The large amount of data required to train a deep learning algorithm poses a significant challenge. Bigger datasets result in adequate training of the model's parameters and further improve generalizability. Ideally, these training datasets are composed of numerous, manually annotated real data samples. However, these datasets are costly and, therefore, scarce. Although a few large datasets exist, training deep learning models using small datasets is still possible through 3 strategies. The first technique exploits B-scans adjacent to the training image within a volume. These neighboring B-scans can be used as additional examples in the training dataset because of their similar, but slightly different, anatomical structures. Similarly in computed tomography (CT) scanning, Ben-Cohen et al.
29 used unlabeled liver CT scan slices adjacent to the labeled training image as additional images. Second, transfer learning and/or fine-tuning where a network is pretrained on a larger unrelated dataset such as ImageNet can be used to start closer to a local minimum because the lower-level filters are already “learned.” Finally, applying data augmentations to individual scans can expand and diversify datasets without the need to acquire new images. Common transformations, including flipping, shearing, rotation, and outward/inward scaling, are generalizable because they are representative of the true variance captured in OCT imaging. Lee et al.
25 used a 432 × 32 window to OCT images and varied its position throughout the scan to significantly increase their training dataset size. Morley et al.
30 performed rotation and a unique myopic warping transformation to increase the RETOUCH dataset size by 45 times the original amount. Kuwayama et al.
31 improved their training dataset from 1,100 B-scans to 59,400 through horizontal flipping, rotation, and translation, producing an algorithm that correctly classified rare diseases such as Vogt-Koyanagi-Harada disease. Similarly, Kihara et al.
32 applied data augmentation (transformation, rotation, horizontal reflection) to increase their training dataset from 67,899 OCT B-scans to 103,053. Gao et al.
33 used a mirroring operation for data augmentation. Devalla et al.
13 compared the performance of a deep learning model with and without data augmentation (rotation, horizontal flipping, shifting, additive white noise, multiplicative speckle noise, elastic deformation, and occluding patches). Superior performance was reported in the model trained using both real and synthetic OCT data compared with the model trained using only real images. These results were attributed to less overfitting and improved generalizability because of additional synthetic training inputs. Although data augmentation can generate large and diverse training datasets, it is important to emphasize that numerous real data in the form of validated datasets are superior to synthetic images.
34 In addition to these techniques, newer methods have recently demonstrated potential in expanding datasets.