Search Results

The Supria system is indicated for head, whole body, and vascular X-ray Computed Tomography applications in patients of all ages. The images can be acquired in either axial, helical, or dynamic modes.

The volume datasets acquired by the Supria can be post processed by the system to provide additional information. Post processing capabilities included in the Supria software include CT angiography (CTA), Multi-planar reconstruction (MPR) and volume rendering.

Volume datasets acquired by the Supria can be transferred to external devices via a DICOM standard interface.

The guideShot Option adds a remote in-room display and controls to support interventional imaging. The device output can provide an aid to diagnosis when used by a qualified physician.

The Supria is a multi-slice computed tomography system designed to perform multi-slice CT scanning supported by 16-detector technology. The system allows optimum clinical applications ranging from routine exams in response to the diversified circumstances in imaging whole body regions.

The Supria system uses 16-slice CT technology, where the X-ray tube and detector assemblies are mounted on a frame that rotates continuously around the patient using slip ring technology. The solid-state detector assembly design collects up to 16 slices of data simultaneously. The Xray sub-system features a high frequency generator. X-ray tube, and collimation system that produces a fan beam X-ray output. The system can operate in a helical (spiral) scan mode where the patient table moves during scanning. As the X-ray tube/detector assembly rotates around the patient, data is collected at multiple angles.

The collected data is then reconstructed into cross-sectional images by a high-speed reconstruction sub-system. The images are displayed on a Computer Workstation, stored, printed, and archived as required. The workstation is based on current PC technology using the Windows™ operating system.

The Supria system consists of a Gantry, Operator's Workstation, Patient Table, High-Frequency X-ray Generator, and accessories.

The provided text is a 510(k) Pre-market Notification for a medical device, specifically the HITACHI Supria Whole-body X-ray CT System Phase 3. It compares the new device to a predicate device (HITACHI SUPRIA w/guideShot Option K161748) to demonstrate substantial equivalence, rather than providing a detailed study proving the device meets acceptance criteria in the sense of a performance study with specific metrics and statistical analysis.

The document states that the new device has two new features: "Intelli IP Quick" (a faster noise reduction technique) and "HiMAR" (reduces artifacts caused by metal). The "Performance Testing - Clinical" section briefly mentions that "clinical images were collected and analyzed" for these new features to "ensure that images constructed by the Supria Whole-body X-ray CT System meet user needs." It also notes that "Hitachi has provided clinical images demonstrating the image quality of Intelli IP Quick and HiMAR features and validated by a physician."

Therefore, it is important to note that the provided text does NOT contain the detailed information typically found in a clinical study report that defines and proves specific acceptance criteria for performance metrics (like sensitivity, specificity, accuracy) using a rigorous methodology. Instead, it relies on demonstrating comparable performance to a predicate device and physician validation of image quality for new features.

Based on the provided text, here's what can be extracted and what remains unknown:

Acceptance Criteria and Device Performance (Based on provided text)

Since direct quantitative acceptance criteria and performance metrics are not explicitly stated in a table format for the new features or overall device, we can infer the "acceptance" is primarily based on substantial equivalence to the predicate device and subjective physician validation of image quality for the new features.

"Hitachi believes that, based on the information included in the submission, Supria Whole-body X-ray CT System Phase 3 is substantially equivalent with respect to hardware, base elements of the software, safety, effectiveness, and functionality to the SUPRIA w/guideShot Option (K161748)." |
| - Hardware | No differences identified (e.g., Gantry, Detector, X-ray Tube, X-ray Generator, Patient Table, Display, Image Storage parameters are identical to predicate). |
| - Base elements of software | Most software features are identical to the predicate. Key differences (Intelli IP Quick, HiMAR, Orbit synchronization scan, Off-time mode, On-time standby, Shutter Scan Reduction) are described as improvements or additional functionalities. |
| - Safety | "The technological characteristics do not impact safety and effectiveness." (Stated for the differences in Table 3). Compliance with applicable safety standards (e.g., IEC 60601 series, NEMA XR 25, NEMA XR26) is declared. |
| - Effectiveness | "The technological characteristics do not impact safety and effectiveness." (Stated for the differences in Table 3). Clinical images demonstrating the image quality of Intelli IP Quick and HiMAR features were "collected and analyzed" and "validated by a physician" to "ensure that images constructed by the Supria Whole-body X-ray CT System meet user needs." The overall "Performance Comparison" section also states "A clinical evaluation comparison was conducted with the Supria Phase 3 system and the SUPRIA w/guideShot Option (K161748) and found to be substantially equivalent." |
| - Functionality | Detailed comparison in Table 2 shows identical functionality for many parameters, with new features (Intelli IP Quick, HiMAR etc.) presented as enhancements that do not negatively impact core functionality. |
| Image Quality with new features (Intelli IP Quick, HiMAR) | "clinical images demonstrating the image quality of Intelli IP Quick and HiMAR features and validated by a physician." The images were collected and analyzed "to ensure that images constructed by the Supria Whole-body X-ray CT System meet user needs." |

Study Details:

1. Sample sizes used for the test set and data provenance:

   • Test Set Sample Size: Not specified. The document only mentions that "clinical images were collected and analyzed" for the new features. No specific number of images or patients is provided.
   • Data Provenance: Not specified regarding country of origin. The study is described as "clinical images were collected," implying real patient data. It is a retrospective or prospective study is not specified, but the phrasing "were collected" could suggest a collection from existing or newly acquired cases.

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

   • Number of Experts: Not specified. The document states the image quality was "validated by a physician." It does not specify if this was one physician or a panel.
   • Qualifications of Experts: The qualification is generally stated as "a physician." Specific specialties (e.g., Radiologist) or years of experience are not mentioned.

3. Adjudication method for the test set:

   • Not specified. Given the limited detail ("validated by a physician"), it's unlikely a formal adjudication method (like 2+1 or 3+1) was employed and documented in this 510(k) submission.

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

   • Not explicitly stated or described. The document refers to a "clinical evaluation comparison" but does not detail it as a formal MRMC study. It states the comparison "found to be substantially equivalent" and that clinical images were "validated by a physician." There is no mention of multiple human readers, a comparative effectiveness study design, or an effect size for human readers' improvement with AI assistance. The new features (Intelli IP Quick, HiMAR) are signal processing techniques within the CT system, not an AI assistance tool for human interpretation in the sense of a CAD system.

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

   • The "performance comparison" section mentions "Performance Testing - Bench" with a rationale analysis indicating "Hitachi judged that Supria Whole-body X-ray CT System Phase 3 is substantially equivalent to the predicate." It also notes that the device complies with "all applicable requirements for Dose Profile, Noise, Mean CT number and Uniformity, Spatial Resolution, Tomographic Section Thickness and Sensitivity Profile, Tomographic Plane Location, and CT dose index." This sounds like standalone technical performance testing, but not necessarily a clinical "algorithm only" performance evaluation akin to an AI diagnostic tool. The device itself is a CT scanner, not an AI algorithm intended for standalone diagnosis.

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

   • For the clinical evaluation of the new features (Intelli IP Quick, HiMAR), the ground truth appears to be based on "physician validation" of "image quality" and ensuring that the images "meet user needs." This is a subjective assessment, not pathology or outcomes data. For the comparison to the predicate, it's about comparable physical and performance characteristics.

7. The sample size for the training set:

   • Not applicable / Not specified. The document describes a CT system and its new image processing features. It does not mention a "training set" in the context of machine learning. The "Intelli IP Quick" and "HiMAR" are described as "processing techniques" that reduce noise or reduce metal artifacts, implying algorithms that might have been developed and tuned, but the text does not detail any "training data" or "training set" as would be seen for a deep learning model.

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

   • Not applicable / Not specified. As no training set or machine learning model is explicitly described, there is no information on how a ground truth for such a set would have been established.

Ask a specific question about this device

The TRILLIUM OVAL Head Coil 32 is a 32 channel recieve-only multiple array device used with the Hitachi TRILLIUM OVAL 3.0 Tesla systems for imaging of the head region that can be interpreted by a trained physician.

The TRILLIUM OVAL Head Coil 32 is a receive-only device that detects the MR signal used to produce transverse, coronal, sagittal, oblique, and/or curved cross-sectional images that display the internal structure of the head. The images produced by the MR system reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. When interpreted by a trained physician, these images provide information that can be useful in diagnosis determination.

The provided document is a 510(k) premarket notification for the "TRILLIUM OVAL Head Coil 32". This document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study to prove a device meets specific acceptance criteria for diagnostic performance. Therefore, many of the requested elements for a diagnostic AI study are not applicable or not present in this type of submission.

Here's a breakdown of the available information with respect to your request:

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

The document does not specify "acceptance criteria" in the context of diagnostic performance metrics like sensitivity, specificity, or AUC, as it's a device component (MRI coil) and not an AI diagnostic algorithm. Instead, it refers to performance characteristics related to hardware and safety.

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

Not applicable. This device is an MRI head coil, and the evaluation focuses on its technical performance and safety, not its diagnostic accuracy on a dataset of patient scans. The "clinical images of the head were provided to support the effectiveness of the subject device," but this is not a diagnostic test set with labeled outcomes.

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

Not applicable. Ground truth for diagnostic outcomes is not established for this type of device submission. The images are interpreted by a "trained physician," which is a statement about the intended use of the images, not a ground truth assessment for a study.

4. Adjudication method for the test set

Not applicable. There is no diagnostic test set requiring adjudication in this submission.

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

Not applicable. This is not an AI diagnostic device.

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

Not applicable. This is not an AI diagnostic algorithm.

7. The type of ground truth used

Not applicable. No ground truth for diagnostic outcomes was used as this is a device component, not a diagnostic algorithm. Performance evaluation focuses on engineering standards and safety.

8. The sample size for the training set

Not applicable. This is a hardware device; there is no training set in the context of machine learning.

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

Not applicable. See above.

Summary of the Study Proving Device Meets Acceptance Criteria (Based on the provided document):

The "study" conducted for the TRILLIUM OVAL Head Coil 32 was primarily a series of non-clinical tests and comparisons to demonstrate substantial equivalence to a legally marketed predicate device (TRILLIUM OVAL WIT Posterior Head/Neck coil and WIT Anterior Head attachment - K142734).

The acceptance criteria are implicitly defined by compliance with recognized standards and a comparison of technological characteristics and performance to the predicate device.

• Tests Conducted:

  • NEMA MS 1 (Determination of Signal-to-noise Ratio (SNR)): This standard quantitatively assesses the signal quality of MRI systems. The subject device reported an SNR of 245 +/- 20%, compared to the predicate's 145 +/- 20%. The higher SNR for the subject device indicates improved signal quality.
  • NEMA MS 3 (Determination of Image Uniformity): This standard assesses the consistency of the signal across the image.
  • AAMI / ANSI ES60601-1 (Medical Electrical Equipment - Basic Safety and Essential Performance): This evaluates overall electrical safety.
  • IEC 60601-1-2 (Electromagnetic Compatibility): This ensures the device operates correctly without interference and doesn't cause interference.
  • IEC 60601-2-33 (Particular Requirements for Basic Safety and Essential Performance of Magnetic Resonance Equipment): This is a specific safety standard for MRI equipment.
  • Heat testing: Performed on the new coil to ensure it operates within safe temperature limits.

• Methodology:
  The evaluation focused on comparing the intended use, hardware specifications (e.g., coil dimensions, coil type, number of elements, decoupling method), and performance (SNR, electrical safety) of the subject device to the predicate device. The conclusion of substantial equivalence was reached based on the analysis that:

  • The subject device has the same intended use.
  • Any differences in specifications (e.g., increased number of channels from 19 to 32, improved SNR) do not constitute a new intended use and do not raise new questions of safety or effectiveness. In fact, the higher SNR for the subject device is generally considered an improvement in performance.
  • Compliance with recognized safety and performance standards was demonstrated.

• Clinical Data: No formal clinical trials for diagnostic accuracy were conducted. However, "clinical images of the head were provided to support the effectiveness of the subject device." This is typically to visually demonstrate the image quality produced by the new coil.

In essence, the "study" was a regulatory submission that leveraged engineering tests and comparative analysis against an already approved predicate device to demonstrate that the new head coil is as safe and effective, and in some aspects, technologically improved, without introducing new risks.

Ask a specific question about this device

The Supria system is indicated for head, whole body, and vascular X-ray Computed Tomography applications in patients of all ages. The images can be acquired in either axial, helical, or dynamic modes.

The volume datasets acquired by the Supria can be post processed by the system to provide additional information. Post processing capabilities included in the Supria software include CT angiography (CTA). Multi-planar reconstruction (MPR) and volume rendering.

Volume datasets acquired by the Supria can be transferred to external devices via a DICOM standard interface. The guideShot Option adds a remote in-room display and controls to support interventional imaging. The device output can provide an aid to diagnosis when used by a qualified physician.

The SUPRIA is a multi-slice computed tomography system designed to perform multi-slice CT scanning supported by 16-detector technology. The system allows optimum clinical applications ranging from routine exams in response to the diversified circumstances in imaging whole body regions.

The SUPRIA system uses 16-slice CT technology, where the X-ray tube and detector assemblies are mounted on a frame that rotates continuously around the patient using slip ring technology. The solid-state detector assembly design collects up to 16 slices of data simultaneously. The X-rav sub-system features a high frequency generator. X-ray tube, and collimation system that produces a fan beam X-ray output. The system can operate in a helical (spiral) scan mode where the patient table moves during scanning. As the X-ray tube/detector assembly rotates around the patient, data is collected at multiple angles.

The collected data is then reconstructed into cross-sectional images by a high-speed reconstruction sub-system. The images are displayed on a Computer Workstation, stored, printed, and archived as required. The workstation is based on current PC technology using the Windows™ operating system.

The SUPRIA system consists of a Gantry, Operator's Workstation, Patient Table, High-Frequency X-ray Generator, and accessories.

The provided text does not contain specific acceptance criteria or a detailed study proving the device meets those criteria with numerical performance metrics. Instead, it focuses on demonstrating substantial equivalence to a predicate device (SCENARIA Phase 2 Whole-body X-ray CT System K123509) through comparison of technological characteristics and general performance.

Here's an attempt to extract and synthesize the requested information based on what is available in the document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria. Instead, it relies on demonstrating that the SUPRIA w/guideShot Option has "equivalent basic performance" or "comparable performance" to the predicate device, SCENARIA Phase 2. The 'Performance' section within the "Device Technological Characteristics" table offers some numerical comparisons for specific aspects:

Note: The "Acceptance Criteria" column is inferred from the predicate device's specifications, as the goal is to show equivalence. The "Reported Device Performance" column directly reflects the SUPRIA's specifications as listed. The document states that the SUPRIA's performance characteristics are "comparable" or "generally equivalent" to the predicate, and for some specific metrics like reconstruction time, SUPRIA even shows improved performance.

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

• Test Set Sample Size: The document mentions that "clinical images were collected and analyzed" and that "clinical image examples" were provided. However, it does not specify a numerical sample size for this clinical image collection.
• Data Provenance: Not explicitly stated. The document simply refers to "clinical images." It does not mention the country of origin or whether the data was retrospective or prospective.

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

The document states, "We provide clinical image examples which we judged to be sufficient to judge a clinical usability." This implies an internal assessment.

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. It only mentions "we judged," which could refer to the manufacturer's internal team.

4. Adjudication Method for the Test Set

Not specified. The document only mentions that "clinical images were collected and analyzed" and "judged to be sufficient to judge a clinical usability." There is no indication of a formal adjudication process (e.g., 2+1, 3+1).

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

• Was an MRMC study done? No, the document does not indicate that an MRMC comparative effectiveness study was conducted. The evaluation focuses on the device's technical specifications and a comparison to a predicate device, rather than human reader performance with and without AI assistance.
• Effect size of human readers with AI vs. without AI assistance: Not applicable, as no MRMC study involving AI assistance for human readers was reported.

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

The device itself is a Computed Tomography (CT) system (hardware and software for image acquisition and basic post-processing), not an AI algorithm for diagnosis. The "guideShot Option" adds remote in-room display and controls for interventional imaging. Therefore, the concept of a "standalone algorithm" performance as typically evaluated for AI-driven diagnostic tools is not directly applicable here. The focus is on the performance of the CT system in producing images, which are then used by a physician.

7. The Type of Ground Truth Used

The document mentions "clinical image examples" which were "judged to be sufficient to judge a clinical usability." This suggests the ground truth was based on:

• Expert Clinical Judgment/Usability: The images were evaluated to confirm they met clinical usability standards, likely by qualified personnel. It does not mention pathology, outcomes data, or a formal consensus process as a "ground truth" for diagnostic accuracy of an AI model within the system.

8. The Sample Size for the Training Set

Not applicable. The SUPRIA w/guideShot Option is a computed tomography x-ray system, not primarily an AI algorithm that undergoes "training" in the conventional sense of machine learning for image interpretation. The device's software includes image reconstruction and post-processing capabilities, which are based on established scientific principles and algorithms, not a training set of images with ground truth for learning.

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

Not applicable, as there is no mention of a training set or AI model training in the context of this device.

Ask a specific question about this device

The TRILLIUM Oval MRI System is an imaging device, and is intended to provide the physician with physiological and clinical information, obtained non-invasively and without the use of ionizing radiation. The MR system produces transverse, coronal, sagittal, oblique, and curved cross-sectional images that display the internal structure of the head, body, or extremities. The images produced by the MR system reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. The NMR properties that determine are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2), and flow. When interpreted by a trained physician, these images provide information that can be useful in diagnosis determination.

Anatomical Region: Head, Body, Spine, Extremities
Nucleus excited: Proton
Diagnostic uses:
T1, T2, proton density weighted imaging
Diffusion weighted imaging
MR Angiography
Image processing
Spectroscopy
Whole Body

The TRILLIUM OVAL is a Magnetic Resonance Imaging System that utilizes a 2.9 Tesla superconducting magnet in a gantry design. The TRILLIUM OVAL has been designed to enhance clinical utility as compared to the ECHELON Oval by taking advantage of the stronger magnetic field and stronger gradient field and slew rate. There is no change in the system composition from the predicate device.

The document you provided is a 510(k) premarket notification for the Hitachi TRILLIUM Oval V5.1 MRI System. It describes a software update to an existing MRI system (TRILLIUM OVAL, K142734) and therefore focuses on demonstrating substantial equivalence to the predicate device, rather than proving that the device meets specific acceptance criteria through a standalone study with defined performance thresholds.

The "acceptance criteria" discussed in this document are primarily compliance with international and national standards for medical electrical equipment and MRI devices, and the demonstration that new software features perform as intended without compromising safety or effectiveness.

Here's an analysis based on the information provided, framed to address your questions as closely as possible, while noting where specific answers are not available due to the nature of a 510(k) for a software update:

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

For a software update to an existing MRI system, the "acceptance criteria" are generally about maintaining compliance with safety and performance standards established for the predicate device and confirming the intended function of new features.

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

The document primarily describes non-clinical testing involving phantom simulations and volunteer studies. It does not specify a quantitative "test set" in terms of patient data or detailed sample sizes.

• Sample Size for Test Set: Not explicitly stated as a number of cases/patients for each feature. The studies involved "phantom simulations and volunteer studies." This suggests a small, controlled set of healthy volunteers rather than a large patient cohort.
• Data Provenance: Not specified. "Volunteer studies" typically implies prospective data collection. Country of origin is not mentioned. Given Hitachi Medical Systems America, Inc. is the submitter, the studies could be internal or conducted in an associated facility.

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)

This information is not provided in the document. For non-clinical performance evaluations of MRI system features, "ground truth" might be established through:

• Physical measurements on phantoms.
• Physiological parameters measured during volunteer studies.
• Comparison to established imaging techniques or qualitative assessment by experienced MR physicists or radiologists, but specifics are absent here.

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

This information is not provided. Given the nature of a software update for an MRI system demonstrating substantial equivalence, formal adjudication methods (common in AI/CADe studies) are generally not performed or required for these types of submissions. The evaluations are more focused on technical performance and image quality by MR physicists and system engineers, potentially with clinical input from radiologists for qualitative assessment of images.

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, a multi-reader, multi-case (MRMC) comparative effectiveness study was not performed and is not described for this submission. This is because the device is an MRI system itself and its software, not an AI/CADe product intended to assist human readers. The document focuses on the technical performance of the MRI system's new sequences and processing capabilities.

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

The entire performance evaluation described is essentially "standalone" in the sense that it assesses the technical capabilities of the MRI system and its new software features directly (e.g., confirming acquisition, mapping, or reduction of scan time). It's not an "algorithm-only" performance as one might describe an AI model, but rather the performance of the full integrated imaging system. The "test results from phantom simulations and volunteer studies" for all the new features (Multi-b and DKI, k-Space Parallel Imaging, T2* RelaxMap, etc.) represent the demonstrated performance of the system directly, without explicitly quantifying 'human-in-the-loop' interaction in terms of diagnostic performance metrics.

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

For the new features, the "ground truth" likely refers to:

• Physical measurements/known properties of phantoms: For features like SNR, geometric distortion, T2* relaxation times in phantoms, or artifact reduction.
• Physiological measurements/expected outcomes in volunteers: For features like ASL-Perfusion (labeled blood flow), or the detection of metabolites in Breast MRS.
• Qualitative assessment of image quality and feature functionality: By qualified personnel (e.g., MR physicists, radiologists) for aspects like "improvement of overall SNR," "reduction of scan time," or "mitigation of dark band artifact."

No mention of pathology or outcomes data is made, which is typical for demonstrating substantial equivalence of an imaging system software update.

8. The sample size for the training set

The document describes software updates and performance validation for an MRI system. It does not mention "training sets" in the context of machine learning or AI models. The software features are likely based on established MR physics principles and algorithms, rather than being data-driven machine learning models that require training sets. Therefore, this question is not applicable in the context of this submission.

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

As there is no mention of a "training set" for machine learning, this question is not applicable.

Ask a specific question about this device

The ECHELON Oval MRI System is an imaging device, and is intended to provide the physician with physiological and clinical information, obtained non-invasively and without the use of ionizing radiation. The MR system produces transverse, coronal, sagittal, oblique, and curved cross-sectional images that display the internal structure of the head, body, or extremities. The images produced by the MR system reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-lattice relaxation time (TI), spin-spin relaxation time (T2), and flow. When interpreted by a trained physician, these images provide information that can be useful in diagnosis determination.

The ECHELON OVAL V5.1 is a Magnetic Resonance Imaging System that utilizes a 1.5 Tesla superconducting magnet in a gantry design. The design was based on the ECHELON MRI system. The ECHELON OVAL has been designed to enhance clinical utility as compared to the ECHELON by taking advantage of open architecture.

This FDA 510(k) summary for the ECHELON Oval V5.1 MRI System does not contain acceptance criteria or a study proving the device meets acceptance criteria in the format often seen for AI/ML-driven devices. Instead, this document focuses on demonstrating substantial equivalence to a previously cleared predicate device (ECHELON Oval V5.0 MRI System K151015).

In the context of a 510(k) for an MRI system, acceptance criteria are typically related to the physical and performance characteristics of the imaging system itself, rather than diagnostic accuracy like in AI/ML products. The 'studies' conducted here are primarily verification and validation tests to ensure the modified device meets established safety and performance standards equivalent to the predicate.

Given these limitations from the provided text, I will answer based on the information available and point out what is missing or not applicable.

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

The document does not explicitly state "acceptance criteria" and "reported device performance" in a table for diagnostic accuracy, as it's not an AI/ML diagnostic device with performance metrics like sensitivity/specificity.

However, the closest equivalent in this document would be the comparison of technical specifications against established standards and the predicate device. The "Performance Evaluation" section (Page 5) states: "There is no change from the previous predicate device that would affect performance." This implies that the performance of the ECHELON Oval V5.1 MRI System is expected to be equivalent to the ECHELON Oval V5.0 MRI System (K151015) which successfully met its own performance criteria (not detailed in this document).

The "Summary of Non-Clinical Testing" (Page 9) lists the standards that the device conforms to. These standards effectively act as the "acceptance criteria" for the MRI system's physical and technical performance. The "reported device performance" implicitly matches these standards by stating conformance.

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

This information is not provided in the document. The document primarily focuses on technical comparisons and conformance to standards, not a clinical study on diagnostic performance with a test set of patient data.

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)

This information is not provided and is not applicable in this context. Ground truth establishment by experts for specific diagnostic outcomes is typical for AI/ML device evaluations, not for demonstrating substantial equivalence of a new MRI system version. The "Indications for Use" mentions interpretation by a "trained physician," but this is general usage, not specific to a testing ground truth.

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

This information is not provided and is not applicable for this type of submission.

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

An MRMC study was not done. This type of study is relevant for evaluating the clinical utility and impact of AI software on human reader performance, which is not the focus of this MRI system's 510(k) submission.

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

A standalone performance evaluation of an algorithm was not done. This device is an MRI system, not an AI algorithm. Its performance is evaluated through its adherence to technical standards and demonstration of equivalence to its predicate.

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

The concept of "ground truth" (e.g., pathology, expert consensus) as used in AI/ML evaluations is not applicable here. The "ground truth" for an MRI system's performance revolves around its ability to accurately and safely generate images according to its technical specifications and relevant industry standards. The summary of non-clinical testing refers to conformance with NEMA and IEC standards, which define objective measures for image quality (SNR, geometric distortion, uniformity, slice thickness), safety (acoustic noise, SAR), and software processes.

8. The sample size for the training set

This information is not provided as this is an MRI system, not an AI/ML device trained on a dataset.

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

This information is not provided as this is an MRI system, not an AI/ML device.

Ask a specific question about this device

The SCENARIA Phase 3 system is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages. The images can be acquired in either axial, helical, gated or dynamic modes.

The volume datasets acquired by the SCENARIA Phase 3 can be post processed by the SCENARIA Phase 3 to provide additional information. Post processing capabilities included in the SCENARIA Phase 3 software include CT angiography (CTA), Multi-planar reconstruction (MPR) and volume rendering.

Volume datasets acquired by the SCENARIA Phase 3 can be transferred to external devices via a DICOM standard interface.

The guideShot Option adds a remote in-room display and controls to support interventional imaging. The device output can provide an aid to diagnosis when used by a qualified physician.

The SCENARIA Phase 3 is a multi-slice computed tomography system that uses x-ray data to produce cross-sectional images of the body at various angles. The system consists of a Gantry, Operator's Workstation, Patient Table, High-Frequency X-ray Generator, and accessories. The system uses 128-slice CT technology, where the X-ray tube and detector assemblies are mounted on a frame that rotates continuously around the patient using slip ring technology. The solid-state detector assembly design collects up to 64 slices of data simultaneously. The X-ray sub-system features a high frequency generator, X-ray tube, and collimation system that produces a fan beam X-ray output. The system can operate in a helical (spiral) scan mode where the patient table moves during scanning. As the X-ray tube/detector assembly rotates around the patient, data is collected at multiple angles. The collected data is then reconstructed into cross-sectional images by a high-speed reconstruction sub-system. The images are displayed on a Computer Workstation, stored, printed, and archived as required. The workstation is based on current PC technology using the Windows™ operating system.

The provided text describes the 510(k) premarket notification for the HITACHI SCENARIA Phase 3 Whole-body X-ray CT System, asserting its substantial equivalence to a predicate device (SCENARIA Phase 2 Whole-body X-ray CT System, K123509). The document focuses on demonstrating that the new device has comparable performance and technological characteristics to the predicate device, rather than proving that it meets specific, quantitative acceptance criteria for diagnostic accuracy through a controlled study.

Therefore, many of the requested items (e.g., sample size for test set, ground truth experts, adjudication methods, MRMC study, standalone performance, training set size) are not explicitly detailed in the provided document, as the submission strategy is based on demonstrating substantial equivalence to a previously cleared device.

Here's an analysis based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are not presented in a traditional "pass/fail" format with numerical thresholds for diagnostic accuracy metrics. Instead, the "acceptance criteria" are implied by the demonstration of comparable performance to the predicate device for various technical parameters and a judgment of clinical usability of example images.

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

• Sample Size for Test Set: "Five clinical image examples" were provided for the clinical evaluation. This is a very small sample, used for qualitative judgment of usability and comparability, not for statistical performance evaluation.
• Data Provenance: The document does not specify the country of origin of the clinical data. It is implied these were collected as part of the device's development or validation. It is a prospective collection for the purpose of this submission as "Clinical images were collected and analyzed."

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

The document states: "We provide five clinical image examples which we judged to be sufficient to judge a clinical usability." It does not specify the number or qualifications of the individuals who performed this judgment.

4. Adjudication Method (for the test set)

No adjudication method is described. The text only mentions that "we judged" the examples to be sufficient.

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

No MRMC comparative effectiveness study was mentioned or performed to assess human reader improvement with or without AI assistance. The device is a CT system itself, not an AI-assisted diagnostic tool that augments human interpretation in the sense of comparing human performance with and without an AI algorithm.

6. Standalone (Algorithm Only) Performance

This document describes a CT imaging system. The performance metrics reported (e.g., spatial resolution, low-contrast resolution) are for the system's image acquisition and reconstruction capabilities themselves, which represent its "standalone" performance as an imaging device. The device itself is the "algorithm only" in the context of image generation. It's not an AI diagnostic algorithm that processes images; it's the image acquisition and processing hardware and software for a CT scanner.

7. Type of Ground Truth Used

For the clinical evaluation, the "ground truth" was a subjective assessment of "clinical usability" and "comparability" to the predicate device's examples. For bench testing, the ground truth was based on adherence to regulatory standards (21 CFR 1020.33) and technical specifications (e.g., IEC standards, NEMA standards) for image quality parameters (dose, noise, spatial resolution, etc.), established through phantom studies and measurements.

8. Sample Size for the Training Set

There is no mention of a "training set" in the context of machine learning, as this device is a CT imaging system and not primarily an AI algorithm for diagnostic interpretation that would require a distinct training set of labeled data in the sense of deep learning. The "training" for the device's image reconstruction algorithms would be inherent in its design and engineering based on physics and mathematical principles.

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

Not applicable, as a traditional machine learning training set with external ground truth labels is not described or relevant for this type of device submission. The device's performance is validated against physical and regulatory standards.

Ask a specific question about this device

The Supria system is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages. The images can be acquired in either axial, helical, gated or dynamic modes.

The volume datasets acquired by the Supria can be post processed by the system to provide additional information and can be transferred to external devices via a DICOM standard interface.

Post processing capabilities included in the Supria software include CT angiography (CTA), Multi-planar reconstruction (MPR) and volume rendering.

The device output can provide an aid to diagnosis when used by a qualified physician.

The Supria is a multi-slice computed tomography system designed to perform multi-slice CT scanning supported by 16-detector technology. The system allows optimum clinical applications ranging from routine exams in response to the diversified circumstances in imaging whole body regions.

The Supria system consists of a Gantry, Operator's Workstation, Patient Table, High-Frequency X-ray Generator, and accessories.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria for clinical performance in a structured table. Instead, it relies on a qualitative assessment against a predicate device. The performance comparisons for the Supria CT system are primarily against the SCENARIA Phase 2 Whole-body X-ray CT System (K123509).

• Six clinical image examples were provided and judged sufficient to demonstrate clinical usability across general anatomy outlined in indications for use. These were deemed comparable to the predicate's examples, with the exception of cardiac images due to lack of ECG support in Supria.
• A radiologist validated that clinical images using image quality optimization technology (Intelli IP Advanced and IntelliEC) exhibited "acceptable image quality for clinical use." |
  | Physical and Performance Characteristics (General equivalence to predicate and regulatory compliance) | Bench Performance Testing:
• Evaluation for dose profile, image noise, Modulation Transfer Function (MTF), slice thickness and sensitivity profile, slice plane location, and CT dose index were conducted.
• Found to be "substantially equivalent" to the predicate device for these parameters.
• Confirmed that these items met the conditions of 21 CFR 1020.33(c) or (g).
• Performance characteristics are comparable to the predicate device. |
  | Technological Characteristics (No significant impact on safety and effectiveness despite differences from predicate) | Demonstrated through a detailed comparison (Table 2 & 3) that differences in Gantry, Detector, X-ray Tube, X-ray Generator, Patient Table, Image Storage, Scanning/Reconstruction, Dose Controls, and Features do not "substantially affect the intended use of the device and does not impact the effectivity and safety of this device". For example, the lack of ECG function is acknowledged but deemed not to impact safety/effectiveness for the device's general-purpose use. |
  | Compliance with Standards | Conformance with a list of applicable standards, including AAMI ANSI ES60601-1, IEC 60601-1-2, IEC 60601-1-3, IEC 60601-2-44, NEMA XR 25, NEMA XR26, and IEC 62304. |

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

• Sample Size for Clinical Test Set: "Six clinical image examples" were used. This is a very small sample size for a clinical evaluation.
• Data Provenance: Not explicitly stated, but it's implied that these images were generated by the Supria system itself during its development or testing. No information on country of origin or whether it was retrospective/prospective is provided.

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

• Number of Experts: "A radiologist" (singular) was used to validate the clinical images.
• Qualifications of Experts: The document explicitly states "a radiologist." No further details on experience level (e.g., "10 years of experience") are provided.

4. Adjudication Method for the Test Set

• Adjudication Method: "A radiologist validated" the images. This implies a single-reader assessment rather than a multi-reader adjudication process. No mention of 2+1, 3+1, or any other consensus method.

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

• MRMC Study: No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly mentioned or performed. This device is an X-ray CT system, not an AI-powered diagnostic tool, and the evaluation focuses on the inherent performance and image quality of the hardware and software without specific "AI assistance" for human readers in a comparative effectiveness study.

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

• This device is an X-ray CT system. Its primary output is images, which are then interpreted by human physicians. Therefore, the concept of "standalone (algorithm only) performance" as it might apply to an AI diagnostic algorithm is not directly applicable here. The performance tests (dose profile, noise, MTF, etc.) are inherent to the machine's operation, and the clinical image assessment validates the output of the machine for human interpretation.

7. The Type of Ground Truth Used

• Ground Truth Type:
  • For bench performance testing, the ground truth was regulatory standards (21 CFR 1020.33(c) or (g)) and physical measurements against known values (e.g., for spatial resolution, MTF).
  • For clinical image examples, the "ground truth" was a qualitative assessment by "a radiologist" that the images had "acceptable image quality for clinical use" and were "sufficient to judge a clinical usability." This is effectively expert consensus (from a single expert) on image quality suitable for diagnosis, rather than pathology, or outcomes data resolving the presence/absence of a specific condition.

8. The Sample Size for the Training Set

• The document does not explicitly mention a "training set" in the context of an AI/machine learning model. The Supria is a CT imaging system. While it has "image quality optimization technology (Intelli IP Advanced and IntelliEC)" and "Iterative Reconstruction," these are typically engineered features based on physics and signal processing principles, not necessarily machine learning models that require a distinct "training set" in the way a diagnostic AI algorithm would. If these features involved machine learning, the training data used is not disclosed.

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

• As a "training set" is not explicitly mentioned or implied for a machine learning context, the method for establishing its ground truth is not provided.

Ask a specific question about this device

The ECHELON Oval System is an imaging device and is intended to provide the physician with physiological and clinical information, obtained non-invasively and without the use of ionizing radiation. The MR system produces transverse, coronal, sagittal, oblique, and curved cross-sectional images that display the internal structure of the head, body, or extremities. The images produced by the MR system reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2) and flow. When interpreted by a trained physician, these images provide information that can be useful in diagnosis determination.

The ECHELON OVAL is a Magnetic Resonance Imaging System that utilizes a 1.5 Tesla superconducting magnet in a gantry design. The design was based on the ECHELON MRI system. The ECHELON OVAL has been designed to enhance clinical utility as compared to the ECHELON by taking advantage of open architecture.

This request is asking for a detailed breakdown of the acceptance criteria and the study used to validate the ECHELON Oval V5.0 MRI system, based on the provided FDA 510(k) summary.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in a traditional table format for performance metrics. Instead, the acceptance is based on qualitative assessments and comparisons to the predicate device.

• ASL-Perfusion: "Test results confirm ASL-Perfusion acquires perfusion images using labeled blood flowing into the brain tissue without Contrast-Enhanced both in phantom simulations and clinical results."
• Beam Sat VASC-ASL: "Test results confirm Beam Sat improves the visibility of the portal vein in making MIP images both in phantom simulations and clinical results."
• Breast MRS: "Test results from phantom simulations and clinical results confirm MRS (Magnetic Resonance Spectroscopy) acquires the magnetic resonance signal of in vivo metabolites through chemical shift phenomenon and can detect Choline as metabolite in the breast area."
• Enhanced PC: "Test results from phantom simulations and clinical results indicate a reduction in scan time of phase contrast (PC) sequence in 2D and 3D by shorting the TR by optimizing velocity encode gradient and applied parallel imaging (RAPID). As a result of this improvement, we can shorten scan time of '4D flow' which is time-resolved (CINE) three-dimensional (3D) spatial encoding combined with three-directional velocityencoded phase contrast MRI."
• Fat and water separation scan (FSE, RSSG, GE): "Test results from phantom simulations and clinical results indicate reliable and uniform fat suppression by utilizing the difference between resonant frequencies due to chemical shift of water protons and fat protons to obtain a water image and a fat image. The chemical shift of a water signal and a fat signal receives two echo signals at the timing which becomes an in-phase and an out-of-phase. By adding and subtracting it, a water image and a fat image are simultaneously acquirable."
• k-RAPID: "Test results from phantom simulations and clinical results indicate that k-space parallel imaging technique accelerates the scan by acquiring k-space data with skipped phase encoding and skipped position which is filled with estimated data by the interpolation of neighboring data."
• Multi b and DKI: "Test results from phantom simulations and clinical results confirm Multi b DKI images can be acquired in one scan utilizing Tensor 15 and Tensor 30 being added to the number of MPG Axes. Diffusion Kurtosis Imaging (DKI) is the diffusion-weighted imaging technique in restriction."
• opFSE / opFIR: "Test results from phantom simulations and clinical results confirm by deriving opFSE and opFIR sequence from the primeFSE and primeFIR image quality is improved."
• PBSG: "Test results from phantom simulations and clinical results confirm PBSG which is a sequence based on BASG sequence improves to mitigate the dark band artifact which is unique to BASG sequence. The PBSG sequence makes it possible to acquire BASG images under the condition of inhomogeneous magnetic field with less band artifact."
• RADAR-GE/TOF: "Test results from phantom simulations and clinical results confirm the RADAR measurement feature is functioning with the GE and TOF sequence."
• T2 RelaxMap:* "Test results from phantom simulations and clinical results confirm that T2* relaxation time can be mapped on morphological image in color by using T2* RelaxMap function. The T2* RelaxMap function consists of (a) acquisition of multi-echo images (up to 32) and (b) analysis of T2* relaxation time." |
  | Substantial Equivalence | Hardware, coils, and functionality are substantially equivalent to the predicate device in design features, fundamental scientific technology, indications for use, and safety and effectiveness. | "based on a thorough analysis and comparison of the functions, scientific concepts, physical and performance characteristics, performance comparison and technological characteristics, the proposed ECHELON Oval V5.0 MRI is considered substantially equivalent to the currently marketed predicate device (ECHELON Oval MRI System (K113145)) in terms of design features, fundamental scientific technology, indications for use, and safety and effectiveness." |

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

The document states:

• "Clinical images were collected and analyzed, to ensure that images from the new features meet user needs."
• "We provide clinical image examples for each new feature..."

However, the specific sample size (number of images or patients) used for the clinical test set is not provided in the document.

The data provenance is also not explicitly stated in terms of country of origin or whether it was retrospective or prospective. It only mentions "clinical images were collected," implying real patient data, but without further detail.

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

• Number of Experts: "A radiologist" (singular) validated the clinical images.
• Qualifications of Experts: The document specifies "a radiologist." No further details on their experience (e.g., "10 years of experience") are provided.

4. Adjudication Method for the Test Set

The document mentions "a radiologist validated" the images. This suggests a single expert review. There is no mention of an adjudication method such as 2+1, 3+1, or any multi-reader consensus process for the clinical images.

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 involving human readers with and without AI assistance was not done or reported in this submission. This submission is for a software update to an MRI system itself, not an AI-assisted diagnostic tool for readers. The "AI" features (like k-RAPID for image acceleration or certain processing tasks) are integrated into image acquisition and reconstruction, not designed to directly assist human interpretation in a comparative effectiveness study setting mentioned in the question.

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

The "Performance Evaluation" section indicates that both "Performance Testing - Clinical" and "Performance Testing - Bench" were conducted for the new features.

• Bench tests involved "phantom simulations," which represents an algorithm-only evaluation for the technical performance of specific sequences.
• Clinical tests involved collecting and analyzing clinical images, and "a radiologist validated" them. While a human reviewed the output, the core algorithms for the new features (e.g., ASL-Perfusion generating perfusion images, T2* RelaxMap creating maps) operate in a standalone manner to produce these outputs before human interpretation.

Therefore, standalone performance tests were conducted for the new features on phantoms, and the resulting clinical images were then validated by a radiologist. The focus was on the technical and image quality output of the new algorithms, not diagnostic accuracy in a standalone AI context compared to a ground truth.

7. The Type of Ground Truth Used

• For the bench tests (phantom simulations), the "ground truth" would be the known physical properties and configurations of the phantom, allowing for objective measurement of parameters like signal-to-noise ratio, geometric distortion, etc.
• For the clinical validation, the ground truth appears to be expert consensus or opinion from "a radiologist" who validated the "acceptable image quality for clinical use." There is no mention of pathology, outcomes data, or a multi-expert consensus forming the ground truth.

8. The Sample Size for the Training Set

The document does not describe the development or training of new algorithms in a way that suggests a "training set" in the context of machine learning. The enhanced features are described as software updates and new pulse sequences. Therefore, there is no information provided regarding a training set size. This submission focuses on the performance verification and validation of the software update, not the development process of, for example, a deep learning model.

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

Since no training set is mentioned in the context of machine learning algorithm development, this information is not applicable and not provided in the document. The document describes system updates and their performance validation.

Ask a specific question about this device

The Mobile X-ray Unit Sirius Starmobile tiara is a general radiography system and is composed of the X-ray high voltage generator, X-ray tube, support unit, and digital radiograph device (DR-ID 800) made by Fujifilm Corporation.

This device is designed for pediatric and adult patients.

It is intended for use in general radiography of the head, body, or extremities including pediatric exams. The device output can provide an aid to diagnosis when used by a qualified physician.

The Sirius Starmobile tiara battery powered, mobile x-ray system features a built-in Flat Panel Detector System: DR-ID800 which is a modification of the FDR D-EVO Flat Panel Detector System (DR-ID600), K132509. Because the Flat Panel Detector System is incorporated in the mobile equipment, the images are available to the technologist in a very short time, allowing the technologist to assure the exam has been performed adequately, minimizing return trips. Wireless communication is available, as an option, for updates to the patient worklist from the RIS/HIS.

The Sirius Starmobile tiara provides smooth and quiet motorized travel capability via rear wheels independently driven by dual motors, a versatile radiography range through the pantograph arm, and easy-to-operate positioning of flat detector providing sharp image quality with a short exam completion time.

The provided document is a 510(k) premarket notification letter for the Sirius Starmobile tiara, a mobile x-ray system. It does not contain information about acceptance criteria or a study proving its performance against such criteria for an AI/CAD/software device.

The document focuses on:

• Regulatory clearance: The FDA's determination of substantial equivalence to a predicate device (Carestream DRX-Revolution Mobile X-ray System, K120062).
• Device description and intended use: General radiography for head, body, or extremities for pediatric and adult patients.
• Non-clinical testing: Compliance with various IEC and AAMI ANSI standards related to medical electrical equipment, safety, electromagnetic compatibility, radiation protection, usability, and software life cycle processes.
• Technological characteristics comparison: Discussion of similarities and minor differences (e.g., target angle, anode heat capacity, detector pixel size) between the subject device and the predicate device, concluding overall substantial equivalence.
• Clinical testing snippet: Mentions "sample clinical images in Section 10 Performance" but provides no details on how they were used to define or meet acceptance criteria, study design, or metrics.

Therefore, I cannot extract the requested information (acceptance criteria, study details, sample sizes, ground truth, expert qualifications, etc.) as it is not present in the provided text. This document is a regulatory clearance letter, not a detailed performance study report.

Ask a specific question about this device

The TRILLIUM Oval MRI System is an imaging device, and is intended to provide the physiological and clinical information, obtained non-invasively and without the use of ionizing radiation. The MR system produces transverse, coronal, sagittal, oblique, and curved cross-sectional images that display the internal structure of the head, body, or extremities. The images produced by the MR system reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2), and flow. When interpreted by a trained physician, these images provide information that can be useful in diagnosis determination.

Anatomical Region: Head, Body, Spine, Extremities
Nucleus excited: Proton
Diagnostic uses: T1, T2, proton density weighted imaging, Diffusion weighted imaging, MR Angiography, Image processing, Spectroscopy, Whole Body

The TRILLIUM OVAL is a Magnetic Resonance Imaging System that utilizes a 2.9 Tesla superconducting magnet in a gantry design. The design was based on the ECHELON Oval MRI system. The TRILLIUM OVAL has been designed to enhance clinical utility as compared to the ECHELON Oval by taking advantage of the stronger magnetic field and stronger gradient field and slew rate.

The provided document is a 510(k) premarket notification for the "Trillium Oval MR System." It primarily focuses on demonstrating substantial equivalence to a predicate device and does not contain detailed information about acceptance criteria or a specific study proving the device meets those criteria in the context of diagnostic accuracy, particularly for AI/CADe systems.

This document describes a Magnetic Resonance Imaging (MRI) system, which is a diagnostic imaging device. The "acceptance criteria" discussed are largely related to safety and general performance standards for MRI systems, rather than specific diagnostic performance metrics (e.g., sensitivity, specificity) for a particular clinical application. The "study" refers to non-clinical and some clinical imaging tests to demonstrate that the device meets these engineering and safety standards.

Here's an analysis based on the provided text, addressing the requested points:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present a table of specific acceptance criteria with corresponding performance metrics in the format typically used for evaluating diagnostic accuracy (e.g., sensitivity, specificity, AUC). Instead, it lists non-clinical test standards and mentions that the device was subjected to these tests. The implication is that the device met these standards.

Regarding the Absence of AI/CADe Specifics:

It's crucial to note that this submission is for a Magnetic Resonance Imaging System (hardware and core software), not an Artificial Intelligence (AI) or Computer-Assisted Detection/Diagnosis (CADe/CADx) software. Therefore, the questions related to AI performance metrics (like sample sizes for test/training sets, expert ground truth adjudication for AI, MRMC studies, standalone algorithm performance, etc.) are not applicable to this specific document. The "device" here is the MRI scanner itself.

Specific Answers to Your Questions (where applicable for an MRI system submission):

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

   • Test Set Sample Size: The document mentions "sample clinical imaging of the head, torso, and extremities using all anatomy coils." It does not specify the number of subjects or images used for this clinical imaging.
   • Data Provenance: Not specified in the document (e.g., country of origin). The document implies these were internally generated as part of the submission process, likely prospective.

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)

   • This is not applicable in the context of this 510(k) submission for an MRI system. The "ground truth" for the clinical imaging mentioned would be the visual assessment by "trained physicians" (as mentioned in the indications for use) to confirm diagnostic quality, but the number and qualifications of evaluators are not specified.

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

   • Not applicable. This level of detail on ground truth adjudication is typically for AI/CADe performance studies, not for the submission of a core imaging device.

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 is not an AI/CADe device. Such a study was not performed or described.

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

   • No. This is not an AI/CADe device. The device is an MRI system, which always requires human operation and interpretation.

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

   • For the non-clinical tests (NEMA standards, SAR simulations), the "ground truth" is adherence to established engineering and safety specifications and theoretical models.
   • For the "sample clinical imaging," the implied ground truth is that the images generated are of sufficient diagnostic quality as determined by "trained physicians," comparable to the predicate device. This is a qualitative assessment of imaging capability rather than a definitive diagnosis of a specific condition against a gold standard like pathology.

8. The sample size for the training set

   • Not applicable. This is not an AI/CADe device that uses a "training set" in the machine learning sense.

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

   • Not applicable.

Ask a specific question about this device