Clinical trials are expensive and delay the regulatory evaluation and early patient access to novel devices. In order to demonstrate an alternative approach, a recent effort at the Division of Imaging, Diagnostics, and Software Reliability at the U.S. Food and Drug Administration (known as the VICTRE project) demonstrated the replication of one such clinical trial using completely in-silico tools and compared results in terms of imaging modality performance between the human trial and the computational trial. The VICTRE trial involved imaging approzimately 3000 digital breast models in digital mammography and digital breast tomosynthesis system models. The simulated Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE) trial was designed to replicate a clinical trial that used human patients and radiologists. Images obtained with in silico versions of DM and DBT systems via fast Monte Carlo x-ray transport were interpreted by a computational reader detecting the presence of lesions.
Input variables : In silico created digital mammography and digital breast tomosynthesis images
Output Variables : Presence or Absence of Lesion
| Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
| Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : github.com
Additional links : jamanetwork.com
| Model Category | : | Public |
| Date Published | : | November, 2018 |
| Healthcare Domain | : | Medical Technology |
| Code | : | github.com |
| Medical Imaging |
| Health Risk Management |
| Disease Detection |