“…Convolutional neural networks have helped to significantly increase the accuracy of computer vision classification tasks in the last few years [30, 31, 32, 33, 34, 35]. These methods has also been used to identify multiple types of cancer, predict progression of tumor, and classify various types of skin diseases [36, 37, 38, 39, 40, 41]. Because of this, the effective use of CNNs for image classification depends on the availability of a substantial quantity of image data and high-quality annotation, which may be difficult to achieve because of the cost associated in collecting labels by medical specialists [42, 43, 44, 45].…”