The researchers used state-of-the-art machine vision and computational linguistics models, including the popular GPT-3.5 and the GPT-4 predecessor, the GPT-3 small.
Unlike traditional models, Skoltech’s neural network automatically identifies x-rays, allowing doctors to confirm or reject diagnoses such as fibrosis, heart enlargement or suspected cancer.
To train the neural network, a large database of x-ray images and a special radiological dictionary were created to improve accuracy in the use of radiological terms.
The system can also reportedly be adapted to work with MRI and CT images and use active learning, allowing the model to be refined based on adjustments made by clinicians.
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.
