Related Experiment Video
Updated: Jan 28, 2026
An Ex Vivo Tissue Culture Model for Fibrovascular Complications in Proliferative Diabetic Retinopathy
Published on: January 25, 2019
Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative
Toshihiko Nagasawa1, Hitoshi Tabuchi2, Hiroki Masumoto2
1Department of Ophthalmology, Saneikai Tsukazaki Hospital, 68-1 Aboshi Waku, Himeji City, Hyogo Prefecture, 671-1227, Japan. t.nagasawa@tsukazaki-eye.net.
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.
Related Concept Videos
01:20Proliferative Phase
Notably, the stratum basale, the basal layer of the endometrium, including the basal parts of the uterine glands, remains unaffected by menstruation. Stem cells in this layer undergo mitosis, regenerating the stratum functionalis and thickening the...
02:07Improving Translational Accuracy
02:07Improving Translational Accuracy
03:37Uncertainty in Measurement: Accuracy and Precision
01:52Accuracy and Precision
01:20Pathophysiology of Diabetes
Type 1 diabetes is characterized by autoimmune-mediated destruction of pancreatic β cells, with environmental factors potentially triggering this process in genetically susceptible individuals. Despite many not having a family history, certain genes increase susceptibility,...