(133 days)
Surgery Theater, LLC Surgery Rehearsal Platform is intended for use as a software interface and image segmentation system for the transfer of imaging information from CT or MR medical scanner to an output file. It is also intended as pre-operative software for simulating surgical treatment options.
The Surgery Rehearsal Platform (SRP) is software based medical image management system. It is intended for use as a software interface and image segmentation system. for the transfer of imaging information from a CT or MR medical scanner, to an output file. It is also intended as pre-operative software for simulation and evaluation of surgical treatment options.
The SRP software has the capability of creating 3D models of patient data from 2D scan slices. Additionally, it provides the user with ability to input, display, color, and manipulate the 2D scan slices via a 3D representation.
Here's an analysis of the acceptance criteria and study information for the Surgical Theater Surgery Rehearsal Platform (K123023) based on the provided text:
Important Note: This 510(k) summary primarily focuses on demonstrating substantial equivalence to a predicate device and does not involve a traditional clinical study with detailed performance metrics and ground truth establishment in the way typically seen for diagnostic AI/ML devices. The "acceptance criteria" here are essentially the requirements for demonstrating substantial equivalence and functional performance.
Acceptance Criteria and Reported Device Performance
| Acceptance Criteria / Performance Metric | Reported Device Performance |
|---|---|
| Intended Use | "Software interface and image segmentation system for the transfer of imaging information from CT or MR medical scanner to an output file. It is also intended as pre-operative software for simulating/evaluation surgical treatment options." (Matches predicate) |
| Technological Characteristics | - Computer: PC Workstation (Matches predicate) |
- Image Sources: CT and MRI (Matches predicate)
- Data Transfer Method: CD or USB (Matches predicate)
- Preoperative Planning: Yes (Matches predicate)
- Patient Contact: No (Matches predicate)
- Human Intervention for Interpretation of Images: Yes (Matches predicate)
- Capability of creating 3D models of patient data from 2D scan slices: Yes (Matches predicate)
- Provides the user with ability to input, display, color, and manipulate the 2D scan slices via a 3D representation: Yes (Matches predicate)
- Image tools such as rotation, scaling and coloring: Yes (Matches predicate) |
| Functional Verification | Design outputs met design input requirements (confirmed internally by Quality personnel). |
| Functional Validation (User Needs) | Met user needs and intended use (confirmed internally by Quality personnel, and subsequently by surgeons). |
| Risk Analysis Compliance | Performed in accordance with ISO 14971 (2007). Risk management file verification and validation conducted (desk audit and system testing). |
| Overall Safety and Effectiveness | Demonstrated to be "as safe and effective as its predicate device" based on matching indications for use, construction, operational principles, and performance test results. |
Study Information
-
Sample sizes used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated. The document mentions "documented software test procedures" and testing on "each supported system configuration (e.g. 2D vs. 3D Stereoscopic)." However, a specific number of cases or datasets used for testing is not provided.
- Data Provenance: Not specified. It's likely that synthetic or anonymized clinical data was used for functional testing, but this is not confirmed. The document does not mention the country of origin or whether the data was retrospective or prospective.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated for the test set's "ground truth."
- Qualifications of Experts: The document states that "the system was validated by surgeons to ensure the system meets end-user requirements." While these surgeons were involved in functional validation, their role in establishing a formal "ground truth" for specific medical findings is not described.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Adjudication Method: Not applicable or not described in the context of this submission. The validation involved internal quality personnel and surgeons assessing the system's functionality and meeting user needs, not typically a "ground truth" adjudication process for medical findings.
-
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:
- MRMC Study: No. This submission does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The device is for "pre-operative software for simulating/evaluation surgical treatment options," not primarily a diagnostic AI tool meant to improve human reader accuracy.
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Standalone Performance: The device itself is a standalone software, but its performance is measured against its functional requirements and substantial equivalence to a predicate, not against a specific diagnostic or clinical outcome metric. The "Human Intervention for Interpretation of Images" characteristic is listed as "Yes," indicating it is an assistive tool, not fully autonomous.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Type of Ground Truth: For the "test set" in the context of traditional AI evaluation, a formal ground truth (e.g., pathology, expert adjudicated labels) is not described. The "ground truth" for this device's validation appears to be adherence to design specifications and user requirements, as confirmed by internal quality personnel and surgeons.
-
The sample size for the training set:
- Training Set Sample Size: Not applicable. This document describes a software device that performs image segmentation and 3D modeling from existing CT/MR scans, and provides tools for simulation. It is not presented as an AI/ML device that requires a training set in the typical sense for learning patterns from labeled data to make predictions.
-
How the ground truth for the training set was established:
- Training Set Ground Truth: Not applicable, as no training set for an AI/ML model is described.
Summary of Approach:
The K123023 submission for the Surgical Theater Surgery Rehearsal Platform focuses on demonstrating substantial equivalence to an existing predicate device (Simbionix PROcedure Rehearsal Studio K112387). The "performance data" describes:
- Internal test plans and execution to confirm the device meets specified requirements (functional verification).
- Functional validation testing by quality personnel and surgeons to ensure the system meets user needs and intended use.
- Compliance with risk analysis standards (ISO 14971).
The validation activities ensure the device functions as intended and is comparable to the predicate. It explicitly states, "Test results confirmed that SRP is substantially equivalent to the predicate." This is a pre-AI/ML era submission, and therefore, the testing and validation criteria do not align with the typical "acceptance criteria" and "ground truth" definitions used for AI/ML diagnostic devices.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).