Regulatory Science Tools Catalog
The Regulatory Science Tools Catalog provides a peer-reviewed resource for use where standards and qualified Medical Device Development Tools (MDDTs) do not yet exist. These tools do not replace FDA-recognized standards or MDDTs. This catalog collates a variety of regulatory science tools that the FDA's Center for Devices and Radiological Health's (CDRH) Office of Science and Engineering Labs (OSEL) developed. If you are considering using a tool from this catalog in your marketing submissions, note that these tools have not been qualified as Medical Device Development Tools and the FDA has not evaluated the suitability of these tools within any specific context of use. You may request feedback or meetings for medical device submissions as part of the Q-Submission Program.
Registration-based Automated Matching and Correspondence (RAMAC) is a tool that automatically identifies corresponding locations of landmarks across multiple images.
This regulatory science tool is an AI model tool used for developing and evaluating deep learning-based survival models.
This regulatory science tool (RST) is a computational model for predicting implantable lithium battery temperature, remaining capacity and longevity.
DxGoals is a freely-accessible, RShiny software application that is intended to determine and visualize performance goals for common diagnostic test classification accuracy metrics including sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio. Model outputs are dependent on user inputs of desired risk stratification (pre- and post-test probabilities of the target condition). The tool also analyzes whether goals are met with statistical significance.
- Github Webpage: https://github.com/DIDSR/DxGoals
- Link to Software: https://fda-cdrh-osel-didsr-rst.shinyapps.io/DxGoals/
This regulatory science tool (RST) is a MATLAB script that automates the determination of stiffness from the slope of a linear region from mechanical test data using an algorithm that is in compliance with ASTM E3076-18 [1]. Specifically, it analyzes test data (i.e., force-displacement curve or torque-angle curve) and then generates output parameters including bending and torsional stiffness typically requested in the preclinical mechanical performance test standards, ASTM F3574 [2] and ASTM F2267 [3].
DomID is a Python package offering a suite of unsupervised deep learning algorithms specifically designed for clustering medical image datasets. The primary goal is to identify subgroups that have not been previously annotated in a given image dataset.
This regulatory science tool is a mathematical model of the cardiovascular system response to fluid perturbations and includes a cohort generation tool to simulate virtual subjects as part of non-clinical testing of physiologic closed-loop control algorithms that automate fluid infusions following blood loss.
This regulatory science tool (RST) is a software program written in Python for performance assessment of segmentation algorithms applied to digital pathology whole slide images (WSIs).
This regulatory science tool is a computer model intended to support evaluation of photon counting detectors (PCDs) during the product development phase by generating in-silico X-ray projections of computational anatomical models detected by PCDs.
sFRC (scanning Fourier Ring Correlation) is a tool that compares radiological images from AI or iterative-based image restoration algorithms against those from standard-of-care analytical algorithms to identify and label hallucinations (aka fakes) using small red bounding boxes, which serve as visual indicators of the detected hallucinations.
This RST, a “threshold-based” validation method, provides a means to determine an acceptance criterion for computational models. A “credible” computational model has the potential to provide a meaningful evaluation of safety in medical-device submissions [1,2].
This regulatory science tool is a software program written in Python for analyzing whole slide images (WSIs) and assisting developers or pathologists in the assessment of machine learning algorithms used in digital pathology.
This regulatory science tool comprises a model for conducting a retrospective analysis of COVID-19 intervention strategies.
This regulatory science tool comprises a computer model of a human action potential, which includes the effects of heart failure (HF) and the anti-arrhythmic drugs amiodarone (AM) and d-sotalol (DS).
This regulatory science tool presents Python-based software for evaluating computer models that predict the number of COVID-19 deaths or hospitalizations expected in a specific locality.
This regulatory science tool presents a method for assessing credibility of patient-specific computational models implemented in medical device software.
The Virtual Imaging Clinical Trials for Regulatory Evaluation (VICTRE) computer modeling pipeline is a set of tools that allow for the replication of clinical trials of in silico breast radiographic images for the evaluation of digital mammography (DM) and digital breast tomosynthesis (DBT) devices.
The Virtual Family provides detailed three-dimensional computational models of the human anatomy including an adult male, an adult female, and two children
A series of benchmark problems with known exact solutions that can be used to verify if tissue-level (e.g., ventricular, atrial) computational models of cardiac electrophysiology have been implemented correctly
A computational modeling tool that provides first-pass estimation of the thermal effect produced in the vaginal wall by vaginal therapy devices.