Shang Ruan1, Yang Liu1, Wei-Ting Hu2, Hui-Xun Jia1, Shan-Shan Wang1, Min-Lu Song1, Meng-Xi Shen1, Da-Wei Luo1, Tao Ye3, Feng-Hua Wang1,4. 1. Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University, School of Medicine, Shanghai 200080, China. 2. Shanghai Phoebus Medical Co. Ltd., Shanghai 200000, China. 3. West Nanjing Road Community Health Center, Shanghai 200000, China. 4. Shanghai Key Laboratory of Ocular Fundus Diseases; Shanghai Engineering Center for Visual Science and Photomedicine; National Clinical Research Center for Eye Diseases; Shanghai Engineering Center for Precise Diagnosis and Treatment of Eye Diseases, Shanghai 200025, China.
Abstract
AIM: To explore the performance in diabetic retinopathy (DR) screening of artificial intelligence (AI) system by evaluating the image quality of a handheld Optomed Aurora fundus camera in comparison to traditional tabletop fundus cameras and the diagnostic accuracy of DR of the two modalities. METHODS: Overall, 630 eyes were included from three centers and screened by a handheld camera (Aurora, Optomed, Oulu, Finland) and a table-top camera. Image quality was graded by three masked and experienced ophthalmologists. The diagnostic accuracy of the handheld camera and AI system was evaluated in assessing DR lesions and referable DR. RESULTS: Under nonmydriasis status, the handheld fundus camera had better image quality in centration, clarity, and visible range (1.47, 1.48, and 1.40) than conventional tabletop cameras (1.30, 1.28, and 1.18; P<0.001). Detection of retinal hemorrhage, hard exudation, and macular edema were comparable between the two modalities, in principle, with the area under the curve of the handheld fundus camera slightly lower. The sensitivity and specificity for the detection of referable DR with the handheld camera were 82.1% (95%CI: 72.1%-92.2%) and 97.4% (95%CI: 95.4%-99.5%), respectively. The performance of AI detection of DR using the Phoebus Algorithm was satisfactory; however, Phoebus showed a high sensitivity (88.2%, 95%CI: 79.4%-97.1%) and low specificity (40.7%, 95%CI: 34.1%-47.2%) when detecting referable DR. CONCLUSION: The handheld Aurora fundus camera combined with autonomous AI system is well-suited in DR screening without mydriasis because of its high sensitivity of DR detection as well as its image quality, but its specificity needs to be improved with better modeling of the data. Use of this new system is safe and effective in the detection of referable DR in real world practice. International Journal of Ophthalmology Press.
AIM: To explore the performance in diabetic retinopathy (DR) screening of artificial intelligence (AI) system by evaluating the image quality of a handheld Optomed Aurora fundus camera in comparison to traditional tabletop fundus cameras and the diagnostic accuracy of DR of the two modalities. METHODS: Overall, 630 eyes were included from three centers and screened by a handheld camera (Aurora, Optomed, Oulu, Finland) and a table-top camera. Image quality was graded by three masked and experienced ophthalmologists. The diagnostic accuracy of the handheld camera and AI system was evaluated in assessing DR lesions and referable DR. RESULTS: Under nonmydriasis status, the handheld fundus camera had better image quality in centration, clarity, and visible range (1.47, 1.48, and 1.40) than conventional tabletop cameras (1.30, 1.28, and 1.18; P<0.001). Detection of retinal hemorrhage, hard exudation, and macular edema were comparable between the two modalities, in principle, with the area under the curve of the handheld fundus camera slightly lower. The sensitivity and specificity for the detection of referable DR with the handheld camera were 82.1% (95%CI: 72.1%-92.2%) and 97.4% (95%CI: 95.4%-99.5%), respectively. The performance of AI detection of DR using the Phoebus Algorithm was satisfactory; however, Phoebus showed a high sensitivity (88.2%, 95%CI: 79.4%-97.1%) and low specificity (40.7%, 95%CI: 34.1%-47.2%) when detecting referable DR. CONCLUSION: The handheld Aurora fundus camera combined with autonomous AI system is well-suited in DR screening without mydriasis because of its high sensitivity of DR detection as well as its image quality, but its specificity needs to be improved with better modeling of the data. Use of this new system is safe and effective in the detection of referable DR in real world practice. International Journal of Ophthalmology Press.
Authors: Frank D Verbraak; Michael D Abramoff; Gonny C F Bausch; Caroline Klaver; Giel Nijpels; Reinier O Schlingemann; Amber A van der Heijden Journal: Diabetes Care Date: 2019-02-14 Impact factor: 19.112
Authors: Daniel Shu Wei Ting; Carol Yim-Lui Cheung; Gilbert Lim; Gavin Siew Wei Tan; Nguyen D Quang; Alfred Gan; Haslina Hamzah; Renata Garcia-Franco; Ian Yew San Yeo; Shu Yen Lee; Edmund Yick Mun Wong; Charumathi Sabanayagam; Mani Baskaran; Farah Ibrahim; Ngiap Chuan Tan; Eric A Finkelstein; Ecosse L Lamoureux; Ian Y Wong; Neil M Bressler; Sobha Sivaprasad; Rohit Varma; Jost B Jonas; Ming Guang He; Ching-Yu Cheng; Gemmy Chui Ming Cheung; Tin Aung; Wynne Hsu; Mong Li Lee; Tien Yin Wong Journal: JAMA Date: 2017-12-12 Impact factor: 56.272
Authors: Jose R Davila; Sabyasachi S Sengupta; Leslie M Niziol; Manavi D Sindal; Cagri G Besirli; Swati Upadhyaya; Maria A Woodward; Rengaraj Venkatesh; Alan L Robin; Joseph Grubbs; Paula Anne Newman-Casey Journal: Ophthalmologica Date: 2017-07-05 Impact factor: 3.250
Authors: Joanne W Y Yau; Sophie L Rogers; Ryo Kawasaki; Ecosse L Lamoureux; Jonathan W Kowalski; Toke Bek; Shih-Jen Chen; Jacqueline M Dekker; Astrid Fletcher; Jakob Grauslund; Steven Haffner; Richard F Hamman; M Kamran Ikram; Takamasa Kayama; Barbara E K Klein; Ronald Klein; Sannapaneni Krishnaiah; Korapat Mayurasakorn; Joseph P O'Hare; Trevor J Orchard; Massimo Porta; Mohan Rema; Monique S Roy; Tarun Sharma; Jonathan Shaw; Hugh Taylor; James M Tielsch; Rohit Varma; Jie Jin Wang; Ningli Wang; Sheila West; Liang Xu; Miho Yasuda; Xinzhi Zhang; Paul Mitchell; Tien Y Wong Journal: Diabetes Care Date: 2012-02-01 Impact factor: 19.112