Publications by authors named "V Sivaraman"
Background: This study aims to assess the effectiveness of low-dose Escitalopram (10 mg) or low-dose Desvenlafaxine (25 mg) combined with mindfulness-based cognitive therapy (MBCT) in addressing challenges in treating generalized anxiety disorder (GAD), particularly in patients resistant to conventional therapies.
Methods: A prospective cohort study was conducted with individuals diagnosed with treatment-resistant GAD. group A included patients unresponsive to citalopram, imipramine, paroxetine, and sertraline, who were then treated with low-dose Escitalopram (10 mg) combined with MBCT.
Retinal image registration is essential for monitoring eye diseases and planning treatments, yet it remains challenging due to large deformations, minimal overlap, and varying image quality. To address these challenges, we propose RetinaRegNet, a multi-stage image registration model with zero-shot generalizability across multiple retinal imaging modalities. RetinaRegNet begins by extracting image features using a pretrained latent diffusion model.
View Article and Find Full Text PDFObjective: We aimed to study the disease course, outcomes, and predictors of outcome in pediatric-onset antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) affecting the kidneys.
Methods: Patients eligible for this study had a diagnosis of granulomatosis with polyangiitis (GPA), microscopic polyangiitis, or ANCA-positive pauci-immune glomerulonephritis, were 18 years or younger at diagnosis, had renal disease defined by biopsy or dialysis dependence, and had clinical data at diagnosis and at either 12 or 24 months. Ambispective data from A Registry for Children with Vasculitis/Pediatric Vasculitis Initiative Registry was used.
Article Synopsis
- Advances in medical imaging and endovascular techniques enable less invasive treatments for aortic diseases, but accurate 3D segmentation of the aorta is vital for effective surgical planning.
- The paper presents Context-Infused Swin-UNet (CIS-UNet), a deep learning model that enhances multi-class segmentation by effectively distinguishing the aorta and its thirteen branches through a new Context-aware Shifted Window Self-Attention (CSW-SA) module.
- CIS-UNet outperformed existing models in segmentation accuracy, achieving a mean Dice coefficient of 0.732 in evaluations using CT scans from 59 patients, and the researchers will share their dataset and code publicly.
Article Synopsis
- Adolescents and young adults with chronic rheumatic diseases often struggle during the transition to adult care, impacting their health and wellbeing.
- Quality improvement (QI) and clinical informatics (CI) techniques can enhance the implementation of effective transition programs in pediatric rheumatology.
- A study demonstrated that automating patient surveys significantly improved transition readiness assessment from 12% to over 90%, allowing for better identification of patients' educational needs and establishing sustainable transition practices.