VICTRE: Virtual Imaging Clinical Trials for Regulatory Evaluation
A real full-field digital mammogram of a patient next to the in silico version of one of our computational models of human anatomy (the simulated image is on the left).
The results of the computer-simulated VICTRE trial are consistent with the comparative trial using human subjects and human image interpreters. While further research is needed to assess the generalizability of the findings, the work reported in this article provides evidence that state-of-the-art computational methods can lead to less burdensome regulatory evaluation approaches.
It is important to note that the all–in silico approach for conducting imaging trials is not intended to replace but rather complement or minimize traditional clinical trials. Incrementally incorporating computational results in regulatory submissions can, for example, help decrease the human trial size and length.
Evaluation of Digital Breast Tomosynthesis as Replacement of Full-Field Digital Mammography Using an In Silico Imaging Trial. A Badano, CG Graff, A Badal, D Sharma, R Zeng, FW Samuelson, SJ Glick and KJ Myers. JAMA Netw Open. 2018;1(7): e185474. https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2717000.
Future research on in silico imaging clinical trials needs to address limitation in the VICTRE study. In addition, a systematic exploration of the trial parameters including lesion types and sizes is now possible and greatly facilitated by the availability of open-source, free software tools (see https://github.com/DIDSR/VICTRE).
Expensive and lengthy clinical trials can delay regulatory evaluation of innovative technologies, affecting patient access to high-quality medical products. Although computational modeling is increasingly used in product development, it is rarely at the center of regulatory applications. Within this context, the VICTRE project attempted to replicate a previously conducted imaging clinical trial using only computational models. The VICTRE trial involved no human subjects and no clinicians. All trial steps were conducted in silico. The fundamental question the VICTRE trial addressed is whether in silico imaging trials are at a mature development stage to play a significant role in the regulatory evaluation of new medical imaging systems. The VICTRE trial consisted of in silico imaging of 2,986 virtual patients comparing digital mammography (DM) and digital breast tomosynthesis (DBT) systems. The improved lesion detection performance favoring DBT is consistent with results from a comparative trial using human patients and radiologists.