Search Results

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

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.

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.

Ask a specific question about this device

EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, angiography, and mammography.

EOSedge allows the radiographic acquisition of either one or two orthogonal X-ray images, for diagnostic purposes, in one single scan of the whole body or a reduced area of investigation of a patient, in the upright or seated position. The Micro Dose feature is indicated for assessing global skeletal deformities in follow-up pediatric exams.

The EOSedge™ system is a digital radiography system comprised of an acquisition workstation, a gantry including an electrical cabinet housing the system power and communication controls, and an acquisition software to obtain diagnostic images. Two sets of detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. If desired, the Micro Dose feature enables image acquisition for assessing global skeletal deformities in pediatric follow-up exams.

The diagnostic images are stored in a local database and are displayed on a high-resolution medical-quality non-diagnostic monitor. The diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.

The provided text outlines the substantial equivalence of the EOSedge device to its predicate, rather than detailing a specific clinical study with AI assistance demonstrating performance against acceptance criteria for an AI/ML powered device. The document describes changes to an existing, cleared device (EOSedge, K202394), primarily the activation of a dual-energy detection mode within already integrated detectors.

Therefore, the information required to fully answer the question regarding acceptance criteria and a study proving a device meets these criteria for an AI/ML powered device is largely not present in the provided text. The document focuses on showing the modified EOSedge is substantially equivalent to the cleared EOSedge system, implying that the previous clearances and tests are sufficient.

However, based on the provided text, I can infer and extract some relevant (though limited) information regarding performance testing that aligns with aspects of an AI/ML device, particularly concerning image quality and software:

Acceptance Criteria and Reported Device Performance (Inferred from "Performance Data" and "Technological Characteristics" sections):

• No specific acceptance criteria for AI/ML performance metrics (e.g., sensitivity, specificity, AUC) are stated. The performance data section focuses on general device standards and image quality.
• The document does not detail specific "reported device performance" in terms of clinical accuracy or an AI model's output metrics. It states that the device "performs according to specifications and is as safe and effective as the predicate device."

Here's a table synthesizing the types of performance criteria and the general statement of performance, as can be extracted from the document:

Since the document is a 510(k) summary focused on demonstrating substantial equivalence of a modified X-ray system, it does not contain the detailed information typically found in a clinical study report for an AI/ML-powered diagnostic device.

Missing Information (for an AI/ML powered device, based on the provided text):

1. Sample sizes used for the test set and data provenance: Not explicitly stated for any clinical performance evaluation of an AI component. The document mentions "bench testing."
2. Number of experts used to establish ground truth & qualifications: Not applicable/not stated, as no clinical ground truth establishment for AI performance is described.
3. Adjudication method for the test set: Not applicable/not stated.
4. MRMC comparative effectiveness study: Not mentioned. The document is for an imaging system, not an AI assistance tool for human readers.
5. Standalone (algorithm only) performance: Not mentioned, as it's a hardware system with software, not a pure AI algorithm.
6. Type of ground truth used: Not applicable/not stated for an AI/ML performance evaluation. Only "bench testing" is mentioned.
7. Sample size for the training set: Not applicable; no AI training set is mentioned.
8. How ground truth for the training set was established: Not applicable; no AI training set is mentioned.

In conclusion, the provided text is a regulatory filing for an X-ray imaging system (EOSedge) demonstrating substantial equivalence to a predicate device, focusing on hardware and software modifications. It does not describe an AI/ML device, nor does it present clinical study data for AI performance against defined acceptance criteria. The "Performance Data" section primarily addresses compliance with general X-ray system standards (IEC 60601-1, IEC 62220-1-1) and software verification/validation, concluding that the modified device is as safe and effective as its predecessor.

Ask a specific question about this device

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 mages. 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 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 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 VEA Portal 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 VEA Portal is a Class | 510(k)-exempt device (LMD).

spineEOS is a software indicated for assisting healthcare professionals with preoperative planning of spine surgeries. EOS images (generated from EOS imaging's acquisition system) and associated 3D datasets are used as inputs of the software. The product manages clinical measurements and allows user to access surgical planning tools to define a patient specific surgical strategy. The product is indicated for adolescent and adult patients.

The provided text describes the performance data for the VEA Align device, focusing on the standalone performance of its AI algorithm.

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

1. A table of acceptance criteria and the reported device performance

2. Sample size used for the test set and the data provenance

• Test set sample size: 538 patients.
• Data provenance: Not explicitly stated as country of origin, but the images were collected from EOS (K152788) and EOSedge (K202394) systems at a variety of sites. The subgroup analysis includes "US vs. OUS" (Outside US), implying international data. The data collection period was from 2007-2023. The study seems to be retrospective as it uses previously collected images.

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

The document states that the ground truth for the test set was an "EOS 3DServices reconstruction (model) from sterEOS Workstation (K172346)". It does not explicitly state the number or qualifications of experts used to establish this ground truth for the test set. However, the nature of the sterEOS Workstation suggests that these 3D reconstructions are typically performed or validated by trained specialists.

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

The document does not specify an adjudication method for the test set ground truth. It relies on the "ground truth EOS 3DServices reconstruction (model) from sterEOS Workstation (K172346)."

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 described where human readers' improvement with AI vs. without AI assistance was evaluated. The performance testing focused on the standalone performance of the AI algorithm. The VEA Align device involves a machine learning-based algorithm for initial landmark placement, but then explicitly states, "The user may adjust the landmarks to align with the patient's anatomy. Landmark locations require user validation." This implies a human-in-the-loop system, but the described performance study is primarily on the algorithm's initial accuracy, not human improvement.

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

Yes, a standalone performance test of the AI algorithm was done. The document explicitly states: "To assess the standalone performance of the Al algorithm of the VEA Align, the test was performed with..."

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

The ground truth used for the standalone algorithm performance was "a ground truth EOS 3DServices reconstruction (model) from sterEOS Workstation (K172346)". This suggests a reconstructed anatomical model derived from clinically used software, likely validated by trained operators or experts who generated that model previously.

8. The sample size for the training set

The AI algorithm was trained using 10,376 X-ray images and a total of 5,188 corresponding 3D reconstructions.

9. How the ground truth for the training set was established

The document states that the training data included "corresponding 3D reconstructions" presumably generated by sterEOS Workstation (K172346), similar to the test set ground truth. These 3D reconstructions would have been based on images from EOS systems and likely performed by trained personnel using the sterEOS Workstation. It's implied that these served as the ground truth for training the AI algorithm to generate its initial placements.

Ask a specific question about this device

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, degenerative diseases, 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.

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. The product is hosted on a cloud infrastructure and relies on VEA Portal 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 VEA Portal is a Class I 510(k)-exempt device (LMD).

The provided text describes the VEA Align device and its performance testing to support its substantial equivalence to a predicate device. However, it does not contain a detailed table of acceptance criteria with reported device performance metrics that would typically be found in a comprehensive study report. It states that "Direct comparison between skeletal landmark locations between the subject VEA Align device and predicate sterEOS Workstation (K172346) met acceptance criteria for algorithm performance," but it does not quantify these criteria or the specific performance results.

Therefore, some of the requested information cannot be directly extracted from the provided text. I will provide what is available and note what is missing.

Here's the breakdown of the information:

1. Table of Acceptance Criteria and Reported Device Performance

The document states: "Direct comparison between skeletal landmark locations between the subject VEA Align device and predicate sterEOS Workstation (K172346) met acceptance criteria for algorithm performance." However, the specific quantitative acceptance criteria (e.g., maximum allowable error for landmark placement) and the actual numerical performance results (e.g., mean absolute error) are not provided in this text.

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

• Test Set Sample Size: 555 patients.
• Data Provenance: The images were acquired from "EOS (K152788) and EOSedge (K202394) systems." The country of origin and whether the data was retrospective or prospective are not explicitly stated.

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

This information is not provided in the text. The document refers to the predicate device manually deforming a 3D model through control points to match X-ray contours, which implies expert interaction in the past, but it does not describe how ground truth was established for the 555-patient test set for the VEA Align device.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

This information is not provided in the text.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs. without AI assistance.

A MRMC comparative effectiveness study involving human readers with and without AI assistance is not mentioned in the provided text. The performance testing focuses on the standalone algorithm's comparison to the predicate device.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:

Yes, a standalone performance assessment was done. The text states:
"Standalone performance assessment of the machine learning algorithm. The testing dataset consisted of 555 patients... Direct comparison between skeletal landmark locations between the subject VEA Align device and predicate sterEOS Workstation (K172346) met acceptance criteria for algorithm performance."

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

The ground truth for the standalone performance assessment appears to be based on the "skeletal landmark locations" derived from the predicate sterEOS Workstation (K172346). This implies that the predicate's output, which involved manual deformation by users ("The 3D model is deformed manually by the user through control points up to matching accurately the X-ray contours. This deformation is performed by using the common linear least squares estimation algorithm."), served as the reference for the VEA Align's automated landmark placement. It is not explicitly stated that an independent expert consensus or pathology was used directly for the 555-patient test set for the standalone evaluation of VEA Align, but rather conformance to the predicate's output.

8. The Sample Size for the Training Set

The sample size for the training set is not explicitly stated in the provided text. It mentions that the machine learning algorithm was "trained from data generated by EOS Imaging's imaging systems", but it doesn't quantify the size of this training dataset.

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

The text states that the machine learning algorithm learns to generate "an initial placement of the patient anatomic landmarks on the images" and that "The user may adjust the landmarks to align with the patient's anatomy." For the predicate device, it mentions "identification of anatomical landmarks" or "a model of bone structures derived from an a priori image data set from 175 patients (91 normal patients, 47 patients with moderate idiopathic scoliosis and 37 patients with severe idiopathic scoliosis), and dry isolated vertebrae data for spine modeling."

While it implies that human interaction and potentially pre-existing models established the ground truth used for training, the specific methodology and who established the ground truth labels for the VEA Align training set are not detailed. It implies the machine learning was "trained from data generated by EOS Imaging's imaging systems," which suggests leveraging existing data from their systems and prior approaches (potentially like the predicate).

Ask a specific question about this device

spineEOS software 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.

spineEOS is a software indicated for assisting healthcare professionals with preoperative planning of spine surgeries. EOS images (generated from EOS imaging's acquisition system) and associated 3D datasets are used as inputs of the software. The product manages clinical measurements and allows user to access surgical planning tools to define a patient specific surgical strategy. The product is indicated for adolescent and adult patients.

The provided document is a 510(k) premarket notification for the device spineEOS. It primarily focuses on demonstrating substantial equivalence to a predicate device (K160407 spineEOS) rather than detailing a clinical study with acceptance criteria and performance data for a novel AI/ML-based device.

Therefore, the document does not contain the detailed information required to fully answer the request, specifically relating to a study proving the device meets acceptance criteria for new or modified AI/ML features. The information regarding performance data (Section 7) states that "Nonclinical performance testing performed on the subject device, spineEOS, supports substantial equivalence to the predicate device" and explicitly, "Determination of substantial equivalence is not based on an assessment of clinical performance data."

However, based on the provided text, I can extract information relevant to the comparison for substantial equivalence as presented, and highlight what is missing for a comprehensive answer on acceptance criteria and a study proving performance for a new AI/ML feature.

Here's an attempt to answer the questions based on the available information, noting where data is absent:

1. A table of acceptance criteria and the reported device performance

The document does not provide a table of acceptance criteria for specific performance metrics of a new AI/ML model. Instead, it presents a comparison for substantial equivalence between the modified spineEOS and its predicate (K160407 spineEOS). This comparison focuses on demonstrating that technological differences do not affect safety or effectiveness, not on proving a specific quantitative performance metric against a set acceptance criterion for a novel feature.

Here's a re-interpretation of "acceptance criteria" based on the "Substantially Equivalent?" column in Table 5-1, which represents the justification for equivalence rather than quantitative performance.

2. Sample size used for the test set and the data provenance

The document states "Nonclinical performance testing performed on the subject device, spineEOS, supports substantial equivalence to the predicate device." It also mentions "Validation activities" including "Validation of the multifunctional requirements in terms of design" and "Usability testing".

• Sample Size for Test Set: This information is not provided. The document makes no mention of a specific dataset size for evaluating the performance of the claimed features, especially for any new AI/ML components. Given the "nonclinical performance" and "not based on clinical performance data" statements, it's highly likely that a traditional "test set" in the context of an AI/ML study (i.e., a set of patient cases to evaluate algorithm performance) was not part of this 510(k) submission.
• Data Provenance: This information is not provided. (e.g., country of origin, retrospective or prospective).

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

This information is not provided. Since the submission states "Determination of substantial equivalence is not based on an assessment of clinical performance data," it's unlikely that such an expert-adjudicated ground truth dataset, typical for AI/ML device evaluations, was used. The focus was on demonstrating that the modified features (like the new Spondylolisthesis tool) function as intended and do not introduce new safety concerns compared to the predicate, rather than on proving diagnostic or measurement accuracy against a gold standard.

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

This information is not provided.

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, an MRMC comparative effectiveness study was not done. The document explicitly states: "Determination of substantial equivalence is not based on an assessment of clinical performance data." The core of this 510(k) is demonstrating substantial equivalence based on technological comparisons and nonclinical performance (e.g., software verification and validation activities), not an MRMC study.

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

This information is not explicitly provided. The document mentions "Validation of the multifunctional requirements in terms of design" and "Usability testing." The product, spineEOS, is presented as a tool "assisting healthcare professionals," implying a human-in-the-loop model for its primary use ("clinical judgment and experience are required to properly use the software"). There's no separate mention of a "standalone" algorithm-only performance evaluation, especially one related to diagnostic accuracy without human input.

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

Since the submission states it's not based on clinical performance data and focuses on substantial equivalence via nonclinical V&V, the concept of "ground truth" in the context of clinical accuracy (e.g., expert consensus, pathology) for performance claims is not applicable or provided. The "ground truth" for the V&V activities would be the design specifications and requirements.

8. The sample size for the training set

This information is not provided. The document does not describe the specific AI/ML algorithms used or their training. The changes highlighted (like the new Spondylolisthesis tool) are additions to existing functionality, and the filing focuses on their technological equivalence and safety, not on a new AI/ML model requiring a training dataset.

9. How the ground truth for the training set was established

This information is not provided, as there is no mention of a training set for an AI/ML model for this submission.

Summary of what the document does provide regarding performance and validation:

• Nonclinical performance testing: This includes design input review, unit testing, software integration, system integration, validation of multifunctional requirements in terms of design, and usability testing.
• Safety & Effectiveness Argument: The core argument is that the modified device, including new tools like "Spondylolisthesis" and "Rod Curvature Management," operates on principles similar to existing cleared functionalities (e.g., segmental alignment tool), and therefore does not raise new questions of safety or effectiveness.
• No Clinical Performance Data: The submission explicitly states that "Determination of substantial equivalence is not based on an assessment of clinical performance data." This significantly limits the type of "acceptance criteria" and "study" information available, as it implies a focus on V&V of software functionality and comparison to predicate rather than a clinical trial proving new performance claims.

Ask a specific question about this device

EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, and mammography. EOSedge allows the radiographic acquisition of either one or two orthogonal X-ray images, for diagnostic purposes, in one single scan, of the whole body or a reduced area of investigation of a patient, in the upright or seated position.

The Micro Dose feature is indicated for assessing global skeletal deformities in follow-up pediatric exams.

The EOSedge system is a digital radiography system comprised of an acquisition workstation, a gantry including an electrical cabinet housing the system power and communication controls, and an acquisition software to obtain diagnostic images. Two identical sets of detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. If desired, the Micro Dose feature enables image acquisition for assessing global skeletal deformities in follow-up pediatric exams. The two sets of detectors and X-ray tubes are identical between the predicate device and the subject device. The image acquisition can be performed with a MANUAL mode or an AUTO mode of patient examination. To select the area of interest (acquisition area), a vertical collimation is set using green lasers and to correctly position the patient in the EOSedge, a centering system is used based on red lasers. The diagnostic images are stored in a local database and are displayed on a high-resolution medical-quality non-diagnostic monitor. The diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.

The provided text describes a 510(k) premarket notification for the EOSedge™ system, an updated digital radiography system. The document focuses on demonstrating that the updated device is substantially equivalent to a previously cleared predicate device (EOS imaging's EOSedge System K192079).

Based on the provided text, the acceptance criteria and study proving the device meets these criteria are primarily based on bench testing and comparative analysis with a predicate device, rather than a clinical study evaluating diagnostic performance.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly tied to demonstrating substantial equivalence to the predicate device, implying that the updated device must perform at least as safely and effectively. The performance data section refers to conformity to various IEC standards and internal functional testing.

• Quantity: 2
• Type: Hybrid CdTe-CMOS dual energy photons counting X-ray detector
• Dimensions: Width 585 mm x 98 mm, Thickness 131 mm
• Weight: 131 000 gray levels)
• Nominal input voltage: 12 VDC – 20 A
• Temperature control: Internal check, Peltier + PWM, Ventilator system checked
• DQE type: RQA5 spectrum ~ 80%
• MTF type: ~70% @ 2lp / mm, ~25% @ 5lp / mm
• Pixel Depth: 17 bits (> 131 000 grey levels)
• Pixel Size: 100 µm
• Resolution: 3.7 lp/mm
• Typical Dynamic Range: > 100 dB |
  | Average Acquisition Time | Must be comparable or improved compared to predicate. | Current Device (EOSedge™): 7 seconds for a spine and 13 seconds for an entire body
  Predicate Device (EOSedge System K192079): 8 seconds for a spine and 15 seconds for an entire body (Improved performance stated for current device) |

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

The document does not describe a clinical test set with patient data for evaluating diagnostic performance. The testing described is primarily bench testing and software verification/validation. Therefore, there are no details on sample size for a test set of patient images or their provenance (country of origin, retrospective/prospective). The assessment is based on technical specifications and comparison to the predicate device.

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

As there is no clinical test set for diagnostic performance described, there is no information on experts establishing ground truth for such a set. The ground truth for the engineering/technical tests would be the established specifications and accepted performance metrics for medical imaging devices, as defined by relevant IEC and FDA guidance.

4. Adjudication Method for the Test Set

Not applicable, as no clinical test set requiring expert adjudication is described in the provided text.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not explicitly done or described in the provided text. The submission focuses on demonstrating substantial equivalence through technical performance data and comparison to a predicate device, not on improved human reader performance with AI assistance. The device itself is an X-ray imaging system, not an AI diagnostic assistant.

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

Not explicitly applicable in the context of an X-ray imaging system. The performance evaluated here is the image acquisition and processing capabilities of the X-ray device itself, which operates as a standalone system to produce images for human interpretation.

7. The Type of Ground Truth Used

The ground truth used for these tests is based on established engineering and performance standards for X-ray imaging devices (e.g., IEC standards, FDA guidance for solid-state X-ray imaging devices). For comparative purposes, the predicate device's cleared performance serves as a benchmark for substantial equivalence.

8. The Sample Size for the Training Set

Not applicable. The document describes a medical imaging device (hardware and software for image acquisition), not a machine learning algorithm that requires a training set of data for inference.

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

Not applicable, as there is no training set for a machine learning algorithm described.

Ask a specific question about this device

EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, angiography, and mammography. EOSedge allows the radiographic acquisition of either one or two orthogonal X-ray images, for diagnostic purposes, in one single body or a reduced area of investigation of a patient, in the upright or seated position.

The Micro Dose feature is indicated for assessing global skeletal deformities in follow-up pediatric exams.

The EOSedge system is a digital radiography system comprised of an acquisition workstation, a gantry including an electrical cabinet housing the system power and communication controls, and an acquisition software to obtain diagnostic images. Two sets of detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. If desired, the Micro Dose feature enables image acquisition for assessing global skeletal deformities in follow-up exams. The diagnostic images are stored in a local database and are displayed on a highresolution medical-quality non-diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.

The provided text is a 510(k) summary for the EOS imaging's EOSedge System. It describes the device, its intended use, and compares it to a predicate device (EOS System K152788) to demonstrate substantial equivalence.

However, the document does not contain information about acceptance criteria for an AI/algorithm's performance, nor does it describe a study that proves a device meets such criteria. It focuses on the substantial equivalence of an X-ray imaging system to its predecessor, based on design, technical specifications, and general performance testing (bench testing for dosing and image quality).

Therefore, I cannot fulfill your request for information regarding acceptance criteria and a study proving an AI device meets them based on the provided text. The document is about a conventional X-ray imaging system, not an AI-driven device with specific performance metrics like sensitivity, specificity, or AUC established through clinical studies with ground truth.

The "Performance Data" section (page 4) states: "Bench performance testing were conducted based on FDA's Guidance for the Submission of 510/k)'s for Solid-State X-ray Imaging Devices (September 1, 2016), to verify that EOSedge performs according to specifications and is as safe and effective as the predicate device." This refers to engineering and image quality tests common for X-ray hardware, not an AI algorithm evaluation.

Ask a specific question about this device

The sterEOS Workstation is intended for use in the fields of musculoskeletal radiology and orthopedics in both pediatric and adult populations as a general device for acceptance, transfer, display, storage, and digital processing of 2D X-ray images of the musculoskeletal system including interactive 2D measurement tools.

When using 2D X-ray images obtained with the EOS Imaging EOS System, the sterEOS Workstation provides interactive 3D measurement tools:

• · To aid in the analysis of scoliosis and related disorders and deformities of the spine in adult patients as well as pediatric patients. The 3D measurement tools interactive analysis based either on identification of anatomical landmarks for postural assessment, or on a model of bone structures derived from an a priori image data set from 175 patients (91 normal patients, 47 patients with moderate idiopathic scoliosis and 37 patients with severe idiopathic scoliosis), and dry isolated vertebrae data for spine model of bone structures is not intended for use to assess individual vertebral abnormalities and is indicated only for patients 7 years and older. For postural assessment, a set of comparative tools is provided allowing the comparison of performed measurements to reference values for patients over 18 years old.
• · To aid in the analysis of lower limbs alignment and related disorders and deformities based on angle and length measurements. The 3D measurement tools include interactive analysis based either on identification of lower limb alignment landmarks or as for the spine, on a model of bone structures derived from an a priori image data set. The model of bone structures is not intended for use to assess individual bone abnormalities. The 3D package including model-based measurements and torsion angles is indicated only for patients 15 years or older. Only the 2D/3D ruler is indicated for measurements in patients younger than 15 years old.

The sterEOS Workstation is a general system for acceptance, transfer, display, storage, and digital processing of 2D X-ray images of the musculoskeletal system, including interactive 2D measurement tools.

When used with 2D X-ray images obtained with the EOS imaging's EOS System (K152788), the sterEOS Workstation provides interactive 3D measurement tools to aid in the analysis of skeletal deformities in spine and lower limbs.

The provided text describes a 510(k) premarket notification for the sterEOS Workstation, a device for processing 2D X-ray images and providing 3D measurement tools for skeletal deformities. The submission focuses on revisions to contraindications for spine modeling and minor software/hardware modifications.

However, the document does not contain the detailed information required to fill out a table of acceptance criteria and reported device performance based on a rigorous study. The "Performance Data" section primarily discusses functional testing and verification of software modifications, rather than a clinical study with specific performance metrics against acceptance criteria.

Here's an analysis of what is available and what is missing based on your request:

1. Table of acceptance criteria and the reported device performance:

• Missing. The document mentions "compliance with specifications, performance and non-regression" for software modifications, and that "additional performance and functional testing has confirmed the equivalent performance of the modified sterEOS Workstation compared to the predicate sterEOS." However, it does not specify what those specifications, performance metrics, or acceptance criteria were, nor does it provide quantified results of the performance against said criteria.

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

• For the modification related to contraindications: "functional testing of the spine 3D modeling workflows for the no longer contraindicated types of spine with extra vertebra, spine with missing vertebra, and spine with spondylolisthesis." This implies a test set composed of such cases, but the exact sample size is not stated. The data provenance is not explicitly mentioned (e.g., country of origin, retrospective/prospective).
• For the training set of the original model: "a model of bone structures derived from an a priori image data set from 175 patients (91 normal patients, 47 patients with moderate idiopathic scoliosis and 37 patients with severe idiopathic scoliosis), and dry isolated vertebrae data for spine modeling." This refers to the data used for the original 3D spine model, not necessarily a test set for the modifications presented in this 510(k). This data would likely be considered retrospective.

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

• For the functional evaluation study on revised contraindications: "a functional evaluation study conducted by internal experienced radiographers from EOS imaging."
  • Number of experts: Not specified, but plural ("radiographers") implies more than one.
  • Qualifications: "internal experienced radiographers from EOS imaging." Further specific qualifications (e.g., years of experience, board certification) are not provided.
• For the original model (when establishing its ground truth): Not stated in this document.

4. Adjudication method for the test set:

• Not specified. The document mentions a "functional evaluation study conducted by internal experienced radiographers," but does not detail how their findings were reconciled or adjudicated.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

• No. The document does not describe an MRMC study comparing human readers with and without AI assistance. The functional evaluation study was to verify "ease to perform a 3D modeling and to obtain an adjusted outline," not a comparative effectiveness study involving human readers' diagnostic accuracy or efficiency with AI assistance.

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

• The "functional testing of the spine 3D modeling workflows" evaluated the software's ability to model specific spine types. While this involves the algorithm's performance, it's not described as a formal standalone performance study with specific quantitative metrics like sensitivity, specificity, or comparable clinical endpoints. The "functional evaluation study" involved radiographers, indicating a human-in-the-loop component for verification.

7. The type of ground truth used:

• For the functional evaluation of revised contraindications: The ground truth appears to be the ability of the software to successfully perform 3D modeling and provide an adjusted outline that matches the vertebrae for the previously contraindicated spine types. This is based on expert visual assessment ("internal experienced radiographers"). It's more of a qualitative "functional" ground truth rather than a clinical diagnostic ground truth like pathology or long-term outcomes.
• For the original model: Ground truth for the "model of bone structures" was derived from "an a priori image data set from 175 patients" and "dry isolated vertebrae data for spine modeling." How the ground truth for these foundational datasets was established is not detailed in this document.

8. The sample size for the training set:

• "a priori image data set from 175 patients (91 normal patients, 47 patients with moderate idiopathic scoliosis and 37 patients with severe idiopathic scoliosis), and dry isolated vertebrae data for spine modeling." This refers to the data used to build the original 3D model, which serves as a training or development set for the model itself.

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

• Not detailed in this document. It states the model was "derived from an a priori image data set," but how the ground truth for those 175 patient cases or the dry isolated vertebrae was established (e.g., manual annotation by experts, specific measurements, pathology) is not described here.

Ask a specific question about this device

The sterEOS Workstation is intended for use in the fields of musculoskeletal radiology and orthopediativ and adult populations as a general device for acceptance, transfer, display, storage, and digital processing of 2D X-ray images of the musculoskeletal system including interactive 2D measurement tools.

When using 2D X-ray images obtained with the EOS imaging EOS System, the sterEOS Workstation provides interactive 3D measurement tools:

• To aid in the analysis of scoliosis and related disorders and deformities of the spine in adult patients. The 3D measurement tools interactive analysis based either on identification of anatomical landmarks for postural assessment or on a model of bone structures derived from an a priori image data set from 175 patients, 47 patients with moderate idiopathic scoliosis and 37 patients with scoliosis), and dry isolated vertebrae data for spine modeling. The model of bone structures is not intended for use to assess individual vertebral abnormalities and is indicated only for patients 7 years and older. For postural assessment, a set of comparative tools is provided allowing the comparison of performed measurements to reference values for patients over 18 years old.
• To aid in the analysis of lower limbs alignment and deformities based on angle and length measurements. The 3D measurement tools include interactive analysis based either on identification of lower limb alignment landmarks or as for the spine, on a model of bone structures derived from an a priori image data set. The model of bone structures is not intended for use to assess individual bone abnormalities. The 3D package including model-based measurements and torsion angles is indicated only for patients 15 years or older. Only the 2D/3D ruler is indicated for measurements in patients younger than 15 years old.

The sterEOS Workstation is a general system for acceptance, transfer, display, storage, and digital processing of 2D X-ray images of the musculoskeletal system, including interactive 2D measurement tools.

When used with 2D X-ray images obtained with the EOS imaging's EOS System (K152788), the sterEOS Workstation provides interactive 3D measurement tools to aid in the analysis of skeletal deformities in spine and lower limbs.

The provided text appears to be a 510(k) summary for the sterEOS Workstation, a medical device for processing X-ray images, and not a study with detailed acceptance criteria and performance data. Therefore, the information requested in the prompt, especially regarding specific acceptance criteria, study methodologies, and quantitative results like sample sizes for test and training sets, number and qualifications of experts, and MRMC study effect sizes, is not present in the provided document.

The document discusses that the device has undergone software verification and validation testing to confirm compliance with specifications, performance, and non-regression. It also states that additional performance and functional testing was performed, and this testing "confirmed the equivalent performance of the modified sterEOS Workstation compared to the predicate sterEOS." However, it does not provide the details of these tests, such as the specific acceptance criteria, the actual performance metrics, or the study methodologies used.

The document states that the new device is "substantially equivalent" to its predicate device (K14137 sterEOS Workstation) due to having the same intended use, similar technological characteristics, and minor differences that do not raise new questions of safety or effectiveness. This suggests that the approval is based on demonstrating equivalence rather than meeting new, specific acceptance criteria through a standalone clinical study detailed in this summary.

Therefore, I cannot populate the table or answer the specific questions because the detailed information about acceptance criteria and the comprehensive study results are not provided in this 510(k) summary.

Here's a summary of what is available related to the request, and what is missing:

The 510(k) summary indicates that the sterEOS Workstation is a software upgrade to an existing device (K14137). The basis for approval is "substantial equivalence" to the predicate.

Missing Information:

• Detailed Acceptance Criteria and Performance Data: The summary states "performance data demonstrate that the device is as safe and effective," but it does not provide a table with specific acceptance criteria (e.g., minimum accuracy, precision, sensitivity, specificity for 3D measurements) or the reported device performance against those criteria.
• Sample sizes for test set and data provenance: Not mentioned.
• Number of experts and qualifications for ground truth: Not mentioned.
• Adjudication method: Not mentioned.
• MRMC comparative effectiveness study: Not mentioned. The focus is on demonstrating equivalence to the predicate device.
• Standalone performance study: The document refers to "software verification and validation testing" and "additional performance and functional testing" which imply standalone testing, but no detailed results or methodology for such a study (beyond "equivalent performance") are provided.
• Type of ground truth used (for performance testing): Not specified.
• Sample size for the training set: The "model of bone structures" for spine analysis is derived from an a priori image data set from 175 patients (91 normal, 47 moderate idiopathic scoliosis, 37 severe idiopathic scoliosis) and dry isolated vertebrae data for spine modeling. This 175-patient dataset likely serves as the basis for the model, which could be considered training/development data for the model-based measurements. For lower limbs, it also mentions "a model of bone structures derived from an a priori image data set," but doesn't specify the size or nature of this dataset here.
• How ground truth for the training set was established: Not explicitly stated, though for the 175-patient spine data, it implies clinical diagnoses (normal, moderate/severe idiopathic scoliosis).

In conclusion, the provided document is a regulatory submission focused on demonstrating substantial equivalence rather than a detailed scientific study report. It states that performance testing confirmed equivalence but does not offer the granular data requested.

Ask a specific question about this device

EOS is intended for use in general radiographic examinations and applications, excluding the evaluation of lung nodules and examinations involving fluoroscopy, angiography, and mammography. EOS allows the radiographic acquisition of either one or two orthogonal X-ray images for diagnostic purposes, in one single scan, of the whole body or a reduced area of investigation of a patient in the upright or seated position.

The Micro Dose feature is indicated for imaging with a patient entrance dose of 10 to 90 µGy for assessing global skeletal deformities in follow-up pediatric examinations. Micro Dose is not indicated for focal skeletal abnormalities and/or other pediatric abnormalities. Micro Dose is not indicated for use in patients with a Body Mass Index over 30.

EOS is a digital radiography system in which two sets of xenon gas filled digital detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. An acquisition feature named Micro Dose allows image acquisition with a patient entrance dose of 10 to 90 uGv for assessing global skeletal deformities in follow-up pediatric exams. The diagnostic images are stored in a local database and are displayed on a high-resolution, medical-quality monitor, where the diagnosis is performed. The diagnostic image can be transmitted through a DICOM 3.0 compatible digital network for printing and archiving.

The provided text describes the EOS System, a stationary x-ray system, and states that it has been determined to be substantially equivalent to a legally marketed predicate device. However, this document does not contain details about specific acceptance criteria or an explicit study proving device performance against those criteria in the way you've outlined for clinical performance.

Instead, the document focuses on demonstrating substantial equivalence to an existing cleared device (K142773) based on:

• Same Intended Use/Indications for Use: Both the modified and predicate EOS systems share the same intended use for general radiographic examinations, excluding lung nodules, fluoroscopy, angiography, and mammography. They both also offer the "Micro Dose" feature for assessing global skeletal deformities in follow-up pediatric examinations (with specific dose and BMI limitations).
• Similar Technological Characteristics/Principles of Operation: The fundamental technological characteristics of the modified EOS are unchanged from the cleared EOS. Minor modifications (hardware component supplier changes, electrical component changes due to obsolescence, mirror sticker accessory, software modification related to a recall, optimization of default acquisition protocols, improvement of image processing, and addition of new features like Dose Structured Report and Reject and Repeat Analysis) are described as not altering the core function or safety.
• Performance Data (Bench Testing): The document mentions "Performance data demonstrates that the modified EOS is as safe and effective as the cleared predicate device." This includes "bench testing to confirm appropriate dosing and image quality." It also states, "Performance testing has demonstrated that this modification allows reducing the entrance dose for the changed protocols, with maintaining equivalent or better image quality than the cleared EOS" (referring to the optimization of default acquisition protocols).

Therefore, I cannot fill in your requested table and many of the study details because the provided text does not describe a clinical performance study with defined acceptance criteria and results for the device itself, but rather an argument for substantial equivalence of a modified device to a predicate device based on technical performance and safety.

Here's what I can extract and state based on the provided text, while also noting what is not present:

1. A table of acceptance criteria and the reported device performance

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not explicitly mentioned. The document refers to "bench testing" and "performance and functional testing," which typically involves phantoms or test objects, not patient datasets with "test sets" in the clinical sense.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable/Not mentioned. Since this was a substantial equivalence submission based on technical modifications and bench testing, there's no indication of expert review for clinical ground truth on a 'test set.'

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

• Not applicable/Not mentioned.

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. This document describes an X-ray system, not an AI-powered diagnostic device. Therefore, no MRMC study or AI-related effectiveness is discussed.

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

• Not applicable. As the device is an X-ray imaging system, "standalone" performance refers to its ability to acquire images, which is addressed by the "bench testing" and "performance and functional testing" mentioned. There is no algorithm performance discussed in the context of diagnostic interpretation.

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

• Not applicable/Not mentioned for clinical ground truth. The "ground truth" for the performance claims appears to be based on physical measurements of dose and objective assessments of image quality (e.g., spatial resolution, contrast-to-noise ratio) from bench testing, rather than clinical outcomes or pathology.

8. The sample size for the training set

• Not applicable/Not mentioned. This is not an AI/machine learning device that would require a training set in the typical sense.

9. How the ground truth for the training set was established

• Not applicable/Not mentioned.

Ask a specific question about this device