(156 days)
The TCL3 Motion Tracking System is an accessory to a Magnetic Resonance Imaging (MRI) scanner. The system uses a markerless sensor based technology for tracking of patient movement during an MRI session. It provides the current position of the patient in real-time to the MRI scanner. The TCL3 System is intended to support, supplement and/or augment the performance of the Siemens Magnetom Skyra, Siemens Magnetom Prisma, Philips Achieva and GE Signa Premier scanners.
The TCL3 Motion Tracking System monitors the patient's head for the scan. It can be turned off between patient scans. While running, the TCL3 Motion Tracking System continuously scans the surface of the patient's head, producing high-resolution 3D surfaces consisting of thousands of individual points. A structured light technique is utilized, using the combination of a camera and an infrared light modulator to reconstruct 3D surfaces of the patient's head. Each second, 30 surfaces are created. Each of these surfaces is used for geometric alignment relative to an initial reference position obtained at the beginning of the scan. From these alignments, motion data can be calculated in real-time.
The TCL3 Motion Tracking System is an accessory to a Magnetic Resonance Imaging (MRI) scanner that uses markerless sensor-based technology to track patient movement during an MRI session. It provides the current position of the patient in real-time to the MRI scanner.
Here's an analysis based on the provided document:
1. Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance (TCL3 Motion Tracking System) | Notes from Comparison with Predicate |
|---|---|---|
| Translational Accuracy | 200 μm | Predicate device (KinetiCor Motion Correction System) reported 100 μm. This is a difference highlighted in the comparison table. |
| Rotational Accuracy | 0.2 degrees | Predicate device reported 0.1 degrees. This is a difference highlighted in the comparison table. |
| Recording Rate | 30 frames per second | Predicate device reported 60 frames per second. This is a difference highlighted in the comparison table. |
| MRI Scanner Compatibility | Siemens MAGNETOM Prisma 3T, Siemens MAGNETOM Skyra 3T, Philips Achieva 3T, GE Signa Premier 3T | This expands upon the predicate device's compatibility (Siemens MAGNETOM Skyra 3T only). |
| Core Technology | Markerless sensor-based technology, uses one camera and one infrared light modulator to identify and track a surface. | Predicate device uses at least two cameras to identify and track a physical marker. This is a key technological difference. |
| Line of Sight | Line of sight for the camera and infrared light modulator to the patient. | Predicate device required line of sight for two cameras to the marker. |
| Powering | Battery, >8 hours | Predicate device used plug-in power. |
| Cross Calibration Procedure | Iteratively adapting | Predicate device required at least once per month. |
| Electrical and Mechanical Safety | Met applicable standards (IEC 60601-1) | Verified and validated through bench testing. |
| Electromagnetic Compatibility (EMC) | Met applicable standards (IEC 60601-1-2) | Verified and validated through bench testing. |
| Software Life-cycle Processes | Met applicable standards (IEC 62304) | Verified and validated through software testing, including off-the-shelf software and cybersecurity. |
| Risk Management | Applied ISO 14971 standards, risks analyzed, mitigations implemented and tested. | Overall risk management was performed. |
| MR Compatibility | Met requirements | Verified and validated through bench testing. |
| Mechanical Compatibility | Met requirements | Verified and validated through bench testing. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state a sample size for a "test set" in the context of clinical studies on human subjects. The performance evaluations described are primarily bench testing and technical verifications/validations.
The document mentions that "Clinical data was not required for this type of device." This implies that the performance data does not originate from a clinical trial with a traditional patient test set.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
Since "Clinical data was not required" and the testing primarily involved bench tests and technical verifications, the concept of "ground truth" as established by medical experts for a diagnostic performance study does not directly apply here. Instead, ground truth would refer to established engineering specifications and measurements. The document does not specify the number or qualifications of engineers or technicians who performed the bench testing and verified the technical specifications.
4. Adjudication Method for the Test Set
Given the nature of the testing (bench testing, technical verification, and validation) and the statement that "Clinical data was not required," there was no adjudication method described for a clinical test set, as no such clinical test set was used.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done
No MRMC comparative effectiveness study was done or reported. The document explicitly states, "Clinical data was not required for this type of device." Therefore, there is no information about the effect size of how much human readers improve with AI vs without AI assistance.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device is described as an "accessory to a Magnetic Resonance Imaging (MRI) scanner" that "provides the current position of the patient in real-time to the MRI scanner." This implies that the device is continually active and providing data to the MRI system itself during a scan, rather than acting as a standalone diagnostic tool that a human would then interpret.
The performance data focuses on the accuracy and reliability of the motion tracking algorithm itself (e.g., translational accuracy, rotational accuracy, recording rate), as measured through bench testing. This can be interpreted as a form of standalone performance evaluation for its core function (motion tracking and data provision to the scanner), but not in the context of a diagnostic standalone performance where an algorithm generates a finding for human review.
7. The Type of Ground Truth Used
For the technical performance metrics (translational accuracy, rotational accuracy, recording rate, MR compatibility, etc.), the ground truth would have been established through calibrated measurement instruments and established engineering standards in a bench testing environment. The document implies that these were objectively measurable parameters against which the device's output was compared.
8. The Sample Size for the Training Set
The document does not mention a training set in the context of machine learning. The TCL3 Motion Tracking System uses "markerless sensor-based technology" and "structured light technique," which suggests an algorithmic approach. However, there's no information provided about any machine learning training data or its size.
9. How the Ground Truth for the Training Set Was Established
Since no training set for machine learning is mentioned, there is no information provided on how ground truth for a training set was established.
§ 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.