Recent publications by SoVS staff include:
1.Detection of smoking status from retinal images; a Convolutional Neural Network study
Scientific Reports 2019 May 9;9(1):7180
Ehsan Vaghefi, Song Yang, Sophie Hill, Gayl Humphrey, Natalie Walker, David Squirrell
We trained a customized convolutional neural network (CNN) to accurately determine smoking status. The retinal vasculature, the perivascular region and the fovea appear to be important predictive features in the determination of smoking status. Despite a high degree of accuracy, the sensitivity of our CNN was low. Further research is required to establish whether the frequency, duration, and dosage (quantity) of smoking would improve the sensitivity of the CNN.
Click here to read the paper.
2. Foveal eccentricity can influence activation threshold in subretinal electrical stimulation.
Biomedical Physics & Engineering Express. 2019 Feb 28.
Farzaneh Shalbaf, Nigel H Lovell, Socrates Dokos, Mark Trew, Ehsan Vaghef
Retinal prosthetic devices have been introduced as a potential therapy for patients suffering from outer retinal diseases. Human subjects with retinal implants demonstrated a varying range of responses to these devices. In this study, we introduce an anatomically-based patient-specific model of the human retina, using it to explore the effect of foveal eccentricity on activation threshold.
Click here to read the paper.