AI in Healthcare May 10, 2021
Deep neural networks are capable of tying oncological findings from genetic testing with those from medical imaging and biopsy analysis to not only validate previously discovered connections among and between the three fields but also uncover new ones.
So found researchers at UCLA whose clinical focus for the challenge was non-small cell lung cancer (NSCLC).
The team’s work was published online May 8 in the Journal of Medical Imaging.
Radiological scientist William Hsu, PhD, and colleagues trained their neural networks on 262 public datasets, later testing it on an additional set of 89.
Using an AI-trialing method called gene masking, the team drew out associations between gene subsets and one or another finding on CT scans and molecular histology...