In this editorial, writing for the American Academy of Ophthalmology, Dr. Aaron Lee and his co-authors explain the urgent need for ophthalmic imaging device manufacturers to standardize their imaging formats to comply with existing international standards. Currently, manufacturers of devices such as optical coherence tomography machines use their own proprietary imaging formats, requiring special software to access and analyze the images obtained with their device. This common practice makes it difficult for clinicians and researchers to compare images from different machines. Standardization would allow interoperability between imaging systems, allowing electronic health information to be transferred more easily when a patient is seen at different hospitals or clinics. It would also allow researchers to build comprehensive imaged datasets for and big data analyses and machine learning studies, a growing area of research in ophthalmology that is currently limited by lack of image standardization.
The Digital Imaging and Communications in Medicine (DICOM) standard is recognized worldwide and already includes agreed-upon ophthalmologic definitions. Manufacturers have been reluctant to adopt standardization, likely due to fear of losing competitive advantage. Dr. Lee argues that manufacturers themselves would benefit from adopting these standards, because doing so would reduce excess costs that would have been spent on defining product specifications and service requirements. In addition, although recent legislation, the 21st Century Cures Act, included provisions that encourage greater interoperability of electronic health records, it did not address medical imaging in Picture Archiving and Communications Systems (PACS) outside of electronic health record systems. However, as Dr. Lee explains, the Academy believes that raw images together with the accompanying metadata should be included under these provisions, and that the native format of the PACS should support standardized DICOM format.
DICOM has been adopted widely in the field of radiology, among others, and has revolutionized radiology research by enabling big data studies and the creation of large training data sets for machine learning. Dr. Lee and his colleagues at the American Academy of Ophthalmology would like for ophthalmology research to follow that same path in the near future, which will only be possible if ophthalmic device manufacturers agree to follow their recommendation to implement existing DICOM standards. Once they do so, Dr. Lee concludes, "then the field of ophthalmology can rapidly progress along the path of efficient electronic workflow, interoperability, and artificial intelligence systems that will meet an increased demand for ophthalmic services to the public.
Lee AY, Campbell JP, Hwang TS, Lum F, Chew EY. Recommendations for Standardization of Images in Ophthalmology. Ophthalmology. 2021 April 5; S0161-6420(21)00164-0. PMID: 33832778. doi: 10.1016/j.ophtha.2021.03.003.