Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke

Background Accessible tools to efficiently detect and segment diffusion abnormalities in acute strokes are highly anticipated by the clinical and research communities. Methods We developed a tool with deep learning networks trained and tested on a large dataset of 2,348 clinical diffusion weighted MRIs of patients with acute and sub-acute ischemic strokes, and further tested for generalization on 280 MRIs of an external dataset (STIR). Results Our proposed model outperforms generic networks and DeepMedic, particularly in small lesions, with lower false positive rate, balanced precision and sensitivity, and robustness to data perturbs (e.g., artefacts, low resolution, technical heterogeneity). The agreement with human delineation rivals the inter-evaluator agreement; the automated lesion quantification of volume and contrast has virtually total agreement with human quantification. Conclusion Our tool is fast, public, accessible to non-experts, with minimal computational requirements, to detect and segment lesions via a single command line. Therefore, it fulfills the conditions to perform large scale, reliable and reproducible clinical and translational research.

Kuakini HHP Center for Translational Research on Aging: An Introduction

sKuakini Medical Center (Kuakini) is establishing an interdisciplinary Hawai’i-based Center of Biomedical Research Excellence (COBRE) for clinical and translational research on aging. - Specific Aim 1: Create a world class, innovative, interdisciplinary Center for Translational Research on Aging by building on the existing rare and valuable Kuakini Honolulu Heart Program (Kuakini HHP) and its related studies and research infrastructure. - Specific Aim 2: Advance the genomic, biological and clinical science of aging, and enhance the world class character of our Center, by enlisting accomplished senior scientists to mentor promising Hawaii-based new investigators in interdisciplinary aging research and career development. - Specific Aim 3: Elevate the capacity of our Center by: i) creating a state-of-the-art Clinical and Translational Core, and ii) collaborating with other Centers of Biomedical Research Excellence. This presentation will briefly introduce the Center and discuss its aims, research strategy, and future plans.

Sex differences in non-AIDS comorbidities among People with HIV

Women are grossly underrepresented in HIV clinical and translational research. This is concerning given that people with HIV (PWH) are living longer, and thus accumulating aging-related non-AIDS comorbidities (NACM), and emerging evidence suggests that women are at higher risk of NACM development and progression compared with men. It is widely recognized that women versus men have greater immune activation in response to many viruses, including HIV-1; this likely influences sex-differential NACM development related to differences in HIV-associated chronic inflammation. Furthermore, many sociobehavioral factors that contribute to aging-related NACM are known to differ by sex. The objectives of this review were to 1) synthesize sex-stratified data on four NACM among PWH: bone disease, cardiovascular disease, metabolic dysfunction, and neurocognitive impairment; 2) evaluate the characteristics of key studies assessing sex differences in NACM; 3) introduce potential biological and psychosocial mechanisms contributing to emerging trends in sex-differential NACM risk and outcomes among PWH.

Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke

Background: Accessible tools to efficiently detect and segment diffusion abnormalities in acute strokes are highly anticipated by the clinical and research communities. Methods: We developed a tool with deep learning networks trained and tested on a large dataset of 2,348 clinical diffusion weighted MRIs of patients with acute and sub-acute ischemic strokes, and further tested for generalization on 280 MRIs of an external dataset (STIR). Results: Our proposed model outperforms generic networks and DeepMedic, particularly in small lesions, with lower false positive rate, balanced precision and sensitivity, and robustness to data perturbs (e.g., artefacts, low resolution, technical heterogeneity). The agreement with human delineation rivals the inter-evaluator agreement; the automated lesion quantification of volume and contrast has virtually total agreement with human quantification. Conclusion: Our tool is fast, public, accessible to non-experts, with minimal computational requirements, to detect and segment lesions via a single command line. Therefore, it fulfills the conditions to perform large scale, reliable and reproducible clinical and translational research.

Large cell neuroendocrine lung carcinoma: consensus statement from The British Thoracic Oncology Group and the Association of Pulmonary Pathologists

Over the past 10 years, lung cancer clinical and translational research has been characterised by exponential progress, exemplified by the introduction of molecularly targeted therapies, immunotherapy and chemo-immunotherapy combinations to stage III and IV non-small cell lung cancer. Along with squamous and small cell lung cancers, large cell neuroendocrine carcinoma (LCNEC) now represents an area of unmet need, particularly hampered by the lack of an encompassing pathological definition that can facilitate real-world and clinical trial progress. The steps we have proposed in this article represent an iterative and rational path forward towards clinical breakthroughs that can be modelled on success in other lung cancer pathologies.