This bachelor thesis aims to enhance the quality, alignment, and interpretability of Optical Coherence Tomography (OCT) images, a vital tool in diagnosing eye diseases such as glaucoma and macular degeneration. Despite OCT’s high-resolution capabilities, challenges like image misalignment and data gaps reduce its effectiveness in clinical settings. This research develops advanced preprocessing, alignment, and interpolation techniques, supported by machine learning, to improve OCT image accuracy and reliability. Beyond technical advancements, this study underscores the clinical impact, equipping ophthalmologists with more precise diagnostic tools and facilitating long-term patient monitoring. Additionally, these methodologies have potential applications in other medical imaging fields, encouraging interdisciplinary innovation.