Search Results

Caduceus S is intended as an intraoperative gudance system to enable minimally invasive surgery. Intraoperatively registered surgical Instruments are tracked by a passive marker sensor system to virtual computer image space on a patient's preoperative or intraoperative 2D or 3D image data.

Caduceus S enables image-guide navigation of medical image data, which can either be acquired preoperatively CT or intraoperatively C-arm by an appropriate image acquisition system.

Caduceus S offers pedicle screw implant size planning and navigation on rigid bone structures with intraoperatively registered surgical Instruments.

Caduceus S is indicated for L5~T6 spine surgery where reference to a rigid anatomical structure can be identified relative to the acquired patient imagery (CT or C-arm).

The headset (Surglasses) of the Caduceus S system is an optional heads up display that projects the 2D stereotaxic screens of the system's display.

Caduceus S surgical navigation system is an image guidance system, which is composed of Navi Tracker, Surglasses, other hardware (Navigation Cart with an arm, Touch Screen, Router, Control System, Connection System), disposable tools (Disposable Passive Sphere, Straight Guide Pin, Navi Clamp Kit, Instrument Adapter Type A&B, Calibration Plate, Registration Kit, Correction Tool), reusable tools (Calibration Board, Instrument Holder), and Spine Navigation Software. Caduceus S is an optical tracking and guiding system for spine surgery. It can track the marks on the surgical instruments and patient's anatomical structure with marks, and register with the preoperative or intraoperative images of the patients. During the surgery, it can be displayed on the Touch Screen and the head mounted display Surglasses to provide the navigation for the surgical instruments.

Here's a breakdown of the acceptance criteria and the study proving the Caduceus S device meets them, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

The core performance validation for this device, a surgical navigation system, relates to its accuracy in positioning and trajectory. The summary explicitly states:

*UBL = Upper Bound Limit (This indicates the upper limit of the confidence interval for the measured error, providing a statistical guarantee.)

Study Details

The primary study mentioned for evaluating device performance is a "System's accuracy" and "Performance and Usability of device intended use" study, which involved both phantom and cadaver studies.

1. Sample Size and Data Provenance:

   • Test Set Sample Size: The exact number of pedicle screws positioned or cases in the cadaver study is not explicitly stated as a number of subjects/specimens, but it mentions pedicle screws were positioned in L5-T6 spine. The testing was conducted in both "phantom and cadaver studies."
   • Data Provenance: The document does not specify the country of origin for the cadaver data. It states the studies were non-clinical. The studies were retrospective in the sense that they were pre-market validation studies using pre-existing materials (phantoms, cadavers) to simulate real-world conditions.

2. Number of Experts and Qualifications for Ground Truth:

   • The document does not specify the number of experts used to establish the ground truth or their specific qualifications. It mentions that the positional error was derived from the "post-op scan" and its virtual tip as recorded by the Caduceus S system. This suggests the ground truth was established by comparing system output to a precise post-procedure imaging measurement.

3. Adjudication Method:

   • The document does not describe an adjudication method involving multiple human readers for the test set. The ground truth appears to be based on direct measurement from post-operative imaging.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • No MRMC comparative effectiveness study was done. The submission explicitly states: "No clinical test data was used to support the decision of substantial equivalence." This means no study was performed comparing human readers with and without AI assistance to measure improvement. The device is purely an intraoperative guidance system, and its validation focuses on its technical accuracy rather than interpretive diagnostic performance.

5. Standalone Performance Study:

   • Yes, a standalone study was performed. The described "System's accuracy" assessment is a standalone evaluation of the algorithm's output (positional and angular error) against the established ground truth (derived from post-op scans). This is algorithm-only performance without a human-in-the-loop directly influencing the measured accuracy metrics.

6. Type of Ground Truth Used:

   • The ground truth was established by measurements obtained from post-operative imaging (post-op scan). Specifically, for positional error, it was the difference between the actual screw tip position derived from the post-op scan and the system's recorded virtual tip. For trajectory error, it was the difference between the screw orientation and its recorded virtual trajectory. This closely aligns with "outcomes data" or highly precise "imaging-based comparison."

7. Training Set Sample Size:

   • The document does not specify the sample size used for the training set. This is a common omission in 510(k) summaries, as the focus is on the validation of the final device, not the development process.

8. Ground Truth Establishment for Training Set:

   • The document does not provide details on how ground truth was established for any training set. Given the nature of a 510(k) submission and the device (a surgical navigation system rather than a diagnostic AI), details on training data are typically less prominent in the publicly available summary unless directly relevant to a novel AI methodology requiring extensive clinical data for training. The performance validation relies on the non-clinical bench and cadaver studies.

Ask a specific question about this device

The Bolt Navigation System assists in the accurate placement of pedicle screws when used in conjunction with an intraoperative fluoroscope. It utilizes intraoperative fluoroscopic and pre- operative MRI or CT axial images to provide surgical planning and navigational telemetry relative to gravity, based on a fixed entry point ascertained by the user and validated by intraoperative fluoroscopic imaging. It is not intended to track patient position. The System is indicated for open and minimally invasive pedicle screw placement using a posterior approach in the thoracolumbar and sacral spine (T-9 to S1) where the patients' relevant rigid anatomical structures can be clearly identified on the imaging.

The BNS is comprised of the Bolt Navigation Unit (BNU) (an iPod touch® mobile digital device with the Bolt navigation software loaded on it), the Bolt single use case, and sterile drape. The BNS is intended to provide navigational guidance during spine surgery. The system uses preand perioperative imaging data, and input from the surgeon via the BNU touchscreen to construct the proper angular position of the instrumentation and implants relative to gravity, and communicates this information to the surgeon via the BNU screen attached to the instrument allowing the surgeon to look at both the surgical site and the navigation data at the same time, thus attenuating the risk of attention shift. The BNS provides guidance data by displaying the angular orientation of a surgical instrument (such as a pedicle probe or awl) relative to a surgeon selected entry point on the patient and gravity. Angular orientation of the instruments is linked to the imaging data via the BNS. The system is intended to be used for both image fusion and navigation for spine surgery applications where reference to relevant rigid structures can be identified relative to a perioperative image data of the anatomy and the gravity vector.

Here's an analysis of the acceptance criteria and study details for the Bolt Navigation System ("BNS"), based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

Study Details

1. Sample size used for the test set and the data provenance:

   • Test Set (Cadaveric Trajectory Accuracy Study): The document doesn't explicitly state the number of cadavers or individual screw placements used in the cadaveric study. However, the results are presented as overall accuracy, testing levels T9 to S1 (thoracolumbar and sacral spine).
   • Data Provenance: The cadaveric study is a non-clinical test, implying it was conducted in a controlled lab setting, likely in the country of the manufacturer or test facility. It is a prospective study in the sense that the data was generated specifically for this validation.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • The document does not provide information on the number of experts or their qualifications used to establish ground truth for the cadaveric study.
   • For the cadaveric study, "Planned trajectory vs actual placement accuracy" was assessed, but the method for determining "actual placement" (e.g., post-insertion imaging, dissection measurement) and who evaluated it is not detailed.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • The document does not specify an adjudication method for the cadaveric study.

4. 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:

   • A formal MRMC comparative effectiveness study, comparing human readers with and without AI assistance, was not explicitly detailed in the provided summary.
   • A "multi-surgeon clinical study" was conducted, but its results are only summarized as supplementary information to show the device performs as intended, not as a comparative effectiveness study against a non-AI control group with quantifiable improvement.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • The "Clinical phantom accuracy results" represent a standalone performance assessment of the system against a known phantom, demonstrating the system's inherent accuracy in a controlled environment. The mean accuracy was 0.35 degrees.
   • The "Cadaveric accuracy results" also reflect the algorithm's performance in a more realistic surgical simulation, where surgical instruments guided by the BNS were evaluated for accuracy of placement against a planned trajectory. While a human surgeon uses the system, the
   • accuracy measurement itself quantifies the system's guidance.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

   • Clinical Phantom Accuracy: The ground truth for the phantom study would be the known, precisely manufactured dimensions and orientations of the phantom, which the device is designed to measure.
   • Cadaveric Trajectory Accuracy Study: The ground truth for this study is described as "Planned trajectory vs actual placement accuracy." The "planned trajectory" would be established pre-procedure (likely by a surgeon using imaging), and the "actual placement" would be measured post-procedure using a precise method (e.g., high-resolution CT, C-arm imaging, or physical measurement) to determine the deviation from the plan. The specific method for determining "actual placement" (which serves as the "truth") is not detailed.

7. The sample size for the training set:

   • The document does not provide information on the sample size of any training set used for the BNS software. The BNS utilizes "pre- and perioperative imaging data" and "intraoperative fluoroscopic and pre-operative MRI or CT axial images," suggesting it may rely on existing imaging data for its functionality, but details about supervised machine learning training, if any, are absent.

8. How the ground truth for the training set was established:

   • Since the document does not specify a training set or the use of machine learning that would require a distinct training set with ground truth, this information is not available. The system appears to be more of a navigation system based on physical principles and image registration rather than a deep learning model requiring extensive annotated training data.

Ask a specific question about this device

The ARAI™ System is intended as an aid for precisely locating anatomical structures in either open or percutaneous orthopedic procedures in the lumbosacral spine region. Their use is indicated for any medical condition of the lumbosacral spine in which the use of stereotactic surgery may be appropriate, and where reference to a rigid anatomical structure, such as the iliac crest, can be identified relative to intraoperative CT images of the anatomy.

The ARAI System simultaneously displays 2D stereotaxic data along with a 3D virtual anatomy model over the patient during surgery. The stereotaxic display is indicated for continuously tracking instrument position and orientation to the registered patient anatomy while the 3D display is indicated for localizing the virtual instrument to the virtual anatomy model over the patient during surgery. The 3D display should not be relied upon solely for absolute positional information and should always be used in conjunction with the displayed 2D stereotaxic information.

The ARAI™ System is a combination of hardware and software that provides visualization of the patient's internal boney anatomy and surgical guidance to the surgeon based on registered patient-specific digital imaging.

ARAI™ is a navigation system for surgical planning and/or intraoperative guidance during stereotactic surgical procedures. The ARAI™ system consists of two mobile devices: 1) the surgeon workstation, which includes the display unit and the augmented reality visor (optional), and 2) the control workstation, which houses the optical navigation tracker and the computer. The optical navigation tracker utilizes infrared cameras and active infrared lights to triangulate the 3D location of passive markers attached to each system component to determine their 3D positions and orientations in real time. The 3D scanned data is displayed with both 2D images and 3D virtual models along with tracking information on computer mounted on workstations near the patient bed and a dedicated projection display mounted over the patient. Augmented reality is accomplished with the 3D virtual models being viewed with dedicated headset(s).

Software algorithms combine tracking information and high-resolution 3D anatomical models to display representations of patient anatomy.

Here's an analysis of the acceptance criteria and study details for the ARAI™ Surgical Navigation System based on the provided FDA 510(k) summary:

The document does not explicitly present a table of acceptance criteria. Instead, it presents the results of performance validation for positional and angular errors. Therefore, the reported device performance is used directly to infer the implied acceptance criteria.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes Used for the Test Set and Data Provenance

• Positional and Angular Error Validation (Surgical Simulations):
  • Sample Size: Not explicitly stated in the provided text. The terms "overall 3D positional error" and "overall 3D angular error" are used, but they do not reveal the number of screws measured or the number of cadavers.
  • Data Provenance: Prospective, real-world simulation using cadavers ("Surgical simulations conducted on cadavers were performed for system validation."). The country of origin is not specified.
• Software Segmentation Quality:
  • Sample Size: A "set of test samples presenting lumbosacral spine, extracted from stationary and intraoperative Computed Tomography scans" was used. The exact number of samples is not provided.
  • Data Provenance: CT scans (both stationary and intraoperative) of the lumbosacral spine. It is unclear if these were retrospective or prospective, or their country of origin.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Positional and Angular Error Validation: The document describes the ground truth as the "real implants." It does not mention experts establishing the ground truth for this measurement directly, as it's a direct comparison between the virtual and physically placed surgical artifacts.
• Software Segmentation Quality: The ground truth was established by "manual segmentations prepared by trained analysts." The number of analysts and their specific qualifications (e.g., years of experience, specific medical specialty) are not provided.

4. Adjudication Method for the Test Set

• Positional and Angular Error Validation: Not applicable, as the ground truth derivation is not a subjective consensus process. It's a measurement against a physical reference.
• Software Segmentation Quality: The ground truth was established by "manual segmentations prepared by trained analysts." The document does not specify an adjudication method (like 2+1 or 3+1) if multiple analysts were involved or if a single analyst's segmentation was considered the ground truth.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

• The provided document does not describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study and therefore does not report an effect size for human readers improving with AI vs. without AI assistance. The performance testing focuses on the device's accuracy in tracking and displaying anatomical structures and instruments.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Study Was Done

• Yes, a standalone performance assessment of the algorithm appears to have been conducted, particularly for:
  • Positional and Angular Error Validation: This directly quantifies the system's accuracy in representing physical instrument and screw positions relative to the anatomical model, which is an algorithm-driven output.
  • Software Segmentation Quality: The "autonomous spine segmentation process" was compared against manual segmentations, indicating a standalone evaluation of the algorithm's performance in this task.

7. The Type of Ground Truth Used

• Positional and Angular Error Validation: The ground truth was the "real implants" positioned in cadavers. This is a form of direct physical measurement/outcome data.
• Software Segmentation Quality: The ground truth was expert manual segmentation ("manual segmentations prepared by trained analysts").

8. The Sample Size for the Training Set

• The document does not specify the sample size used for the training set for any of the algorithms (e.g., for spine segmentation or tracking). It only mentions test samples.

9. How the Ground Truth for the Training Set Was Established

• The document does not provide information on how the ground truth for the training set was established, as it does not describe the training process or the dataset used for training. It only details the establishment of ground truth for certain test sets.

Ask a specific question about this device

The HipXpert system is a manual surgical instrument and associated software application designed for use in planning surgery and aligning the acetabular components during hip arthroplasty procedures.

The HipXpert 3D Display and Anchoring application with the HoloLens2 is indicated for visual alignment of an acetabular cup impactor during hip arthroplasty when pin-based fixation of the HipXpert tool is utilized.

The HipXpert system provides a patient-specific hip arthroplasty surgical plan allowing for accurate acetabular positioning using CT mapping of a patient's pelvis using a software application and a reusable, manual, mechanical navigation instrument.

The HipXpert software planning application uses patient image data to create a detailed 3D model of the pelvis as well as the instrument settings necessary for proper acetabular cup orientation.

The HipXpert mechanical instrument has three legs which are secured to the pelvis. The legs form three points which define the sextant plane. The HipXpert mechanical instrument has two protractors that are adjusted to orientate an indicator pin in the direction of the desired orientation of the acetabular component.

The subject HipXpert 3D Display and Anchoring Application utilizes the previously cleared (K093491) HipXpert planning application and HipXpert tools in addition to a mixed reality headset (Microsoft HoloLens2) and QR target. The HoloLens2 is an off-the-shelf component developed and manufactured by Microsoft which is used to view superimposed 3D images from the HipXpert planning application on the real HipXpert tool. In order to properly orient the 3D images displayed by the HoloLens2, a QR target is used to anchor these 3D images in space as they are overlaid on the real HipXpert tool.

The HipXpert System, specifically the 3D Display and Anchoring application with the HoloLens2, was evaluated to ensure accurate alignment of an acetabular cup impactor during hip arthroplasty when pin-based fixation of the HipXpert tool is utilized.

Here's a breakdown of the acceptance criteria and the study proving the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text details various validation and verification activities rather than specific quantitative acceptance criteria in a table format. However, the performance reported for the HipXpert System focused on aspects like software validation, system orientation and position accuracy, image registration and tracking accuracy, and headset display performance.

2. Sample Size Used for the Test Set and Data Provenance

The non-clinical testing included a cadaveric model for verifying overall system orientation and position accuracy. The specific number of cadaveric models used is not specified.

Regarding data provenance for the accuracy testing, it was conducted internally as part of the device's verification and validation. The text does not specify the country of origin of the data or whether it was retrospective or prospective, but given it's a device validation, it would be considered prospective for the purpose of the study.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

The document does not specify the number or qualifications of experts used to establish ground truth for the test set.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method for establishing ground truth for the test set. The validation methods mentioned (cadaveric model using screws placed into the acetabulum and methods analogous to ASTM F2554-10) imply objective measurement rather than expert consensus on subjective evaluations.

5. 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 was mentioned. The HipXpert system is a surgical planning and alignment tool, and the focus of this submission is on the accuracy of the augmented reality display for guiding tool placement, not on interpreting images or improving human reader performance in a diagnostic context.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The HipXpert system, including the 3D Display and Anchoring application, is inherently a human-in-the-loop system. It provides visual guidance to a human surgeon. Therefore, a standalone (algorithm only) performance evaluation without human interaction would not be applicable or relevant to its intended use and was not described. The validation focused on the system's accuracy while being used by a human, even if a cadaver was the "patient."

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The ground truth for the accuracy evaluations appears to be based on objective physical measurements and established engineering standards. For instance, in the cadaveric model, the ground truth for "overall system orientation and position accuracy" would likely be the known, precise placement of screws in the acetabulum, validated by direct measurement or pre-defined landmarks. For system accuracy, image registration accuracy, and tracking accuracy, the ground truth would be precise measurements and positional data defined by the test setup, as per methods analogous to ASTM F2554-10, which are standards for evaluating the accuracy of medical image processing software and surgical navigation systems using precise physical fiducials and defined spatial relationships.

8. The Sample Size for the Training Set

The document does not provide information on the sample size used for the training set of any machine learning algorithms within the HipXpert System. The text primarily focuses on the validation of the system's functionality and accuracy, specifically the 3D display and anchoring application, rather than the development of the underlying planning algorithms (which existed in the predicate device K093491).

9. How the Ground Truth for the Training Set Was Established

Since no specific information about a training set for machine learning was provided, the method for establishing its ground truth is also not mentioned. The HipXpert software planning application itself, which creates the 3D model and instrument settings, was part of a previously cleared device (K093491). The current submission focuses on the augmented reality display portion.

Ask a specific question about this device

The NextAR™ TKA Platform is intended to be used to support the surgeon during total knee replacement procedures by providing information on bone resections, ligaments behavior, instrument and implant positioning.

The NextAR™ TKA Platform is intended to be used in combination with NextARTM stereotaxic instruments, the MyKnee® NextAR™ cutting guides, and general surgical instruments to implant the GMK Sphere Total knee system and perform ligament balancing. As an optional display, the smart glasses can be used auxiliary to the NextAR Platform to view the same 2D stereotaxic information as presented by the NextAR Platform.

The smart glasses should not be relied upon solely and should always be used in conjunction with the primary computer display.

The MyKnee® NextAR cutting guides include a camera/target holder and a PSI MyKnee® cutting guide both for tibia and femur. The MyKnee® cutting guides must be used as anatomical cutting blocks specific for a single patient anatomy, to assist in the positioning of total knee replacement components intraoperatively and in guiding the marking of bone before cutting. MyKnee® NextAR TKA cutting guides are for single use only.

The NextAR™ stereotaxic instruments are intended to be used to surgeon during specific orthopedic surgical procedures by providing information on bone resections, ligaments behavior, instrument and implant positioning. The NextAR™ stereotaxic instruments, when registered with the myKnee NextAR TKA cutting guides, provide reference to a patient's rigid anatomical structures, such as the femur and tibia, that can be identified relative to pre-operative CT based planning.

The NextAR™ TKA Platform is a CT based computer-assisted surgical navigation platform used in total knee replacement surgery and includes the following components:

• navigation software which displays information to the surgeon in real-time;
• Augmented Reality glasses;
• optical tracking system;
• PC based hardware platform;
• MyKnee NextAR Cutting Blocks; and
• reusable surgical instruments for total knee replacement procedures.

The system operates on the common principle of stereotaxic technology in which passive markers are mounted on the bones and an infrared camera is used to monitor the spatial location of the markers to avoid intraoperative registration of bony landmarks. Tracking sensors attached to the bones enable the surgeon to view the position and orientation of bones and instrumentation relative to preoperative data in real-time while performing the surgical procedure. The tracking sensors are provided sterile.

The NextAR™ TKA Platform aids the surgeon in executing the surgical plan by visualizing all the information in real time in a screen monitor. The placement of the implants is performed by cutting the bones using MyKnee® NextAR™ Cutting Blocks while reusable surgical instrumentation (provided non-sterile) guided by the tracking sensors can be used for recut. Although the position of the implants can be validated to assess the correct execution of the planning, the surgeon can change the surgical plan intraoperatively by analyzing the 3D models of the patient, the CT scan, and the 3D geometry of the implants.

The MyKnee® NextAR™ Cutting Blocks, manufactured from medical grade nylon, are single use patient-specific blocks which are designed from patient MRI or CT images. The blocks are designed to be used in standard medial or lateral parapatellar surgical approaches with each set comprised of a femoral block, a tibial block, and two bone models of the patient's femur and tibia (optional). The femoral cutting blocks are provided in right and left configurations in sizes 1 to 7 and 1+ to 6+ and the tibial cutting blocks are provided in right and left configurations in sizes 1 to 6. The blocks are provided sterile via gamma irradiation or non-sterile.

The FDA 510(k) summary for the NextAR™ TKA Platform (K193559) provides details on the device's acceptance criteria and the studies conducted to prove its performance.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a single, consolidated format. However, it mentions various types of testing and states that "Testing was conducted according to written protocols with acceptance criteria that were based on standards." The "Discussion" section also states, "Minor differences in the optical tracking systems and use of patient specific instrumentation are addressed by performance testing." This implies that the performance testing confirmed the device met established criteria for those specific aspects.

Based on the information provided, we can infer some of the areas where acceptance criteria would have been applied:

2. Sample Size for Test Set and Data Provenance

The document explicitly mentions a "cadaver study" as part of the performance data.

• Sample Size for the Test Set: Not explicitly stated in the provided text.
• Data Provenance: The cadaver study would involve human remains, but the exact country of origin or whether it was retrospective/prospective in the context of data collection for this specific study is not detailed. However, cadaver studies are inherently prospective for the purpose of testing the device.

3. Number of Experts and Qualifications for Ground Truth

The document does not explicitly mention the number of experts, their qualifications, or their role in establishing ground truth specifically for the reported studies (e.g., cadaver study). For a device like this, ground truth would likely be established through precise anatomical measurements or post-hoc imaging.

4. Adjudication Method for the Test Set

The document does not detail any adjudication method (e.g., 2+1, 3+1) for the test set. Adjudication methods are typically associated with human interpretation of medical images or data, which is not the primary focus for establishing the technical accuracy of a navigation system in a cadaver study.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No mention of an MRMC comparative effectiveness study, or the effect size of human readers improving with AI vs. without AI assistance, is made. This device is a surgical navigation platform, not an AI-assisted diagnostic tool that heavily relies on human reader interpretation of images. The smart glasses are described as an auxiliary display, not an AI-driven interpretive aid for human readers.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The performance testing, particularly the "performance testing to evaluate mechanical and optical properties" and elements of the "cadaver study," would inherently involve evaluating the standalone performance of the algorithm and system components. The software validates the navigation software's ability to display information to the surgeon accurately. The cadaver study would assess how accurately the system guides the surgeon, implying that the system's output (measurements, guidance) is evaluated independently of a human's ultimate judgment during the assessment phase of the study, though a human surgeon performs the actions based on the guidance.

7. Type of Ground Truth Used

For the specific performance testing of this surgical navigation platform, especially in the cadaver study, the ground truth would likely be established using precise direct physical measurements (e.g., with highly accurate measurement tools or CMMs) or potentially post-operative imaging with precise measurements of the cadaver bones to verify the accuracy of resections and implant positioning as guided by the system. The "pre-operative CT based planning" is used by the device, and the device ensures "reference to a patient's rigid anatomical structures... that can be identified relative to pre-operative CT based planning." Therefore, the ground truth would be tied back to the anatomical accuracy relative to these plans.

8. Sample Size for the Training Set

The document does not provide information about a specific "training set" sample size. This type of device relies on established biomechanical principles and image processing of CT scans for its planning and navigation, rather than a deep learning model that requires a discrete training set in the conventional sense. The software is validated, but not "trained" in an iterative machine learning fashion on a large dataset of patient outcomes.

9. How the Ground Truth for the Training Set Was Established

As no specific training set for a machine learning model is mentioned, the method for establishing its ground truth is not applicable or detailed in this summary. The system's foundational data (e.g., anatomical models, instrument specifications) are established through engineering design, scientific principles, and preclinical testing.

Ask a specific question about this device