Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative diabetic retinopathy
| Autor: | Hiroki Masumoto, Toshihiko Nagasawa, Yuki Yoshizumi, Masanori Niki, Yoshinori Mitamura, Hitoshi Tabuchi, Zaigen Ohara, Hideharu Ohsugi, Hiroki Enno |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Adult
Male medicine.medical_specialty endocrine system diseases Fundus (eye) Convolutional neural network Sensitivity and Specificity Therapy naive Ophthalmoscopy 03 medical and health sciences 0302 clinical medicine Ophthalmology Medicine Humans Proliferative diabetic retinopathy Diagnosis Computer-Assisted Aged Diabetic Retinopathy medicine.diagnostic_test business.industry Deep learning Ultrawide-field fundus ophthalmoscopy Diabetic retinopathy Middle Aged medicine.disease eye diseases Area Under Curve 030221 ophthalmology & optometry Female Artificial intelligence sense organs Deep convolutional neural network business 030217 neurology & neurosurgery |
| Zdroj: | International Ophthalmology. 39(10):2153-2159 |
| ISSN: | 1573-2630 |
| Popis: | Purpose We investigated using ultrawide-field fundus images with a deep convolutional neural network (DCNN), which is a machine learning technology, to detect treatment-naïve proliferative diabetic retinopathy (PDR). Methods We conducted training with the DCNN using 378 photographic images (132 PDR and 246 non-PDR) and constructed a deep learning model. The area under the curve (AUC), sensitivity, and specificity were examined. Result The constructed deep learning model demonstrated a high sensitivity of 94.7% and a high specificity of 97.2%, with an AUC of 0.969. Conclusion Our findings suggested that PDR could be diagnosed using wide-angle camera images and deep learning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink