They used a method to learn from multimodal data, including images and text descriptions. This approach provides a deeper understanding of the causes of systemic findings.
The model automatically highlights key elements during the training process, allowing you to avoid manual marking of training examples. The team used more than 18.6 thousand x-ray images of organs, as well as text descriptions and medical reports.
The study, carried out in collaboration with scientists from the University of Copenhagen and the University of Edinburgh, aims to improve the interpretability of artificial intelligence decisions in the medical field. Experimental results confirmed that the new approach increases the robustness of deep learning models.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
