Development of a machine learning computed algorithm to help the early detection of lung cancer

The main aim of our research project is to create the ground for the development of a platform of deep learning and artificial intelligence in thoracic imaging, specifically related to lung cancer screening. 

We want to feed a computer with all the clinical data and imaging features to improve nodule detection and characterisation. 
The main steps to achieve this goal are: i) you have to find all the nodules, determine their morphology, size and density  accurately; ii) this comes in combination with all the clinical parameters, including age, sex, environment [gas, minerals or chemicals exposure], history of previous cancers, family history of cancer and many other parameters); iii) then you can simplify the rules and know what to do next on the screening protocols. 

We want to do this ambitious project with a well-recognised University in Rome (Sapienza University in Rome is one of the top Universities in Europe and in particular the hospital linked to the University (Policlinico Umberto I/St. Andrea Hospital) is one of the largest in Europe with about 1800 beds).

Area

Medicine

UCL leads

• Dr Francesco Fraioli, UCL Institute of Nuclear Medicine