Search

Introduction: The study explains the presence versus complete absence of the foveal contour on optical coherence tomography (OCT) image as predictor of improvement in visual acuity (VA) following epiretinal membrane removal surgery. Methods: We conducted a retrospective observational study in which 100 eyes that underwent vitrectomy for epiretinal membrane, with preoperative and postoperative VA and OCT, were analyzed. The study population was categorized into four groups based on the preoperational presence of a foveal contour and an intraocular lens implantation. Results: The most significant improvement in VA was found among eyes lacking a foveal contour. Pseudo-phakic eyes demonstrated greater improvement than phakic. The smallest improvement was documented in pseudo-phakic eyes with a foveal contour. Phakic eyes that had a foveal contour showed deterioration in VA. Among eyes that lacked foveal contour, the fraction of eyes with improved VA was only slightly larger than among pseudo-phakic eyes during midterm follow-up and no difference was observed at long-term follow-up. Among eyes with foveal contour, the fraction with improved VA was significantly larger among pseudo-phakic eyes. This difference became more prominent over long-term follow-up. Regardless of the presence of foveal contour, the fraction of patients whose VA worsened was greater among those with phakic versus pseudo-phakic eyes, and this difference increased during long-term follow-up. No correlation was found between the central macular thickness and the VA. Conclusion: Complete lack of foveal contour is positively correlated with greater improvement in postoperative VA. The presence of an intraocular lens contributes to improvement in VA, especially among patients with foveal contour. [ABSTRACT FROM AUTHOR]

Objectives: In the midst of the coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in diagnosis and monitoring of patients with COVID-19. We propose a deep learning model for detection of COVID-19 from CXRs, as well as a tool for retrieving similar patients according to the model's results on their CXRs. For training and evaluating our model, we collected CXRs from inpatients hospitalized in four different hospitals. Methods: In this retrospective study, 1384 frontal CXRs, of COVID-19 confirmed patients imaged between March and August 2020, and 1024 matching CXRs of non-COVID patients imaged before the pandemic, were collected and used to build a deep learning classifier for detecting patients positive for COVID-19. The classifier consists of an ensemble of pre-trained deep neural networks (DNNS), specifically, ReNet34, ReNet50¸ ReNet152, and vgg16, and is enhanced by data augmentation and lung segmentation. We further implemented a nearest-neighbors algorithm that uses DNN-based image embeddings to retrieve the images most similar to a given image. Results: Our model achieved accuracy of 90.3%, (95% CI: 86.3–93.7%) specificity of 90% (95% CI: 84.3–94%), and sensitivity of 90.5% (95% CI: 85–94%) on a test dataset comprising 15% (350/2326) of the original images. The AUC of the ROC curve is 0.96 (95% CI: 0.93–0.97). Conclusion: We provide deep learning models, trained and evaluated on CXRs that can assist medical efforts and reduce medical staff workload in handling COVID-19. Key Points: • A machine learning model was able to detect chest X-ray (CXR) images of patients tested positive for COVID-19 with accuracy and detection rate above 90%. • A tool was created for finding existing CXR images with imaging characteristics most similar to a given CXR, according to the model's image embeddings. [ABSTRACT FROM AUTHOR]