Purpose: Image classification may be the fundamental task in imaging artificial intelligence. We have recently shown that reinforcement learning can achieve high accuracy for lesion localization and segmentation even with minuscule training sets. Here, we introduce reinforcement learning for image classification. In particular, we apply the approach to normal vs. tumor-containing 2D MRI brain images. Materials and Methods: We applied multi-step image classification to allow for combined Deep Q learning and TD(0) Q learning. We trained on a set of 30 images (15 normal and 15 tumor-containing). We tested on a separate set of 30 images (15 normal and 15 tumor-containing). For comparison, we also trained and tested a supervised deep-learning classification network on the same set of training and testing images. Results: Whereas the supervised approach quickly overfit the training data and as expected performed poorly on the testing set (57% accuracy, just over random guessing), the reinforcement learning approach achieved an accuracy of 100%. Conclusion: We have shown a proof-of-principle application of reinforcement learning to the classification of brain tumors. We achieved perfect testing set accuracy with a training set of merely 30 images.

翻译：图像分类可能是成像人工智能中的基本任务。 我们最近已经表明, 强化学习即使用微小的训练, 也能在损害定位和分化方面达到很高的精确度。 在这里, 我们引入了强化学习来进行图像分类。 特别是, 我们应用了常规对肿瘤2D MRI脑图象的常规与肿瘤2D MRI脑图象的强化学习。 材料和方法: 我们应用了多步图像分类, 以便能够将深Q学习和TD(0)Q学习结合起来。 我们用一套30张图像( 15个正常和15个含有肿瘤的图像)来培训。 我们用一组30张图像(15个正常和15个含有肿瘤的图象)来进行测试。 为了比较, 我们还在一套培训和测试图像的同一组上培训和测试了一个受监督的深层次分类网络。 结果: 受监督的方法很快地超过了培训数据,而且预期测试集( 57%的精确度高于随机猜测 ) 强化学习方法达到了100%的精确度。 结论: 我们用一套仅仅30张图像来进行完美的测试。