Abstract--The need for medical image encryption is increasingly pronounced, for example to safeguard the privacy of the patients' medical imaging data. In this paper, a novel deep learningbased key generation network (DeepKeyGen) is proposed as a stream cipher generator to generate the private key, which can then be used for encrypting and decrypting of medical images. In DeepKeyGen, the generative adversarial network (GAN) is adopted as the learning network to generate the private key. Furthermore, the transformation domain (that represents the "style" of the private key to be generated) is designed to guide the learning network to realize the private key generation process. The goal of DeepKeyGen is to learn the mapping relationship of how to transfer the initial image to the private key. We evaluate DeepKeyGen using three datasets, namely: the Montgomery County chest X-ray dataset, the Ultrasonic Brachial Plexus dataset, and the BraTS18 dataset. An example application scenario of proposed DeepKeyGen. Compared to block ciphers (e.g., Data Encryption Standard Advanced Encryption Standard (AES)), stream ciphers generally have a high-level security, are faster in terms of encryption I. S medical imaging becomes increasingly commonplace, so does the use of medical images to inform diagnosing [1]-[3]. One challenge, however, is how to design a security and treatment plans, etc. For example, images from brain stream cipher generator to facilitate the process of generating magnetic resonance imaging (MRI) and computed tomography the randomized and unpredictable sequence. Common stream (CT) of chest can be used to facilitate brain tumor detection cipher generators include linear feedback shift register [4], for lung diagnosis.