A New Deep Learning Algorithm with Activation Mapping for Diabetic Retinopathy: Backtesting after 10 Years of Tele-Ophthalmology.

We report the development of a deep learning algorithm (AI) to detect signs of diabetic retinopathy (DR) from fundus images. For this, we use a ResNet-50 neural network with a double resolution, the addition of Squeeze-Excitation blocks, pre-trained in ImageNet, and trained for 50 epochs using the Adam optimizer. The AI-based algorithm not only classifies an image as pathological or not but also detects and highlights those signs that allow DR to be identified. For development, we have used a database of about half a million images classified in a real clinical environment by family doctors (FDs), ophthalmologists, or both. The AI was able to detect more than 95% of cases worse than mild DR and had 70% fewer misclassifications of healthy cases than FDs. In addition, the AI was able to detect DR signs in 1258 patients before they were detected by FDs, representing 7.9% of the total number of DR patients detected by the FDs. These results suggest that AI is at least comparable to the evaluation of FDs. We suggest that it may be useful to use signaling tools such as an aid to diagnosis rather than an AI as a stand-alone tool.

The optics of the human eye at 8.6 µm resolution.

Ocular optics is normally estimated based on up to 2,600 measurement points within the pupil of the eye, which implies a lateral resolution of approximately 175 µm for a 9 mm pupil diameter. This is because information below this resolution is not thought to be relevant or even possible to obtain with current measurement systems. In this work, we characterize the in vivo ocular optics of the human eye with a lateral resolution of 8.6 µm, which implies roughly 1 million measurement points for a pupil diameter of 9 mm. The results suggest that the normal human eye presents a series of hitherto unknown optical patterns with amplitudes between 200 and 300 nm and is made up of a series of in-phase peaks and valleys. If the results are analysed at only high lateral frequencies, the human eye is also found to contain a whole range of new information. This discovery could have a great impact on the way we understand some fundamental mechanisms of human vision and could be of outstanding utility in certain fields of ophthalmology.