(28 days)
The ClearPoint System is intended to provide stereotactic guidance for the placement and operation of instruments or devices during planning and operation of neurological procedures within the MRI environment and in conjunction with MR imaging. The ClearPoint System is intended as an integral part of procedures that have traditionally used stereotactic methodology. These procedures include biopsies, catheter and electrode insertion including deep brain stimulation (DBS) lead placement. The System is intended for use only with 1.5 and 3.0 Tesla MRI scanners and MR Conditional implants and devices.
The ClearPoint System is comprised of a workstation laptop with software, the SMARTGrid™ MRI Guided Planning Grid, the SMARTFrame™ MRI-Guided Traiectory Frame, the SMARTFrame™ Accessory Kit and the SMARTFrame™ Thumbwheel Extension. The SMARTGrid and associated Marking Tool are designed to assist the physician to precisely position the entry hole as called out in the trajectory planning software. The SMARTFrame is an Adjustable Traiectory Frame (ATF) that provides the quidance and fixation for neurosurgical tools. The MRI visible fluids of the Targeting Cannula along with the fiducial markers in the frame allows for trajectory feedback when the physician views the MRI images, makes changes and confirms with subsequent MR images. The modified ClearPoint Software is used to provide stereotactic quidance for the insertion of one or more devices into the brain within a magnetic resonance imaging (MRI) environment, using hardware provided by ClearPoint Neuro, Incorporated. The software will guide the end user through a set of discrete workflow steps for identifying localization hardware mounted onto the patient, planning one or more trajectory paths into the brain, quiding the alignment of one or more stereotactic frames along each of the planned trajectories, and monitoring the insertion of one of more devices into the brain. The software also supports workflow for creating pre-operative plans prior to carrying out the intraoperative procedure. The software will be installed on a physical laptop computer situated inside the MRI Suite during the intra-operative procedure. There, it will be used in conjunction with a MRI scanner, the SMARTFrame adjustable trajectory frame (ATF), and associated disposable hardware kits provided by ClearPoint Neuro to guide the user through the insertion of one or more devices into the brain. Throughout the procedure, in instances where specific scans are required, the software application will prescribe scan plane parameters detailing the position and angulation of a desired image acquisition necessary to proceed with the workflow. In these cases, users are required to enter the parameters prescribed by the software manually on the MRI scanner console to carry out the appropriate image acquisition. The ClearPoint System can be used with any MRI-compatible head fixation frame to immobilize the patient's head with respect to the scanner table, as well as with any imaging coil(s) (supplied by scanner manufacturers) that meet the physician's desired imaging quality. ClearPoint Neuro also supplies an optional head fixation frame that can be used with the ClearPoint System.
The provided document describes a 510(k) premarket notification for a software update (version 2.1) to the ClearPoint System. The primary focus of the submission is to demonstrate that the updated software is substantially equivalent to the predicate device (ClearPoint System with software 2.0).
Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Key Finding: The document explicitly states that the hardware and Indications for Use are unchanged from the predicate device. The updates are limited to the software of the ClearPoint System. Therefore, the "study" described focuses on software verification and validation, primarily demonstrating that the new software does not degrade performance or introduce new risks compared to the previous version, rather than establishing direct clinical effectiveness or an acceptance criteria for a new device.
1. Table of Acceptance Criteria and Reported Device Performance
Given that this submission is for a software update to an already cleared device, the acceptance criteria are framed in terms of ensuring the continued performance and safety of the device, rather than establishing initial performance benchmarks against a specific clinical threshold. The core acceptance criterion for this 510(k) is substantial equivalence to the predicate device.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| No Regression in Existing Functionality | Head-To-Head Comparison: ClearPoint 2.1 passed successfully, verifying "no unintended changes have been introduced from the previous version in essential features that are not expected to have changed." |
| Image Registration Unit Test: ClearPoint 2.1 passed successfully, verifying "users will not be required to perform large manual registrations more often than in the previous version." | |
| Integrity of Core Algorithms (Segmentation, Low-Level Math) | Automated Testing (Segmentation & Unit Tests): "All automated tests were executed with no failures and no incidental observations." This confirms the underlying algorithms perform as expected. |
| Maintenance of Defined Accuracy Specifications (with MRI scanner) | Integrated System Testing: "All tests were executed and pass results were obtained," verifying "the ClearPoint 2.1 software is able to guide placement of a device within the defined accuracy specifications of the system." (The document states the system's targeting accuracy is ±1.5mm @ ≤125mm, implying this was maintained.) |
| Compliance with Software Standards (IEC 62304) and Risk Management (ISO 14971:2019) | "Results of the software verification and validation activities demonstrate compatibilities with the requirements of the IEC 62304 standard. Risk analysis activities were also performed in compliance with requirements of ISO 14971:2019." |
| No New Safety or Effectiveness Issues | Concluded that "The minor differences between the subject and predicate device do not raise any new issues of safety and effectiveness when the device is used as labeled, and the design controls and data collected ensure no adverse impact on safety or effectiveness." |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: The document describes "test cases" and "data inputs" used for various software tests, but does not provide a specific number of cases or patients/procedures used in these tests. It refers to "previously acquired test image data" for manual verification tests.
- Data Provenance: Not explicitly stated, but the mention of "previously acquired test image data" suggests the use of existing, likely retrospective, data for some manual testing. No specific country of origin is mentioned. The integrated system testing involved "reproducing clinical usage" with an MRI scanner, implying simulated or real-world data akin to clinical scenarios.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Not applicable in the traditional sense of clinical experts establishing ground truth for a diagnostic AI. The document describes "two different testers" for manual verification tests.
- Qualifications of Experts: The qualifications of these "testers" are not specified beyond their role in executing tests. Given the nature of a software update, these would likely be software quality assurance or engineering personnel rather than medical professionals.
4. Adjudication Method for the Test Set
- Adjudication Method: Not explicitly described as an adjudication method for ground truth, as the testing focuses on software functionality rather than clinical interpretation. For "manual verification bench tests," it states "Tests were executed independently by two different testers using the same build of software." This implies a form of independent verification but not a concensus-based adjudication of a medical "ground truth."
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done
- MRMC Study: No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not performed. This submission is for a software update to a stereotaxic guidance system, not a diagnostic AI intended to assist human readers in interpreting medical images. Therefore, a study to measure human reader improvement with AI assistance is not relevant to this type of device and submission.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: The testing described focuses on the software's functional correctness and its ability to maintain the system's "defined accuracy specifications" when integrated with hardware and MRI scanners.
- Automated Tests: These "exercise all the underlying segmentation algorithms in isolation outside the application against a range of data inputs" and "exercise low-level math and other libraries in isolation." This broadly represents a form of standalone performance testing for specific algorithmic components. However, this is not a measurement of diagnostic accuracy but rather functional validation.
- The "Targeting Accuracy" of the system is stated as "±1.5mm @ ≤125mm," which is a performance specification for the entire system, not just the software in isolation. The integrated system tests verify that the software contributes to maintaining this accuracy.
7. The Type of Ground Truth Used
- Type of Ground Truth: For the software verification and validation, the "ground truth" is implied by the expected output of the software (e.g., consistency with predicate software, known expected results for algorithms, or adherence to the system's accuracy specifications). It is not based on expert consensus, pathology, or outcomes data in a clinical sense. It's a technical "ground truth" derived from software requirements and direct comparison to the previous, cleared software version.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not applicable/Not provided. This document describes a software update for a medical device that provides stereotactic guidance. It is not an AI/ML device that requires a "training set" in the context of machine learning model development. The software updates are described as "updates" and "upgraded," implying feature changes or bug fixes rather than re-training of a learned model.
9. How the Ground Truth for the Training Set was Established
- Ground Truth for Training Set: Not applicable. As stated above, this is a software update for a medical device, not an AI/ML application that involves a training set and associated ground truth establishment for model learning.
§ 882.4560 Stereotaxic instrument.
(a)
Identification. A stereotaxic instrument is a device consisting of a rigid frame with a calibrated guide mechanism for precisely positioning probes or other devices within a patient's brain, spinal cord, or other part of the nervous system.(b)
Classification. Class II (performance standards).