DLCExpert TM

DLCExpert is Mirada’s first clinical application to utilize our next generation deep learning technology.



What is Deep Learning Contouring (DLC)?

Deep learning is a recent advancement in machine learning and artificial intelligence, extending artificial neural networks to multiple layers. These neural networks learn to mimic human behavior by iteratively improving their performance on hundreds of training examples.

Deep Learning Contouring (DLC) is an autocontouring system that has been developed using deep learning technology. DLCExpert is our breakthrough autocontouring product that uniquely takes advantage of this recent technology.


How good is Mirada’s DLC?

Our validation results show that Mirada’s DLC delivers expert acceptance of OAR contours at a similar level as clinically drawn contours. These results show a substantial improvement over previous “state of the art” autocontouring technologies. We have made these validation results available through a series of white papers.

At www.autocontouring.com you are invited to take the Mirada Turing Test and attempt to identify for yourself which contours are drawn by radiation oncology professionals and which have been automatically drawn by Mirada software.

MAASTRO Clinic’s own assessment1 shows improved time savings compared to both manual and atlas-based contouring.

1 T.Lustberg et. al. Clinical evaluation of atlas and deep learning based automatic contouring for lung cancer, Radiotherapy & Oncology 2018 (in print)

Pictured: Alan Turing

Which anatomical sites are supported?

DLCExpert supports all major anatomical sites including breast, lung, head and neck and prostate.





For more information please see our

Deep Learning Contouring FAQ and

Technical White Paper