“CAD systems for colorectal cancer from WSI are still not ready for clinical acceptance” is the the first (of many!!) scientific studies about deep learning methods applied to colorectal cancer diagnosis, conducted by our team IMP Diagnostics, in collaboration with INESC Technology and Science – Associate Laboratory, is now out in Scientific Reports, a Nature Publishing Group journal.
It´s a review article on artificial intelligence for colorectal cancer diagnosis that underscores the need for large datasets and the use of an appropriate learning methodology to gain the most benefit from partially annotated datasets. Dataset with +1000 WSI.
Access here to Papper.