1 code implementation • 11 Mar 2022 • Erendiz Tarakci, Joseph Mandeville, Fahmeed Hyder, Basavaraju G. Sanganahalli, Daniel R. Thedens, Ali Arbab, Shuning Huang, Adnan Bibic, Jelena Mihailovic, Andreia Morais, Jessica Lamb, Karisma Nagarkatti, Marcio A. Dinitz, Andre Rogatko, Arthur W. Toga, Patrick Lyden, Cenk Ayata, Ryan P. Cabeen
We consistently found high accuracy and ability of the U-net architecture to generalize performance in a range of 95-97% accuracy, with only modest reductions in performance based on lower fidelity imaging hardware and brain pathology.
