Eyeworld

23 EW NEWS & OPINION January 2019 8. Gulshan V, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photo- graphs. JAMA. 2016;316:2402–2410. 9. Ting DSW, et al. Development and validation of a deep learning system for diabetic retinop- athy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017;318:2211–2223. Editors' note: Dr. Huang has finan- cial interests with Optovue (Fremont, California). Contact information David Huang: huangd@ohsu.edu optical coherence tomography angiography of retinal and choriocapillaris alterations in diabetic patients with and without retinopathy. Retina. 2017;37:11–21. 4. Huang D, et al. Optical coherence tomogra- phy angiography of time course of choroidal neovascularization in response to anti-angio- genic treatment. Retina. 2015;35:2260–4. 5. Pi S, et al. Angiographic and structural im- aging using high axial resolution fiber-based visible-light OCT. Biomed Opt Express. 2017;8:4595–4608. 6. Chen S, et al. Retinal oximetry in humans using visible-light optical coherence tomogra- phy. Biomed Opt Express. 2017;8:1415–1429. 7. Pi S, et al. Automated spectroscopic retinal oximetry with visible-light optical coherence tomography. Biomed Opt Express. 2018;9:2056–2067. Limitations include large datasets needed to train the algorithm and variation in image quality in the telemedicine setting. These advance- ments in diagnostics are moving us forward into a brighter future." EW References 1. Yarmohammadi A, et al. Relationship between optical coherence tomography angiography vessel density and severity of visual field loss in glaucoma. Ophthalmology. 2016;123:2498–2508. 2. Hwang TS, et al. Visualization of 3 distinct retinal plexuses by projection-resolved optical coherence tomography angiography in diabetic retinopathy. JAMA Ophthalmol. 2016;134:1411–1419. 3. Choi W, et al. Ultrahigh speed swept source images. 9 Further research is neces- sary to evaluate the feasibility of the algorithms in the clinical setting and whether the use of algorithms and deep learning lead to better care compared to current ophthalmolog- ic assessment. "Deep learning could have a wide impact on ophthalmology," Dr. Huang said. "It is based on fundus photographs or OCT images that could be acquired by technicians using widely available devices. Machine grading can be cheaper and more consistent than human graders. This is a rapidly improving technology that could make tele- medicine practical on a larger scale. Treatment-naïve non-exudative CNV with dense microvascular network in an 88-year-old female patient Source: David Huang, MD

• Blank Page
• Blank Page (1)