作者: Hugo J.W.L. Aerts
DOI: 10.1158/1078-0432.CCR-17-2804
关键词:
摘要: Artificial intelligence (AI), especially deep learning, has the potential to fundamentally alter clinical radiology. AI algorithms, which excel in quantifying complex patterns data, have shown remarkable progress applications ranging from self-driving cars speech recognition. The application within radiology, known as radiomics, can provide detailed quantifications of radiographic characteristics underlying tissues. This information be used throughout care path improve diagnosis and treatment planning, well assess response. tremendous for translation led a vast increase number research studies being conducted field, that is expected rise sharply future. Many reported robust meaningful findings; however, growing also suffer flawed experimental or analytic designs. Such errors could not only result invalid discoveries, but may lead others perpetuate similar flaws their own work. perspective article aims awareness issue, identify reasons why this happening, forward. Clin Cancer Res; 24(3); 532-4. ©2017 AACR.