Recently, many ophthalmologists have heard the keywords artificial intelligence, machine learning, deep learning, and automatization at every conference and keynote lecture and seen them in every ophthalmology journal.1 Many studies1 have evaluated the use of such algorithms on large retrospective data sets—primarily on color fundus photographs at first, then on optical coherence tomography (OCT) images as well. Most of these have been study data sets with standardized and well-structured imaging protocols and reading center image collections with a predefined protocol, and therefore of good quality. However, how functional will algorithms be in a busy clinical routine? Can we trust a computer to localize retinal fluid, and will we base our treatment decisions on automated volumetric measurements of retinal fluid in the future? Could the computer lead to wrong decisions if we fail to detect “erroneous” segmentations in a clinical setting?2
Identify all potential conflicts of interest that might be relevant to your comment.
Conflicts of interest comprise financial interests, activities, and relationships within the past 3 years including but not limited to employment, affiliation, grants or funding, consultancies, honoraria or payment, speaker's bureaus, stock ownership or options, expert testimony, royalties, donation of medical equipment, or patents planned, pending, or issued.
Err on the side of full disclosure.
If you have no conflicts of interest, check "No potential conflicts of interest" in the box below. The information will be posted with your response.
Not all submitted comments are published. Please see our commenting policy for details.
Gerendas BS, Bogunović H, Schmidt-Erfurth U. Deep Learning–Based Automated Optical Coherence Tomography Segmentation in Clinical Routine: Getting Closer. JAMA Ophthalmol. Published online July 08, 2021. doi:10.1001/jamaophthalmol.2021.2309
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: