Detecting Cataract Using Smartphones

Abstract

Objective: Cataract, which is the clouding of the crystalline lens, is the most prevalent eye disease accounting for 51% of all eye diseases in the U.S. Cataract is a progressive disease, and its early detection is critical for preventing blindness. In this paper, an efficient approach to identify cataract disease by adopting luminance features using a smartphone is proposed. Methods: Initially, eye images captured by a smartphone were cropped to extract the lens, and the images were preprocessed to remove irrelevant background and noise by utilizing median filter and watershed transformation. Then, a novel luminance transformation from pixel brightness algorithm was introduced to extract lens image features. The luminance and texture features of different types of cataract disease images could be obtained accurately in this stage. Finally, by adopting support vector machines (SVM) as the classification method, cataract eyes were identified. Results: From all the images that we fed into our system, our method could diagnose diseased eyes with 96.6% accuracy, 93.4% specificity, and 93.75% sensitivity. Conclusion: The proposed method provides an affordable, rapid, easy-to-use, and versatile method for detecting cataracts by using smartphones without the use of bulky and expensive imaging devices. This method can be used for bedside telemedicine applications or in remote areas that have medical shortages. Previous smartphone-based cataract detection methods include texture feature analysis with 95 % accuracy, Gray Level Co-occurrence Matrix (GLCM) method with 89% accuracy, red reflex measurement method, and RGB color feature extraction method using cascade classifier with 90% accuracy. The accuracy of cataract detection in these studies is subject to changes in smartphone models and/or environmental conditions. However, our novel luminance-based method copes with different smartphone camera sensors and chroma variations, while operating independently from sensors' color characteristics and changes in distances and camera angle. Clinical and TranslationalImpact-This study is an early/pre-clinical research proposing a novel luminance-based method of detecting cataract using smartphones for remote/at-home monitoring and telemedicine application.

Indigenous Eye Health in the Americas: The Burden of Vision Impairment and Ocular Diseases

“…More than achieving universal health coverage in a country, equity should be prioritized, otherwise, socially advantaged groups will be more likely to use the new or improved services [71,72]. Specific actions include the following: (1) access: increasing the number of clinic sites, rural locations, and eye care sessions, not only with ophthalmologists, but also with other eye health practitioners as optometrists, ophthalmic technologists, and/or trained nurses should improve the number of patient seen, dispensing spectacles, and surgery referrals [72,73]; (2) integration with family medicine/primary care: several communities have general health programs with systemic condition screening and could include ocular health screening tools into their practice to detect and timely refer cases of vision impairment and blindness for specialized care [19,72,74]; (3) telemedicine: several telemedicine protocols in ophthalmology focused on diabetes retinopathy, glaucoma, and cataract have been shown to be effective in populations living in remote areas and should be used as models towards Indigenous population groups [75][76][77]; (4) customized propaedeutics: specific techniques should be indicated to populations living in remote areas, for example, manual small incision cataract surgery (MSICS) techniques in resource-constrained health care settings such as Indigenous communities [78]; (5) education on eye health: by promoting basic knowledge on eye health, the population can better understand the importance of seeking timely treatment, improving visual outcomes [79,80]; (6) quality data: more studies focused on Indigenous population's eye health should be performed with appropriate methodology and collection of key indicators such as eCSC and eREC, and studies performed in the general population should collect data on the participants' ethnicity/race [52,53].…”

Artificial intelligence in cataract: What’s new?

“…Askarian et al [11] proposed a novel smartphone-based cataract detection system. This AI application uses the phone camera to capture photographs of the eye and then crops out the lens.…”

“…[5] In addition, a prevalence of 0.32-22.9/10,000 children has been noted for paediatric cataracts. [6] In recent times, the use of AI has been described in cataract detection, [7][8][9][10][11][12][13][14][15] cataract grading, [5] intraocular lens (IOL)-related calculations [16][17][18][19][20][21][22][23], and even as an aid in cataract surgery. [24][25][26][27] The developing countries, where healthcare distribution is not equitable, can greatly benefit from such wide-ranging applications of AI.…”

Clinical validation of artificial intelligence-based cataract screening solution with smartphone images (Logy AI cataract screening module)

“…Some researchers have tried to build a solution that uses luminance-based eye image analysis to detect cataracts based on images captured from a smartphone. 13 Similarly, Logy AI has developed an artificial intelligence (AI) based model to detect cataracts using images captured by a smartphone camera. It uses free-hand images captured with the flashlight using a smartphone and internally runs deep learning algorithms on the captured images.…”