Predicting conversion to wet age-related macular degeneration using deep learning
| العنوان: | Predicting conversion to wet age-related macular degeneration using deep learning |
|---|---|
| المؤلفون: | Reena Chopra, Jim Winkens, Geraint Rees, Jason Yim, Gabriella Moraes, Trevor Back, Annette Obika, Clemens Meyer, Pearse A. Keane, Marc Wilson, Jeffrey De Fauw, Jonathan Mark Dixon, Marko Lukic, Harry Askham, Katrin Fasler, Joseph R. Ledsam, Terry Spitz, Mustafa Suleyman, Josef Huemer, Cian Hughes, Christopher Kelly, Alan Karthikesalingam, Dominic King, Peng T. Khaw, Demis Hassabis |
| المساهمون: | University of Zurich, Ledsam, Joseph R, Keane, Pearse A, De Fauw, Jeffrey |
| المصدر: | Nature Medicine. 26:892-899 |
| بيانات النشر: | Springer Science and Business Media LLC, 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Male, 10018 Ophthalmology Clinic, 0301 basic medicine, medicine.medical_specialty, 610 Medicine & health, General Biochemistry, Genetics and Molecular Biology, Macular Degeneration, 03 medical and health sciences, Deep Learning, Imaging, Three-Dimensional, 0302 clinical medicine, Optical coherence tomography, 1300 General Biochemistry, Genetics and Molecular Biology, Time windows, Early Medical Intervention, Geographic Atrophy, Ophthalmology, Wet age-related macular degeneration, medicine, False positive paradox, Humans, In patient, Aged, Aged, 80 and over, medicine.diagnostic_test, business.industry, Deep learning, Disease progression, General Medicine, Macular degeneration, Prognosis, medicine.disease, Early Diagnosis, 030104 developmental biology, 030220 oncology & carcinogenesis, Disease Progression, Wet Macular Degeneration, Female, Artificial intelligence, business, Tomography, Optical Coherence |
| الوصف: | Progression to exudative 'wet' age-related macular degeneration (exAMD) is a major cause of visual deterioration. In patients diagnosed with exAMD in one eye, we introduce an artificial intelligence (AI) system to predict progression to exAMD in the second eye. By combining models based on three-dimensional (3D) optical coherence tomography images and corresponding automatic tissue maps, our system predicts conversion to exAMD within a clinically actionable 6-month time window, achieving a per-volumetric-scan sensitivity of 80% at 55% specificity, and 34% sensitivity at 90% specificity. This level of performance corresponds to true positives in 78% and 41% of individual eyes, and false positives in 56% and 17% of individual eyes at the high sensitivity and high specificity points, respectively. Moreover, we show that automatic tissue segmentation can identify anatomical changes before conversion and high-risk subgroups. This AI system overcomes substantial interobserver variability in expert predictions, performing better than five out of six experts, and demonstrates the potential of using AI to predict disease progression. |
| وصف الملف: | Yim_Nat_Med_2020.pdf - application/pdf |
| تدمد: | 1546-170X 1078-8956 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbc51f346429a271c52d2de98ba8f2c8Test https://doi.org/10.1038/s41591-020-0867-7Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....cbc51f346429a271c52d2de98ba8f2c8 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 1546170X 10788956 |
|---|