With the help of related FAs, the OCT strips are created from OCT B-scans in four labels including MA, normal, non-normal, and vessel. In our dataset, MA, normal, non-normal, and vessel classes comprise 72, 110, 91, and 108 strips of OCT images, respectively. The OCT strips have a width of approximately 32 pixels, whereas their height may vary between 160-190 pixels. The images are cropped in a way that they contain only retinal layers while the other pixels are withdrawn. That is why the images have various heights.
Please reference the following paper if you would like to use any part of this dataset or method:
Almasi, R., Vafaei, A., Kazemi nasab, E., & Rabbani, H.. Automatic detection of Microaneurysms in Optical Coherence Tomography images of retina using deep convolutional neural networks and transfer learning