Skychain AI for retinal diseases recognition

Greetings, Skychain community! We have launched the sixth ANN in Skychain Alpha available for public testing — it’s the AI for retinal diseases recognition.

The ANN for retinal diseases detection uses retinal optical coherence tomography (OCT) images to recognize a disease.

OCT is an imaging technique used to capture high-resolution cross sections of the retinas of living patients.

Data

Skychain used the. The images it contains were selected from retrospective cohorts of adult patients from the Shiley Eye Institute of the University of California San Diego, the California Retinal Research Foundation, Medical Center Ophthalmology Associates, the Shanghai First People’s Hospital, and Beijing Tongren Eye Center between July 1, 2013 and March 1, 2017.

There are 84,484 retinal OCT images classified in 4 categories:

  1. NORMAL — images of normal retinas;
  2. CNV — images of choroidal neovascularization;

Choroidal neovascularization involves the growth of new blood vessels that originate from the choroid through a break in the Bruch membrane into the sub–retinal pigment epithelium or subretinal space. .

3. DME — images of diabetic macular edema;

is an accumulation of fluid in the macula — part of the retina that controls our most detailed vision abilities — due to leaking blood vessels. It is one the most prevalent causes of visual loss in industrialized countries.

4. DRUSEN — images of optic disc drusen.

Optic disc drusen are globules of and that progressively calcify in the optic disc. They may be associated with vision loss of varying degree occasionally resulting in blindness.

Image for post
Image for post

Model of the ANN

A modified version of the VGG16 convolutional neural network was used as the deep learning model for classification. We replaced the final fully-connected layer with one that has four outputs. We also tried others models as DenseNet169, ResNet, Inception-v3, ShuffleNet but no one of them was good as VGG16. The weighted cross entropy was used as the loss function.

Results

After training the deep learning model, we achieved an accuracy of 96,88% on training dataset and an accuracy of 99,9% on validation dataset. After constructing an ROC curve, the area under the ROC curve (AUROC) was 99%.

Image for post
Image for post
Achieved accuracy on train and validation datasets
Image for post
Image for post
The area under the ROC curve (AUROC)

Below there are some examples of the ANN predictions using retinal OCT images. It creates heat maps to highlight questionable areas.

Image for post
Image for post
The result of deep learning model predictions. Left — prediction of Drusen, center — CNV, right — DME.

Test this neural network and the others in .

Skychain Global official website: .

Join Skychain Global on social media: , , , , .

Skychain Official Channel

Written by

Blockchain infrastructure aimed to host, train and use artificial intelligence (AI) in healthcare. Our website: https://skychain.global/

Skychain Official Channel

Written by

Blockchain infrastructure aimed to host, train and use artificial intelligence (AI) in healthcare. Our website: https://skychain.global/

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch

Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore

Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store