Abdomenatlas contains more than 45,000 IT Slides from 145 hospitals worldwide and includes additional explanations to 142 anatomical structures. On a scale, it exceeds all similar databases existing more than 36 times.
Previously, marking medical images required a great time: a specialist manually marked 45,000 photographs with 6 million anatomical structures in an expert. However, the researchers applied a technique that analyzes the pictures, foresees additional explanations and conveys the most complex fields for radioologists.
This approach has made it possible to accelerate the marking process 500 times and the detection of tumors 10 times. As a result, it has been possible to create the most accurate and detailed database used to teach new AI models that can identify malignant formations and diagnose diseases in early stages.
In addition, abdominalized will become a reference data set to assess the accuracy of medical segmentation algorithms. Researchers plan to make accessible to other scientific groups and medical institutions to accelerate the development of technology in the field of health.
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.
