Abstract: We disclose the generation and training of Generative Adversarial Networks (GAN) to synthesize clinical images with skin conditions. Synthetic images for a pre-specified skin condition are generated, while being able to vary its size, location and the underlying skin color. We demonstrate that the generated images are of high fidelity using objective GAN evaluation metrics. The synthetic images are not only visually similar to real images, but also embody the respective skin conditions. Additionally, synthetic skin images can be used as a data augmentation technique for training a skin condition classifier, and improve the ability of the classifier to detect rare but malignant conditions.

Abstract: Some embodiments of the current disclosure disclose methods and systems for batch active learning using the Shapley values of data points. In some embodiments, Shapley values of a first subset of labeled data are used to measure the contributions of the first subset of data to the performance of neural network. Further, a regression model that correlates the first subset of data to their Shapley values is trained to predict the Shapley values of a second subset of data that are unlabeled. A portion of the second subset of data may then be selected for labeling based on the predicted Shapley values.

Abstract: Some embodiments of the current disclosure disclose methods and systems for batch active learning using the Shapley values of data points. In some embodiments, Shapley values of a first subset of labeled data are used to measure the contributions of the first subset of data to the performance of neural network. Further, a regression model that correlates the first subset of data to their Shapley values is trained to predict the Shapley values of a second subset of data that are unlabeled. A portion of the second subset of data may then be selected for labeling based on the predicted Shapley values.