 consecutive elective PCI cases, excluding patients with prior coronary artery bypass graft, acute coronary syndrome within 24 hr of index PCI, or shock. All data were obtained from the New York State's PCI Reporting System from the calendar year 2015. In-hospital mortality was the primary outcome of study. Logistic regression models were built to calculate odds ratios (OR) with 95% confidence intervals (CI) for in-hospital mortality after adjustment for coronary anatomy and significant clinical comorbidities.Results: In this cohort of elective PCI cases all cause in-hospital mortality was low (0.3%), with a clear mortality gradient according to the extent of CAD: 0.1% in 1 vessel disease, 0.4% in 2 vessel, 0.5% in 3 vessel disease, and 3.2% in patients with LM CAD (p < .001). Mortality was also significantly increased in patients with multiple comorbidities: 0.1% in patients with 1 comorbidity, 0.7% with 2, 2.5% with 3, and 7.4% with 4 or more studied comorbidities (p < .0001). When adjusted for coronary anatomy and lesion complexity, having any 4 or more comorbidities was associated with significantly increased odds of dying after elective PCI (OR 25.9, 95% CI 8.152-82.063, p < .0001). Furthermore, when compared to patients with 3-vessel CAD, and accounted for comorbidities, the patients with LM disease still had significantly increased (OR 5.254, 95% CI 3.104-8.891, p < .0001) odds of dying after elective PCI. Conclusions:In patients undergoing elective PCI, multivessel CAD and particularly LM disease are associated with significantly increased all-cause mortality. Furthermore, when adjusted for the extent of CAD and lesion complexity, comorbidity burden remains an important predictor of mortality.

SUMMARYWe present a case of a 69-year-old woman presenting with polymorphic ventricular tachycardia caused by QT prolongation. Owing to known intolerances to a majority of antiarrhythmic medications, one remaining option was to initiate phenytoin. Phenytoin's narrow therapeutic window, multiple drug interactions and side effect profile make it an infrequently used antiarrhythmic. It is, however, a potent antiarrhythmic agent, which may be useful in treatment of ventricular tachycardia, especially in patients with multiple drug intolerances. BACKGROUND

Background: Acute kidney injury (AKI) complicating cardiogenic shock is associated with increased mortality. We hypothesize that renal replacement therapy (RRT) improves survival in cardiogenic shock supported by Impella-CP (Abiomed, Danvers, MA) complicated by AKI. Methods: A retrospective chart review identified 34 patients on Impella-CP for cardiogenic shock between January 2015 and December 2017. AKI was defined as an increase in serum creatinine≥0.3 mg/dL from baseline. Three groups were analyzed: AKI plus RRT, AKI minus RRT, and no AKI. Pre-existing dialysis patients were excluded. The only indication for RRT was AKI not responding to diuretics. Thirty-day mortality was analyzed. Results: There were 13 patients with no AKI, 9 with AKI plus RRT groups, and 12 with AKI minus RRT. Thirty-day mortality was similar between no AKI and AKI plus RRT groups [30.8% (4/13) vs.22.2% (2/9), p=0.48; relative risk [RR] 2.25 (95% confidence interval [CI] 0.22-22.1)]. Thirty-day mortality was higher in AKI minus RRT group compared to the no AKI group [75.0% (9/12) vs. 30.8% (4/13); p=0.03; RR 6.75 (95% CI 1.16-39.2)]. Conclusion: In cardiogenic shock patients on Impella-CP, AKI minus RRT is associated with a higher 30-day mortality compared to patients without AKI and/or patients with AKI plus RRT. Short-term mortality may improve in cardiogenic shock patients with AKI who are treated with RRT.