Approaches and Challenges for using Artificial Intelligence in Medical Imaging
Kevin Mader (4Quant and University Hospital Basel)
The diagnosis and treatment of cancer has been drastically improved by newer imaging methods like PET-CT which generate large number of images where single spots can drastically influence the diagnosis and treatment.
For physicians this means a long time must be spent carefully reading thousands images a day and looking at dozens of different regions carefully to check for the possibility of aggressive disease. 4Quant Ltd. together with the University Hospital Basel has demonstrated the potential to radically reduce the physicians reading time without sacrificing quality by using a Deep Learning approach. We present the work we have done towards computer aided staging of Non-Small Cell Lung Cancer (NSCLC) for a more efficient and evidence based precision medicine and illustrate challenges, hurdles and findings while developing an AI-based product for medical use.