Yang Yang, PhD, Zahi Fayad, PhD, Xueyan Mei, PhD, Timothy Deyer, PhD and colleagues from Icahn School of Medicine at Mount Sinai, University of Oklahoma, and Weill Cornell Medicine conducted a study to evaluate the performance of AI models pretrained on radiologic images compared to photographic images. They created a large-scale, diverse medical imaging dataset to generate CNNs trained only from radiologic images. This is a significant study because the researchers demonstrated that pretraining with radiologic images rather than photographic images may result in more effective transfer learning for radiology AI models. A paper detailing the study entitled RadImageNet: An Open Radiologic Deep Learning Research Dataset for Effective Transfer Learning was published in RSNA Radiology AI on July 27, 2022. Within 10 days of publication, the paper has been downloaded over 1,000 times.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. To demonstrate the value of pretraining with millions of radiologic images compared with ImageNet photographic images on downstream medical applications when using transfer learning. This retrospective study included patients who had a radiologic study between 2005 and 2020 at an outpatient imaging facility.