Biomedical hyperspectral imaging (HSI) is a powerful tool for disease diagnosis and medical research, offering rich spectral information for precise tissue characterization. However, the secure transmission and storage of these sensitive images, along with associated patient data, pose significant challenges. This research introduces a novel deep learning-based steganographic method to embed confidential patient data within hyperspectral medical images, ensuring both security and data integrity. Unlike conventional least significant bit (LSB) methods, which are prone to distortion and detection, we employ a GAN-based approach to generate imperceptible and high-capacity steganographic images. To further enhance security, patient data is first encrypted using XChaCha with Argon2 key derivation before embedding, ensuring that access is restricted to authorized users. This research advances privacy-preserving techniques in medical imaging, enabling secure and efficient patient data transmission while maintaining the diagnostic utility of hyperspectral medical images.