(70 days)
VEA Align:
This cloud-based software is intended for orthopedic applications in both pediatric and adult populations.
2D X-ray images acquired in EOS imaging's imaging systems is the foundation and resource to display the interactive landmarks overlayed on the frontal and lateral images. These landmarks are available for users to assess patient-specific global alignment.
For additional assessment, alignment parameters compared to published normative values may be available.
This product serves as a tool to aid in the analysis of spinal deformities and degenerative diseases, and lower limb alignment disorders and deformities through precise angle and length measurements. It is suitable for use with adult and pediatric patients aged 7 years and older.
Clinical judgment and experience are required to properly use the software.
spineEOS:
spineEOS is indicated for assisting healthcare professionals with preoperative planning of spine surgeries. The product provides access to EOS images with associated 3D datasets and measurements. spineEOS includes surgical planning tools that enable users to define a patient specific surgical strategy.
VEA Align:
VEA Align is a software indicated for assisting healthcare professionals with global alignment assessment through clinical parameters computation.
The product uses biplanar 2D X-ray images, exclusively generated by EOS imaging's EOS (K152788) and EOSedge (K202394) systems and generates an initial placement of the patient anatomic landmarks on the images using a machine learning-based algorithm. The user may adjust the landmarks to align with the patient's anatomy. Landmark locations require user validation. The clinical parameters communicated to the user are inferred from the landmarks and are recalculated as the user adjusts the landmarks. 3D datasets may be exported for use in spineEOS for surgical planning.
The product is hosted on a cloud infrastructure and relies on EOS Insight for support capabilities, such as user access control and data access. 2D X-ray image transmissions from healthcare institutions to the cloud are managed by EOS Insight. EOS Insight is classified as non-device Clinical Decision Support (CDS) software.
spineEOS:
spineEOS is indicated for assisting healthcare professionals with preoperative planning of spine surgeries. spineEOS provides access to EOS images with associated 3D datasets and measurements. spineEOS includes surgical planning tools that enable users to define a patient specific surgical strategy.
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for VEA Align.
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria | Reported Device Performance (Implicitly Met) |
|---|---|---|
| Median Error | ≤ 3 mm | Met (All studies performed indicate acceptable performances) |
| 3rd Quartile Error | ≤ 5 mm | Met (All studies performed indicate acceptable performances) |
Note: The document states that "All the studies performed indicate acceptable performances of the algorithm for its intended population," implying that both acceptance criteria (Median error ≤ 3mm and 3rd Quartile ≤ 5mm) were met. Actual reported numerical values for the performance metrics are not explicitly provided in this document, only that the criteria were met.
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 361 patients.
- Data Provenance: Images were collected from EOS (K152788) and EOSedge (K202394) systems at a variety of sites from 2007-2023. The subgroups analysis includes "Data site location - Different US states," indicating that at least some of the data originates from the US. The document does not explicitly state whether the data was retrospective or prospective, but given the collection period (2007-2023), it is likely retrospective.
3. Number of Experts Used to Establish Ground Truth and Qualifications
- The document states that the ground truth was established by "EOS 3DServices reconstruction (model) from sterEOS (K172346)." This implies that the ground truth is derived from a previously cleared and validated 3D reconstruction system.
- The number and qualifications of experts involved in creating these "EOS 3DServices reconstruction" models are not specified in this document.
4. Adjudication Method for the Test Set
- The document does not describe an explicit adjudication method for the test set involving multiple human reviewers. The ground truth for the test set is established by the "EOS 3DServices reconstruction (model) from sterEOS."
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- A formal MRMC comparative effectiveness study comparing human readers with and without AI assistance is not explicitly mentioned in this document. The performance evaluation is focused on the standalone AI algorithm compared to ground truth.
6. Standalone (Algorithm Only) Performance Study
- Yes, a standalone (algorithm only) performance study was done.
- Description: "To assess the standalone performance of the AI algorithm of the VEA Align, the test was performed with:
- A dedicated test data set containing different data from the training data set...
- For each patient of this data set, a ground truth EOS 3DServices reconstruction (model) from sterEOS (K172346) that was available for comparison with VEA Align reconstruction generated by the AI algorithm."
- This confirms that the study focused on the AI algorithm's performance without direct human intervention in the loop for the performance metrics measured.
- Description: "To assess the standalone performance of the AI algorithm of the VEA Align, the test was performed with:
7. Type of Ground Truth Used
- The ground truth used for the test set was based on "EOS 3DServices reconstruction (model) from sterEOS (K172346)." This refers to 3D anatomical models and landmark placements generated by a previously cleared medical imaging and reconstruction system (sterEOS). This can be categorized as a type of expert-system-derived ground truth, as sterEOS itself relies on validated methodologies and presumably expert input/validation in its operation.
8. Sample Size for the Training Set
- Training Set Sample Size: 10,376 X-ray images, with a total of 5,188 corresponding 3D reconstructions.
9. How the Ground Truth for the Training Set Was Established
- The document states, "The AI algorithm was trained using 10,376 X-ray images and a total of 5,188 corresponding 3D reconstructions." It also notes that the images were collected from EOS and EOSedge systems. While it doesn't explicitly detail the method for establishing the ground truth for each training image, the context implies that these 3D reconstructions served as the ground truth. Similar to the test set, it's highly probable these "corresponding 3D reconstructions" were also derived from the established and validated EOS 3DServices/sterEOS pipeline.
§ 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).