Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
3
result(s) for
"Williamson, M. H. (Mark Herbert)"
Sort by:
Factors affecting visual recovery after successful repair of macula-off retinal detachments: findings from a large prospective UK cohort study
ObjectiveTo identify risk factors affecting visual outcomes in successfully re-attached macula-off rhegmatogenous retinal detachment (RD) surgery.DesignA prospective study, using online databases, of visual outcomes for 2074 macula-off retinal detachments that were successfully re-attached by vitrectomy and internal tamponade. The database included detailed retinal diagrams of each detachment.Main outcome measureThe probability of achieving a post-operative visual acuity (VA) of ≤0.30 LogMAR (Snellen 6/12 or better).ResultsMale patients accounted for 64.9% of the sample and the median age was 63 years old. The median pre-operative VA was counting fingers (LogMAR 1.98); this improved to 0.41 LogMAR post-operatively. A post-operative VA of ≤0.30 LogMAR was achieved for 1012 (48.8%) eyes and the factors affecting this were the patient age and gender, pre-operative VA, duration of central vision loss, PVR grade, lens status, total RD and the presence of any ocular co-pathology where the model area under the receiver operator curve was 71.6%.ConclusionsFrom the identified risk factors that decrease the probability of achieving a post-operative visual acuity of ≤0.30 LogMAR, the most important modifiable risk factor was the duration of central vision loss. Recent macula-off retinal detachments should be repaired within 72 h of the loss of central vision.
Journal Article
Artificial intelligence using deep learning to predict the anatomical outcome of rhegmatogenous retinal detachment surgery: a pilot study
Purpose To develop and evaluate an automated deep learning model to predict the anatomical outcome of rhegmatogenous retinal detachment (RRD) surgery.MethodsSix thousand six hundred and sixty-one digital images of RRD treated by vitrectomy and internal tamponade were collected from the British and Eire Association of Vitreoretinal Surgeons database. Each image was classified as a primary surgical success or a primary surgical failure. The synthetic minority over-sampling technique was used to address class imbalance. We adopted the state-of-the-art deep convolutional neural network architecture Inception v3 to train, validate, and test deep learning models to predict the anatomical outcome of RRD surgery. The area under the curve (AUC), sensitivity, and specificity for predicting the outcome of RRD surgery was calculated for the best predictive deep learning model.ResultsThe deep learning model was able to predict the anatomical outcome of RRD surgery with an AUC of 0.94, with a corresponding sensitivity of 73.3% and a specificity of 96%.ConclusionA deep learning model is capable of accurately predicting the anatomical outcome of RRD surgery. This fully automated model has potential application in surgical care of patients with RRD.
Journal Article