Our Vision

Applying Deep Learning technology to bring Healthcare to the "Forgotten Billion"

Artelus stands as a vanguard in the realm of healthcare technology, gaining recognition for its avant-garde contributions to AI-empowered diagnostic screening solutions, drawing heavily on the transformative power of Vision Transformers (ViTs). Through the utilization of cutting-edge self-supervised learning methodologies, Artelus has seamlessly integrated techniques such as DINO (DIstillation of knowledge with NO labels) — a paradigm that focuses on training vision models without any labeled data, by harnessing the power of teacher-student architectures where the student learns from a more powerful teacher network. Furthermore, BYOL (Bootstrap Your Own Latent) is another cornerstone, emphasizing the importance of learning representations by contrasting positive and negative samples without the need for negative sample pairs, enhancing the learning robustness and efficiency. In their quest to build more holistic and inclusive AI models, Artelus has also pioneered the use of Generative Adversarial Networks (GANs). Specifically, in diagnostic simulations, GANs are harnessed to generate synthetic medical images, aiding in the augmentation of datasets and ensuring that the AI models are trained on a diverse range of scenarios, bolstering their accuracy and generalizability.