Computer aided detection and diagnosis

The idea of using computers to analyze medical images is nothing new and has been around since the late sixties, first proposed by Gwylym Lodwick in 1966. Mammography (X-ray images of the breast) was the first modality to which it was actually applied. R2, a tool that shows markers for regions in the image that look suspicious to the AI behind it obtained FDA approval in 1998. With the breakthrough in deep learning in 2012, the medical field and also mammography has received a lot of attention again. Geoffrey Hinton - the godfather of AI - even went so far to say radiologists will be completely replaced 5 to 10 years from now. He said that in 2016, so ought to make haste. Even though several studies show human performance, these are just prototypes.

Autonomous AI will have a far bigger impact on healthcare than small incremental improvement upon physicians from the use of AI as a detection aid. To get to completely autonomous AI, we need to work on systems that do not only get the same performance as humans on small in-house datasets, but are proven to work in the wild. About 100 to 200 million mammograms are recorded on a yearly basis. If all of these are read by a computer, small mistakes will accumulate. Systems therefore need to be tested in large scale prospective studies, just like new drugs are tested, before they are deployed autonomously. Something current systems are notoriously bad at is classifying data that is out of the distribution of the training set. This means the systems may miss massive and dangerous tumors that have never been seen during training. Similar performance does not mean similar behavior.

Reaching autonomous AI for the detection of all diseases that humans now detect in medical scans will mean surmounting machine learning. medical, engineering, regulatory and even philosophical challenges and will keep us busy for at least a decade or two. Beyond that lies a whole new set of challenges, as completely replacing radiologists, ophthalmologists and any physician involved in image interpretation is close to solving artificial intelligence. Combining imaging modalities, images with lab work, anamnesis and genomic profiles of patients will likely keep us busy for decades to come.