Skip to main content Skip to page footer

Medicine: choosing the best AI model

An application developed by Politecnico di Milano to select the best AI model in medicine

Publish date

Politecnico di Milano has developed the first online application capable of selecting the most appropriate artificial intelligence model to generate 3D images of a specific organ or lesion, improving the accuracy of diagnoses and treatments.

The project, carried out by a team from the Department of Electronics, Information and Bioengineering (DEIB) led by Professor Andrea Moglia, originates from a study published in the journal Information Fusion and represents a significant step forward in the use of artificial intelligence in the medical field.

The tool is designed for healthcare professionals, technicians, and physicians working in anatomical imaging. Through a free online interface, users can select organs or anatomical regions, such as the chest, neck, or abdomen, and consult a list of the most effective AI models for reconstructing their three-dimensional images.

With this tool, selecting the right models to produce images used for diagnosis and surgery becomes much more efficient. (…) Professionals no longer need to rely on trial and error to obtain more accurate images.

Andrea Moglia, Professor of the Department of Electronics, Information and Bioengineering

The research team also includes Luca Mainardi and Matteo Leccardi from DEIB, and Pietro Cerveri from EssilorLuxottica Smart Eyewear Lab, affiliated with Politecnico di Milano. The project was partially funded under the PNRR by the Future Artificial Intelligence Research (FAIR) foundation.

Ready the study

The online application