Search Results

The Medical Modeling VSP® System is intended for use as a software system and image segmentation system for the transfer of imaging information from a medical scanner such as CT based system. The is processed by the VSP® System and the result is an output data file that may then be provided as digital models or used as ingut to a rapid prototyping portion of the system that produces physical outputs including and surgical guides for use in maxillofacial surgery. The VSP® System is also intended as a pre-operative software tool for simulating surgical reatment options.

The Medical Modeling VSP® System is a collection of software and associated additive manufacturing (rapid prototyping) equipment intended to provide a variety of outputs to support orthognathic or reconstructive surgery. The system uses electronic medical images of the patient's anatomy with input from the physician, to manipulate original patient images for planning and executing surgery. The system manipulate enginal patient specific outputs including, anatomical models (physical and digital), surgical templates / guides, splints, and patient specific case reports.

Following the Medical Modeling Quality System and specific Work Instructions, trained employees utilize a combination of Commercial Off-The-Shelf (COTS) and trantom software to manipulate 3D medical scan images which can include Computed Tomography (CT), Cone Beam CT (CBCT), 3D scan images from patient physical models (stone models of the patient's teeth), and / or standard (non-bent) or priyered model implant files to create patient-specific physical and digital outputs. The process requires clinical input and review from the physician during planning and process telivery of the final outputs. While the process and data-flow can vary and phor to activery of the particular requirements of a given patient and physician, the following description outlines the functions of key sub-components of the system, following doben pour can be the defined system outputs. It should be noted that the system is operated only by trained Medical Modeling employees, and the the oyotan to open area the information. The physician only provides input for priysioian doos not anothy mactive feedback through viewing of digital models of model mempulation are modified by the engineer during the planning session.

The VSP® System is made up of 14 individual pieces of software and additional manufacturing equipment integrated to provide a range of anatomical models (physical and digital), surgical templates / guides and patient-specific case reports for (priyalour and digital), bargham, burgical region. Surgical guides for graft bone harvesting from patient bone such as, but not limited to, the fibula and hip, are also produced by the system.

The VSP® System requires an input 3D image file from medical imaging systems (i.e. CT) and / or a standard or patient contoured implant file. This input is then used, (i.e. ST) and from the prescribing physician to provide the following categories of with ourport reconstructive surgery. Each system output is designed with outpute to oupper roosiewed by the physician prior to finalization and distribution. priysician input, and foviotity direct physician involvement to reduce the criticality of the outputs.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Medical Modeling Inc. VSP® System:

This document describes a "Special 510(k) for Modified VSP® System," which focuses on verifying that a modified version of an already cleared device (the predicate device) is substantially equivalent to the original. Therefore, the study details are primarily about demonstrating equivalence rather than establishing entirely new performance criteria or efficacy for a novel device.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of specific, quantitative "acceptance criteria" for the VSP® System's performance in the way one might expect for diagnostic accuracy (e.g., sensitivity, specificity thresholds). Instead, the acceptance criteria are framed around demonstrating equivalence to the predicate device and conformity to specifications for the modifications introduced.

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

The document does not specify a distinct "test set" with a quantifiable sample size in terms of number of patients or cases. Instead, the testing appears to be focused on specific modifications and their impact.

• For Patient Contoured Implant Files: "The final output .STL files the cases designed using a patient contoured implant .STL file as input..." (Section 9.3). The text refers to "cases" (plural) but does not provide a specific number.
• For Software Updates: "Four (4) software components were upgraded". Tests were executed "for each software version upgrade." (Section 9.4.1.1). The direct sample size of test cases for these software validations is not detailed.
• For Additional SLA: "An additional SLA model and associated wash tanks have been added..." (Section 9.4.1.2). The testing here (IQ, OQ, PQ, Software Validation) is for the hardware and its integration, not a patient-case-based test set.

Data Provenance: Not explicitly stated, though the context implies internal testing by Medical Modeling Inc. The document does not mention external data, country of origin of data, or if it was retrospective or prospective in the sense of a clinical trial. It describes a "process validation" (Section 9.2) focused on a "worst-case patient contoured implant file" and subsequent digital file outputs that met requirements.

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

• For Patient Contoured Implant Files: "The reconstructive surgeon approved both design..." (Section 9.3). This indicates one expert, identified as "the reconstructive surgeon." The specific qualifications (e.g., years of experience) are not provided beyond the title "reconstructive surgeon."

4. Adjudication Method for the Test Set

• For Patient Contoured Implant Files: The document states, "The reconstructive surgeon approved both design." This suggests a single expert's approval was sufficient, implying no formal adjudication method (e.g., 2+1 or 3+1 consensus) among multiple experts was necessary for this specific part of the testing. The "clinical input and review from the physician during planning and processing" (Section 7.2) and "reviewed by the physician prior to finalization and distribution" (Section 7.4) of system outputs also points to individual physician review.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not done. This submission is for a special 510(k) for a modified Virtual Surgical Planning (VSP) system, where the modifications primarily relate to input file types (patient contoured implant files) and internal manufacturing/software processes. The device itself is a software system for surgical planning and creating physical guides/models, not a diagnostic AI system meant to assist human readers in interpretation. The goal was substantial equivalence, not improved human reader performance with AI.

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

The VSP® System is itself a software component, so in a sense, its underlying algorithms operate in a "standalone" fashion to process inputs and generate outputs. However, the system is explicitly designed with "human-in-the-loop" aspects:

• "The process requires clinical input and review from the physician during planning and delivery of the final outputs." (Section 7.2)
• "The system is operated only by trained Medical Modeling employees, and the physician only provides input for interactive feedback through viewing of digital models... models are modified by the engineer during the planning session." (Section 7.2)
• "Each system output is designed with physician input, and direct physician involvement to reduce the criticality of the outputs." (Section 7.4)

So, while the software performs its functions without direct human intervention at every step of its internal computations, the overall device workflow is inherently human-("clinician and trained employee")-in-the-loop, with outputs subject to expert review and approval. The testing described (e.g., "clinical and/or dimensional equivalency," "reconstructive surgeon approved") assesses the output of the system in the context of its intended use, which includes human oversight.

7. The Type of Ground Truth Used

The ground truth for the "patient contoured implant file" modification was based on:

• Expert Consensus/Approval: "The reconstructive surgeon approved both design, which indicated that there is no clinically significant difference..." (Section 9.3). This relies on the expert judgment of a reconstructive surgeon.
• Dimensional Equivalency: The comparison also sought "dimensional equivalency" (Section 9.3), implying quantitative measurements were involved, compared against established specifications or direct comparison of the designs.

For other internal modifications (software, hardware), the ground truth was conformity to "pre-established specifications and acceptance criteria" (Section 9.5) as demonstrated through standard qualification processes (IQ, OQ, PQ, software validation).

8. The Sample Size for the Training Set

The document does not specify a training set sample size. The VSP® System is not described as a machine learning or AI system that undergoes "training" in the conventional sense (i.e., learning from large datasets to develop an algorithm). It's a system that utilizes a combination of Commercial Off-The-Shelf (COTS) and custom software to manipulate 3D medical scan images based on predefined algorithms and engineering principles (Section 7.2). The modifications described are related to inputs, software updates, and manufacturing hardware, not algorithm retraining.

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

As no training set is described (see point 8), the concept of establishing ground truth for a training set is not applicable to this submission.

Ask a specific question about this device

The Medical Modeling VSP® System is intended for use as a software system and image segmentation system for the transfer of imaging information from a medical scanner such as a CT based system. The input data file is processed by the VSP® System and the result is an output data file that may then be provided as digital models or used as input to a rapid prototyping portion of the system that produces physical outputs including anatomical models, templates, and surgical guides for use in maxillofacial surgery. The VSP® System is also intended as a pre-operative software tool for simulating / evaluating surgical treatment options.

The Medical Modeling VSP® System is a collection of software and associated additive manufacturing (rapid prototyping) equipment intended to provide a variety of outputs to support reconstructive surgery. The system uses electronic medical images of the patients' anatomy with input from the physician, to manipulate original patient images for planning and executing surgery. The system produces a variety of patient specific outputs including; anatomical models (physical and digital), surgical templates / guides, splints, and patient specific case reports.

Following the Medical Modeling Quality System and specific Work Instructions, trained employees utilize a combination of Commercial Off-The-Shelf (COTS) and custom software to manipulate 3-D medical scan images which can include Computed Tomography (CT), Cone Beam CT (CBCT), and/or 3-D scan images from patient physical models (stone models of the patient's teeth) to create patient-specific physical and digital outputs. The process requires clinical input and review from the physician during planning and prior to delivery of the final outputs. While the process and dataflow vary somewhat based on the particular requirements of a given patient and physician, the following description outlines the functions of key sub-components of the system, and how they interact to produce the defined system outputs. It should be noted that the system is operated only by trained Medical Modeling employees, and the physician does not directly input information. The physician provides input for model manipulation and interactive feedback through viewing of digital models of system outputs that are modified by the engineer during the planning session.

The VSP® System is made up of 13 individual pieces of software and 9 pieces of manufacturing equipment integrated to provide a range of anatomical models (physical and digital), surgical guides, and patient specific planning reports for reconstructive surgery in the maxillofacial region. Surgical guides for graft bone harvesting which can include the fibula and hip are also produced by the system.

The VSP® System requires an input 3-D image file from medical imaging systems (i.e. CT). This input is then used, with support from the prescribing physician to provide the following potential outputs to support reconstructive surgery. Each system output is designed with physician input, and reviewed by the physician prior to finalization. All outputs are used only with direct physician involvement reducing the criticality of the outputs.

System Outputs:
Anatomical Models
Surgical Positioning Templates / Guides
Osteotomy Templates / Guides
Plate Bending Templates/Guides
Patient Specific Case Reports

The VSP® System also contains a set of Stainless Steel Cutting and Drill Inserts (VSP® System Accessories) which are intended to be used by the physician to guide cutting and drilling activities during the surgical procedure. The inserts fit into a standard slot/hole in the cutting/drill guides, and can be used across all the VSP® System guides and templates.

The Medical Modeling VSP® System is a collection of software and associated additive manufacturing (rapid prototyping) equipment intended to provide a variety of outputs to support reconstructive surgery. The system uses electronic medical images of the patients' anatomy with input from the physician, to manipulate original patient images for planning and executing surgery.

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

Acceptance Criteria and Reported Device Performance

The provided document describes a 510(k) submission for a medical device and outlines various verification and validation testing performed. However, it does not explicitly state a table of specific acceptance criteria with quantifiable metrics (e.g., "accuracy must be > 95%") alongside reported device performance for the VSP® System.

Instead, the document details a comprehensive set of engineering and process validation activities. The general acceptance criterion is implicit: "All, Design, Process, and Other Verification and Validation Testing, which was required as a result of risk analysis and design impact assessments, showed conformity with pre-established specifications and acceptance criteria." This implies that individual test plans for each category would have contained the specific acceptance criteria.

The study proves the device meets the acceptance criteria through a series of "Verification and Validation testing" categories. The overarching goal was to demonstrate that "the manufacturing process could correctly translate 3 dimensional electronic models of patient anatomies, templates and guides into matching physical models within the allowed tolerance ranges from the process specifications."

Given the lack of a direct table in the provided text, I will infer the categories of performance testing as "acceptance criteria" through successful completion, and "reported device performance" as the successful demonstration against these criteria.

Additional Information on the Study:

1. Sample size used for the test set and the data provenance:
   The document does not specify a distinct "test set" sample size in terms of patient cases or imaging data. The testing described is focused on the manufacturing process and the system's ability to translate 3D electronic models into physical models within tolerance. Therefore, the "sample" for testing would likely refer to the number of physical models, guides, or templates produced and evaluated during OQ, PQ, and Simulated Use. These details are not provided in the summary.
   Data provenance (e.g., country of origin, retrospective/prospective) is not mentioned, as the focus is on system functionality rather than clinical performance on a patient cohort for this type of device (a system for creating models and guides).

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
   The document states that "The process requires clinical input and review from the physician during planning and prior to delivery of the final outputs." and "All outputs are used only with direct physician involvement reducing the criticality of the outputs." This indicates that physicians are key domain experts providing input and review. However, the specific number of experts used for establishing "ground truth" during validation testing (e.g., for evaluating the accuracy of physical models against digital plans) and their qualifications are not detailed. It can be inferred that "trained Medical Modeling employees" (engineers/CAD specialists) operate the system, and physicians provide clinical feedback.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
   The document does not specify any formal adjudication method like "2+1" or "3+1" for establishing ground truth or evaluating the test set results. The process involves physician input and review, but a formal adjudication process for test results is not detailed in this summary.

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:
   No MRMC study was conducted or reported. The VSP® System is a tool for planning and manufacturing patient-specific devices, not an AI-assisted diagnostic or interpretation system that would involve "human readers" in the typical sense of an MRMC study. There is no mention of "AI assistance" in this context.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
   The system is explicitly described as having "human-in-the-loop" performance. "The system is operated only by trained Medical Modeling employees, and the physician does not directly input information. The physician provides input for model manipulation and interactive feedback through viewing of digital models of system outputs that are modified by the engineer during the planning session." Therefore, no standalone (algorithm only) performance was presented or is applicable to the intended use.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
   For mechanical and dimensional testing (OQ, PQ), the ground truth for physical models would be established by comparing them to the digital models/plans generated by the system, referencing "allowed tolerance ranges from the process specifications." This essentially uses the digitally designed model as the 'truth' against which the manufactured physical output is measured. For "Simulated Use (Planning Session)," the ground truth would likely be based on expert (physician) review and acceptance of the surgical plan and resulting outputs as clinically appropriate and accurate based on the patient's anatomy.

7. The sample size for the training set:
   The document does not describe a "training set" in the context of machine learning or AI, as this system is not presented as an AI-driven device. It is a software system for image transfer, segmentation, and pre-operative planning, utilizing COTS and custom software operated by trained personnel. Therefore, the concept of a "training set" for an algorithm is not applicable here.

8. How the ground truth for the training set was established:
   As there is no mention of an algorithm training set, this question is not applicable. The software within the VSP® system undergoes standard software validation (9.3.4), where its performance against defined requirements and interfaces (likely functional specifications) would be the "ground truth."

Ask a specific question about this device