This month, News in Review highlights selected papers from the original papers sessions at AAO 2021. Each was chosen by the session chairs because it presents important news or illustrates a trend in the field. Only four subspecialties are included here; papers sessions also will be held in five other fields. For up-to-date information, check the Mobile Meeting Guide (aao.org/mobile).
With a smartphone, a slit lamp, and artificial intelligence (AI)–generated software, researchers have developed a tool for assessing corneal endothelium (CE) function. The novel system promises to enable mobile field screening for endothelial health, which would be particularly useful in low-resource regions.
Potential. The smartphone-based system was developed to be portable, reliable, not dependent on internet connection, and fast. In a preliminary study published earlier this year, a $500 smartphone, coupled with a slit lamp, performed comparably to a $30,000 specular microscope.1
The system “will empower general ophthalmologists to identify and detect CE changes at a very affordable price, making it accessible to many more patients,” said Madhu Uddaraju, MBBS, MS, at the Srikiran Institute of Ophthalmology in Andhra Pradesh, India.
Testing. The system was tested on 30 eyes (15 patients) without ocular disease who underwent a routine eye exam at the Srikiran Institute, a referral eye hospital, in January 2020.
Image capture and AI. First, researchers captured images of the central cornea of both eyes using the Tomey EM-4000 specular microscope. Next, using the specular reflection technique, they imaged the same set of eyes with a OnePlus 7 Pro smartphone that was attached to a Topcon SL-D701 slit-lamp ocular. A technician performed all imaging.
An AI-based algorithm was used to analyze the images for three clinically relevant parameters of endothelial health: endothelial cell density (ECD), percentage of hexagonal cells (HEX), and coefficient of variation (CV). The analysis can be run in under five seconds on a mobile phone without internet connection, with total capture and analysis taking two to four minutes for both eyes, similar to the speed of specular microscopy.
Outcomes. The findings revealed no significant difference in mean ECD or mean HEX computed by either the specular microscope or the smartphone: Mean ECD was 2,799 ± 156 cells/mm2 when computed by the microscope, versus 2,799 ± 166 cells/ mm2 when computed by the smartphone. Similarly, mean HEX was 52 ± 6% when computed by microscope and 53 ± 6% when computed by smartphone.
There was, however, a difference in CV as computed by the two devices, with a mean difference of 3.8%.
Next steps. The researchers are now comparing the device with conventional specular microscopes in patients with Fuchs dystrophy. Also, for more robust results, they are gradually increasing the number of study patients, which may help explain the CV disparity, Dr. Uddaraju said. “Once we have larger study results and make the system simpler and more user friendly, we will make it available to our colleagues.”
Low-Cost, Smartphone-Based Specular Imaging and Automated Analysis of the Corneal Endothelium. Presented during the cornea original papers session. When: Sunday, Nov. 14, at 8:24 a.m. Where: Room 255-257.
1 Mantena S et al. Transl Vis Sci Technol. 2021;10(4):4.
Relevant financial disclosures—Dr. Uddaraju: None.
For full disclosures and the disclosure key, see below.
Full Financial Disclosures
Dr. Chang AcuFocus: S; Allergan: C,L,S; Carl Zeiss Meditec: C,L,S; Johnson & Johnson Vision: C,L,S; Omega Ophthalmics: C,O.
Dr. Gedde None.
Dr. Uddaraju None.
Dr. Wieland Roche: C.
||Consultant fee, paid advisory boards, or fees for attending a meeting.
||Employed by a commercial company.
||Lecture fees or honoraria, travel fees or reimbursements when speaking at the invitation of a commercial company.
||Equity ownership/stock options in publicly or privately traded firms, excluding mutual funds.
||Patents and/or royalties for intellectual property.
||Grant support or other financial support to the investigator from all sources, including research support from government agencies (e.g., NIH), foundations, device manufacturers, and/or pharmaceutical companies.
More from this month’s News in Review