Publications by authors named "H Menegay"
Purpose: To determine endothelial cell density (ECD) from real-world donor cornea endothelial cell (EC) images using a self-supervised deep learning segmentation model.
Methods: Two eye banks (Eversight, VisionGift) provided 15,138 single, unique EC images from 8169 donors along with their demographics, tissue characteristics, and ECD. This dataset was utilized for self-supervised training and deep learning inference.
Purpose: To create Guided Correction Software for informed manual editing of automatically generated corneal endothelial cell (EC) segmentations and apply it to an active learning paradigm to analyze a diverse set of post-keratoplasty EC images.
Approach: An original U-Net model trained on 130 manually labeled post-Descemet stripping automated endothelial keratoplasty (EK) images was applied to 841 post-Descemet membrane EK images generating "uncorrected" cell border segmentations. Segmentations were then manually edited using the Guided Correction Software to create corrected labels.
Objectives: Identify the incidence, rate of physician recognition, diagnostic practices and cancer outcomes for unintentional weight loss (UWL).
Methods: We completed a secondary analysis of structured and unstructured EHR data collected from adult patients between January 1, 2020 and December 31, 2021. We used four common definitions to define UWL, excluding patients with known causes of weight loss, intentional weight loss, and pregnancy.
Purpose: This study developed machine learning (ML) classifiers of postoperative corneal endothelial cell images to identify postkeratoplasty patients at risk for allograft rejection within 1 to 24 months of treatment.
Methods: Central corneal endothelium specular microscopic images were obtained from 44 patients after Descemet membrane endothelial keratoplasty (DMEK), half of whom had experienced graft rejection. After deep learning segmentation of images from all patients' last and second-to-last imaging, time points prior to rejection were analyzed (175 and 168, respectively), and 432 quantitative features were extracted assessing cellular spatial arrangements and cell intensity values.
Purpose: A disconnect often exists between those with the expertise to manage and analyze complex, multi-source data sets, and the clinical, social services, advocacy, and public health professionals who can pose the most relevant questions and best apply the answers. We describe development and implementation of a cancer informatics infrastructure aimed at broadening the usability of community cancer data to inform cancer control research and practice; and we share lessons learned.
Methods: We built a multi-level database known as The Ohio Cancer Assessment and Surveillance Engine (OH-CASE) to link data from Ohio's cancer registry with community data from the U.