" Few prospective deep learning studies and randomised trials exist in medical imaging. Most non-randomised trials are not prospective, are at high risk of bias, and deviate from existing reporting standards. Data and code availability are lacking in most studies, and human comparator groups are often small. Future studies should diminish risk of bias, enhance real world clinical relevance, improve reporting and transparency, and appropriately temper conclusions."
https://www.bmj.com/content/368/bmj.m689
Vote 0
-
https://www.lemagit.fr/conseil/LIA-ne...olution-de-lintelligence-artificielle
Vote 0
Les signets de cette page sont gérés par un administrateur. 