Computer vision (CV) in medicine, propelled by deep learning and robust data resources, has revolutionized the healthcare landscape. AI models, primarily built on convolutional neural networks (CNNs), have advanced various diagnostic and prognostic tasks in healthcare. These breakthroughs owe their success to the convergence of deep learning, increased GPU-driven compute power, and abundant labeled datasets. In the field of computer vision, progress has been profound, particularly in object classification, localization, and detection, with the ImageNet competition playing a pivotal role. These strides extend to medicine, where AI models tackle tasks from disease classification to medical scene interpretation. They have the potential to rival or surpass expert physician accuracy, especially when trained on sizable medical datasets. Overcoming the challenge of limited medical data involves leveraging techniques like transfer learning and synthetic data generation and tapping into open sourced image annotations to build robust medical algorithms. However, the availability of medical data remains a pivotal concern, invoking ethical and legal queries about data ownership and re-identification risks. In such cases, federated learning emerges as a solution, allowing centralized algorithms to train on distributed data securely. Moreover, computer vision’s growth in medicine has influenced other domains like multimodal learning, 3D visions, and video analysis, proving invaluable in clinical settings. The technology has made significant strides in medical imaging, particularly in radiology, with AI models obtaining regulatory approvals and shaping clinical practices. This transformation extends to cardiology, pathology, dermatology, ophthalmology, and even medical videos, impacting diagnostic accuracy and patient care. However, the responsible deployment of these technologies in clinical settings necessitates addressing data access, ethical concerns, and community involvement, emphasizing data quality, model transparency, and clinical trials. It’s a promising revolution, yet one that requires careful navigation to ensure equity and trust in healthcare.