(121 days)
SWIp is a software option intended for use on Achieva and Ingenia 1.5T & 3.0T MR Systems. It's indicated for magnetic resonance imaging of the Brain. SWIp is a technique using phase information to enhance contrast between tissues presenting susceptibility differences, such as deoxygenated blood or some mineral deposits (e.g. calcium deposits). Due to this contrast enhancement, SWIp images are sensitive for structures containing venous blood such as cerebral venous vasculature. When used in combination with other clinical information, SWIp may help the expert radiologist in the diagnosis of various neurological pathologies.
SWIp (Susceptibility Weighted Imaging with Phase enhancement) exploits the susceptibility differences between tissues. It is based on a 3D FFE acquisition, multiecho compatible, generating high resolution magnitude and phase images.
Phase images are unwrapped to create Susceptibility Weighted Phase (SW-P) images highlighting phase changes due to local susceptibility differences. The magnitude images and SW-P information are combined to generate Susceptibility Weighted Magnitude (SW-M) images with enhanced susceptibility contrast. SW-M images show de-oxygenated blood, such as veins, as hypo-intense signals.
The feature requires:
- Specific parameter settings for the 3D FFE sequence, within cleared parameter limits, to acquire the MR signals
- A new calculation function to generate SW-M and SW-P images. This function uses a set of MR images as input that is generated in a cleared manner from the acquired MR signals.
- The new images need to be stored and displayed with the appropriate labels (SW-M and SW-P), applying the facilities provided by the cleared platform.
Here's an analysis of the provided text regarding the acceptance criteria and study for the SWIp device, formatted to answer your specific questions.
Important Note: The provided document is a 510(k) Summary, which is a premarket notification to the FDA. It often summarizes validation and verification activities rather than providing detailed clinical study protocols and results. As such, some of the information you've requested regarding specific clinical trial methodologies (like MRMC study effect size, concrete acceptance criteria tables with performance metrics) is not explicitly present in this type of document. The summary focuses on demonstrating substantial equivalence to predicate devices based on non-clinical and clinical tests confirming safety and intended use.
Based on the available information:
Acceptance Criteria and Device Performance
-
A table of acceptance criteria and the reported device performance
The document does not present a formal table of quantitative acceptance criteria and corresponding reported device performance metrics in the way one might see in a detailed clinical trial report for an AI/CAD product. Instead, it refers to successful completion of non-clinical and clinical tests, with conclusions drawn about the device's acceptable performance for its intended use.
Implicit Acceptance Criteria and Reported Performance:
Criteria Category Implicit Acceptance Criteria Reported Device Performance Non-Clinical Performance Device functions as designed without crashes, hang-ups, or workflow issues. "All the tests performed for SWIp were successful. While using SWIp, the system didn't crash or hang-up. Workflow was smooth and no problems occurred." (DHF176222 Verification Test Report) Clinical Performance Device meets all clinical user needs on specified MR systems (Achieva and Ingenia 1.5T and 3.0T systems) and helps expert radiologists in diagnosis. SWIp images sensitive for structures containing venous blood, enhancing contrast for susceptibility differences. "The clinical validation of SWIp has completed successfully. All clinical user needs are passed for Achieva and Ingenia. 1.5T and 3T systems." (DHF176223 Validation Test Report). "SWIp images are sensitive for structures containing venous blood such as cerebral venous vasculature." Safety & Effectiveness Device is safe, effective, and performs as well as or better than legally marketed predicate devices; does not introduce new indications or hazards. "The nonclinical and clinical tests have demonstrated that the device is safe and works according to its intended use." "The SWIp software does not introduce new indications for use, nor does the use of the device result in any new potential hazard." Parameter Compliance Specific parameter settings for 3D FFE sequence are within cleared parameter limits. "Specific parameter settings for the 3D FFE acquisition, multiecho compatible, generating high resolution magnitude and phase images... within cleared parameter limits, to acquire the MR signals." Image Generation/Display New calculation function generates SW-M and SW-P images accurately; images are stored and displayed with appropriate labels. "A new calculation function to generate SW-M and SW-P images... The new images need to be stored and displayed with the appropriate labels (SW-M and SW-P), applying the facilities provided by the cleared platform." -
Sample sizes used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not explicitly state the sample size (number of patients/scans) used for the clinical validation test set (DHF176223 Validation Test Report). It also does not specify the country of origin of the data or whether the data was retrospective or prospective. It generally refers to "clinical user needs are tested as part of the validation."
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document does not specify the number or qualifications of experts used to establish ground truth for the clinical validation. It mentions that SWIp "may help the expert radiologist in the diagnosis of various neurological pathologies," implying radiologists are the target users, but provides no details on how their expertise was leveraged for ground truth in the study.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe any specific adjudication method for establishing ground truth for the test set.
-
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
No MRMC comparative effectiveness study is described in this 510(k) summary. The device, SWIp, is a new image acquisition and processing technique (Susceptibility Weighted Imaging with Phase enhancement) that generates new image types (SW-M and SW-P images), not an AI/CAD system assisting human readers directly. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not apply in the context of this specific device's described function.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
SWIp is described as a "new calculation function to generate SW-M and SW-P images" based on acquired MR signals, which are then "stored and displayed." This function is inherent to the MR system's reconstruction capabilities. The validation focuses on the successful generation and utility of these images for clinical interpretation. In essence, the "algorithm only" performance is evaluated by whether the resulting images are correct, interpretable, and serve their intended purpose for the expert radiologist. The document confirms the "new calculation function" generates the new output images and that these images "are sensitive for structures containing venous blood."
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The specific type of ground truth used is not detailed. The language "may help the expert radiologist in the diagnosis of various neurological pathologies" suggests that ground truth would ultimately be related to established clinical diagnoses, likely confirmed by expert radiologist interpretation (possibly consensus, but not explicitly stated) and potentially in conjunction with other clinical information, as SWIp "is used in combination with other clinical information." Pathology or outcomes data are not mentioned as direct ground truth sources for the image validation itself.
-
The sample size for the training set
The document does not mention a training set, as SWIp appears to be a deterministic image reconstruction algorithm rather than a machine learning model that requires a distinct training phase.
-
How the ground truth for the training set was established
Not applicable, as a training set for machine learning is not mentioned for this device.
§ 892.1000 Magnetic resonance diagnostic device.
(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.