Search Results

ARVIS® Shoulder is indicated for assisting the surgeon in the positioning and alignment of implants relative to reference alignment axes and landmarks in stereotactic orthopedic surgery.

The system aids the surgeon in making intraoperative measurements and locating anatomical structures of the shoulder joint based on the patient's preoperative imaging.

The system is intended to be used with the head mounted ARVIS® Eyepiece display for augmented reality visualization and information, such as visualization of the preoperative plan and display of instrument and implant alignment information. The augmented/ virtual displayed information should not be relied upon solely for absolute positional/alignment information and should always be used in conjunction with the displayed stereotaxic information.

ARVIS® Shoulder is indicated for total shoulder arthroplasty using the Enovis AltiVate, LimaCorporation PRIMA, and LimaCorporation SMR implant systems.

ARVIS® Shoulder is a computer-controlled navigation system for shoulder arthroplasty. It aids the surgeon in making intra-operative measurements and locating anatomical structures of the shoulder joint based on the patient's preoperative imaging to assist with selection and positioning of orthopedic implant components. The system consists of software, electronic hardware and surgical instruments.

The ARVIS® Eyepiece is mounted on the surgeon's head and contains tracking cameras that locate the positions of trackers on the patient and instruments. All system measurements, instructions, prompts, and alerts are shown to the surgeon on the Eyepiece display. The Eyepiece communicates with the Belt Pack which is worn by the surgeon around their waist and houses the computer module that runs the ARVIS® Shoulder application software.

The device's workflow involves CT based preoperative planning followed by intraoperative navigation and execution. The preoperative planning software enables 3D virtual implant positioning based on the patient's CT reconstructed digital bone model and bony landmarks. The shoulder navigation software then matches the patient's digital bone model and landmarks to the intraoperative landmarks registered by the surgeon, allowing an image-based navigation to follow. The surgeon uses the plan data as guidance to navigate and help position shoulder instruments and implants.

The provided text does not contain details about acceptance criteria or a study proving the device meets those criteria for the ARVIS® Shoulder system.

The document is an FDA 510(k) clearance letter and a 510(k) Summary. These documents primarily focus on demonstrating substantial equivalence to a predicate device, rather than providing detailed acceptance criteria and performance study data as would be found in a clinical study report or a more comprehensive technical document.

While the document mentions "AI-based automatic image segmentation and landmarking algorithms" and states that "The algorithms and the data used to train and test these remain unchanged from the original submission," it does not provide the specific acceptance criteria or the reported performance metrics for these algorithms. It only broadly states that the data was "labeled and validated in advance by trained experts."

Therefore, I cannot fulfill your request for the detailed table and study information based solely on the provided text.

Here is a breakdown of what can be extracted or inferred, and what cannot:

What can be extracted/inferred:

• Sample size for the training set: 240 CT scans (from 240 patients).
• Sample size for the test set: 60 CT scans (20% of 300, derived from 300 total scans with 80% for training).
• Data provenance for training and test sets: CT scans from candidates for shoulder joint replacement surgery, acquired from 300 patients. The text doesn't explicitly state the country of origin but implies a single cohort. It's retrospective (pre-existing scans).
• How the ground truth for training and test sets was established: "labeled and validated in advance by trained experts."
• Type of ground truth used: Expert consensus on image segmentation and landmarking.
• Standalone performance: The mention of "AI-based automatic image segmentation and landmarking algorithms" being "unchanged" implies these algorithms have standalone performance characteristics, but the details are not provided.

What cannot be extracted from the provided text:

• A table of acceptance criteria and reported device performance: This crucial information is missing.
• Number of experts used to establish the ground truth: Not specified.
• Qualifications of those experts: Only "trained experts" is mentioned, no specific qualifications (e.g., radiologist with 10 years of experience).
• Adjudication method for the test set: Not specified (e.g., 2+1, 3+1, none).
• If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not mentioned.
• Effect size of human readers improving with AI vs. without AI assistance: Not mentioned.

In summary, the provided document describes the regulatory clearance process and confirms the device's substantial equivalence, but it does not detail the specific performance study results and acceptance criteria for the AI components. These details would typically be found in a more technical report submitted as part of the 510(k) submission, but not usually in the public-facing summary or clearance letter.

Ask a specific question about this device

ARVIS® Shoulder is indicated for assisting the surgeon in the positioning and alignment of implants relative to reference alignment axes and landmarks in stereotactic orthopedic surgery. The system aids the surgeon in making intraoperative measurements and locating anatomical structures of the shoulder joint based on the patient's preoperative imaging. ARVIS® Shoulder is indicated for total shoulder arthroplasty using the Enovis AltiVate implant system.

ARVIS® Shoulder is a computer-controlled surgical navigation system intended to provide intra-operative measurements to the surgeon to aid in selection and positioning of orthopedic implant components. The subject device is the equivalent shoulder system of the predicate ARVIS® Surgical Navigation System used for indicated knee and hip arthroplasties. ARVIS® Shoulder combines software, electronic hardware and surgical instruments to intraoperatively track tools and locate anatomical structures based on the patient's preoperative imaging. The navigation platform uses the same electronic hardware, mounted on the surgeon's head and waist, as the predicate device. A new equivalent navigation application and a new equivalent surgical instrument set are provided to allow surgeons to navigate instruments in shoulder arthroplasty procedures. The ARVIS® Shoulder workflow involves CT based reconstruction of the patient's shoulder anatomy and preoperative planning to enable image-based navigation. The surgeon uses the plan data as guidance to navigate and help position shoulder instruments and implants. The preoperative planning platform uses Al-based automatic image segmentation and landmarking algorithms. The data used to train and test the algorithms was labeled and validated in advance by trained experts. The total data consisted of 300 CT scans (from 300 patients) acquired from candidates for shoulder joint replacement surgery. The cohort was partitioned into two disjoint subsets through random sampling, with 80% producing a training dataset and 20% constituting the test dataset. The training dataset consisted of 240 CT scans (from 240 patients). Patient ages ranged from 36 to 89 years (mean age of 70), with 46% male and 54% female. All CT scans were acquired using FDA cleared CT scanners. The navigation system is intended to be used with the Enovis AltiVate implant system. ARVIS® Shoulder displays measurements as described in Performance Claims.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Device: ARVIS® Shoulder
Study Type: Validation of AI algorithms for automatic image segmentation and landmarking.

2. Sample Size and Data Provenance for Test Set

• Sample Size: 60 CT scans (from 60 unique patients)
• Data Provenance: The CT scans were acquired from patients who were candidates for shoulder joint replacement surgery. The scans were acquired using FDA cleared CT scanners (Toshiba, Siemens, Philips, GE Medical Systems, Canon). The specific country of origin is not specified.
• Retrospective/Prospective: The text describes the data as having been used to train and test algorithms, and the cohort was partitioned into disjoint subsets. This suggests the data was retrospective (collected prior to the study for the purpose of algorithm development and validation).

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Total of 3 experts.
  • 1 trained engineer
  • 2 orthopedic surgeons
• Qualifications:
  • Trained Engineer: More than 2 years' experience with medical image processing.
  • Orthopedic Surgeons: Subspecialty qualifications in upper limb surgery.

4. Adjudication Method for Test Set

The adjudication method described is: None (single review - approval).
The reference (ground-truth) label for each CT volume was obtained by a manual process, reviewed, and approved by the consensus of the trained engineer and the two orthopedic surgeons. This implies a single, agreed-upon ground truth rather than a process of resolving disagreements between multiple independent assessments.

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

There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being done to measure the effect of AI assistance on human readers. The validation focuses solely on the standalone performance of the AI algorithms against expert-established ground truth. Clinical testing was explicitly stated as "not required".

6. Standalone Performance Study

Yes, a standalone (algorithm only without human-in-the-loop performance) study was done.
The study compared the algorithm-generated outputs for segmentation (Dice Similarity Coefficient, Mean Absolute Distance, Hausdorff Distance) and landmarking (Euclidean Distance, Angular Separation, Successful Point and Angular Classification Rates) against manually established ground truth.

7. Type of Ground Truth Used

The ground truth used was expert consensus.
It was established through a manual process, reviewed, and approved by a trained engineer with medical image processing experience and two orthopedic surgeons with subspecialty qualifications in upper limb surgery.

8. Sample Size for Training Set

• Sample Size: 240 CT scans (from 240 unique patients)
• Total Data Pool: 300 CT scans (80% used for training, 20% for testing).

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

The text states that "The data used to train and test the algorithms was labelled and validated in advance by trained experts." While it details the process for the test set's ground truth, it implies a similar method was used for the training set's ground truth by "trained experts", without providing specific numbers or identical qualification details as for the test set. Given the context, it's reasonable to infer a process of expert labeling, likely by similar qualified individuals, but the exact expert composition for the training set ground truth isn't explicitly detailed with the same specificity as for the test set.

Ask a specific question about this device