The U.S. Food and Drug Administration (FDA) has finalized rules that make it easier for developers of computer-aided detection (CADe) software to win regulatory clearance for their products. Certain CADe products can now be classified as class II devices.
The final order, which will be published January 22 in the Federal Register, specifically covers what the agency calls "medical image analyzers" for detecting breast cancer on mammography, lung nodules on radiography, and dental caries on radiography. It does not cover computer-assisted diagnosis (CADx) software or computer-assisted triage devices, which have been previously addressed by the FDA.
The change streamlines regulatory review and provides patients with more timely access to these CADe software applications, the FDA said.
What the change covers
The new classification specifically applies to software applications designed to work with radiologists and physicians, rather than replace them. The initiative is part of a broader FDA effort to relax or clarify regulation of certain types of diagnostic software, such as artificial intelligence (AI) algorithms.
A medical image analyzer "incorporates pattern recognition and data analysis capabilities and operates on previously acquired medical images," the FDA wrote in the currently unpublished version of the final order. "This device is not intended to replace the review by a qualified radiologist, and is not intended to be used for triage, or to recommend diagnosis."
In addition to the reclassification, the FDA also adopted special controls for these CADe software applications. The FDA believes that these special controls will provide a reasonable assurance of safety and effectiveness. Specifically, the FDA said that design verification and validation of the CADe software must include the following:
- A detailed description of the image analysis algorithms including a description of the algorithm inputs and outputs, each major component or block, and algorithm limitations
- A detailed description of prespecified performance testing methods and dataset(s) used to assess whether the device will improve reader performance as intended and to characterize the standalone device performance. Performance testing includes one or more standalone tests, side-by-side comparisons, or a reader study, as applicable
- Results from performance testing that demonstrate that the device improves reader performance in the intended use population when used in accordance with the instructions for use
- Appropriate software documentation (e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities, including system-level test protocol, pass/fail criteria, and results; and cybersecurity)
Furthermore, the software labeling must include the following:
- A detailed description of the patient population for which the device is indicated for use
- A detailed description of the intended reading protocol
- A detailed description of the intended user and user training that addresses appropriate reading protocols for the device
- A detailed description of the device inputs and outputs
- A detailed description of compatible imaging hardware and imaging protocols
- Discussion of warnings, precautions, and limitations that must include situations in which the device may fail or may not operate at its expected performance level (e.g., poor image quality or for certain subpopulations), as applicable
- Device operating instructions
- A detailed summary of the performance testing, including test methods, dataset characteristics, results, and a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment