Deep learning for risk-based stratification of cognitively impaired individuals.

Quantifying the risk of progression to Alzheimer's disease (AD) could help identify persons who could benefit from early interventions. We used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI, n = 544, discovery cohort) and the National Alzheimer's Coordinating Center (NACC, n = 508, validation cohort), subdividing individuals with mild cognitive impairment (MCI) into risk groups based on cerebrospinal fluid amyloid-β levels and identifying differential gray matter patterns. We then created models that fused neural networks with survival analysis, trained using non-parcellated T1-weighted brain MRIs from ADNI data, to predict the trajectories of MCI to AD conversion within the NACC cohort (integrated Brier score: 0.

Multimodal deep learning for Alzheimer's disease dementia assessment.

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD).

Stromal cell-derived factor-1alpha activation of tissue-engineered endothelial progenitor cell matrix enhances ventricular function after myocardial infarction by inducing neovasculogenesis.

Background: Myocardial ischemia causes cardiomyocyte death, adverse ventricular remodeling, and ventricular dysfunction. Endothelial progenitor cells (EPCs) have been shown to ameliorate this process, particularly when activated with stromal cell-derived factor-1α (SDF), known to be the most potent EPC chemokine. We hypothesized that implantation of a tissue-engineered extracellular matrix (ECM) scaffold seeded with EPCs primed with SDF could induce borderzone neovasculogenesis, prevent adverse geometric remodeling, and preserve ventricular function after myocardial infarction.

Transmyocardial revascularization to enhance myocardial vasculogenesis and hemodynamic function.

Objective: A significant number of patients have coronary artery disease that is not amenable to traditional revascularization. Prospective, randomized clinical trials have demonstrated therapeutic benefits with transmyocardial laser revascularization in this cohort. The molecular mechanisms underlying this therapy, however, are poorly understood.

Minimally invasive resection of papillary fibroelastoma in a high-risk patient.

Papillary fibroelastomas are rare, benign cardiac tumors that typically mandate surgical resection. These are usually approached through a median sternotomy with cardioplegic arrest and aortic cross-clamping. We describe the minimally invasive resection of a right atrial fibroelastoma performed on a beating heart via right mini-thoracotomy in a patient complicated by a previous laryngectomy, radiation therapy, and a left-sided pulmonary malignancy.