Search Results

MOBILETT Elara Max is a mobile device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. MOBILETT Elara Max enables radio-graphic exposures of the whole body and may be used on pediatric. adult and bariatric patients. It can also be used for emergency applications. MOBILETT Elara Max is not indicated for mammographic imaging.

The MOBILETT Elara Max is a mobile X-ray system with a solid state x-ray imager (SSXI). The system is designed to provide X-ray imaging by healthcare professionals. Rechargeable batteries support cable less operation and motor-driven movements to the point of care. The mobile generator is positioned at bedside and the X-ray system is directed to the anatomical area to be imaged. The image detector is placed perpendicular to the central beam behind this anatomical area. The system features a collimator with a light field that mimics the x-ray field to limit the field of exposure to the area to be imaged. Exposure may be released via remote control. The image data acquired by the detector are send wireless to the mobile unit.

The purpose of this submission is a new software version VF10, some minor hardware changes and the new device name MOBILETT Elara Max. The new software VF10 will introduce the following new features:

• The operating system will be MS Windows 10
• New cybersecurity features
• Additional pediatric programs
• Implementing a "Virtual Machine" that supports hospital IT
• The SSXIs have been updated
• The EMC (Electromagnetic Compatibility was tested according to the IEC 4th edition)
• The image processing algorithms (Diamond View MAX) will be used for exposures without grid.
• The Mobilett Elara will be coated with an anti-microbial paint

The provided text is a 510(k) summary for the Siemens MOBILETT Elara Max, a mobile X-ray system. The document focuses on demonstrating substantial equivalence to a predicate device (MOBILETT MIRA), primarily through non-clinical testing and comparison of technical characteristics, particularly regarding a new software version (VF10) and minor hardware changes.

*Crucially, this document does not contain any information about an AI-powered medical device or a clinical study that establishes acceptance criteria and then proves the device meets those criteria using expert consensus, MRMC studies, or specific performance metrics like sensitivity/specificity.

The device, MOBILETT Elara Max, is a standard X-ray imaging system. The updates described (new software, cybersecurity features, updated SSXIs, antimicrobial paint) are enhancements to the existing X-ray system, not features that introduce AI for diagnostic interpretation or require a clinical study with expert readers to establish diagnostic performance.

Therefore, I cannot fulfill your request to describe acceptance criteria and a study proving an AI device meets them based on the provided text. The document is primarily a regulatory submission demonstrating substantial equivalence for a conventional medical imaging device.

Ask a specific question about this device

The MULTIX Impact system is a radiographic system used in hospitals, clinics, and medical practices. MULTIX Impact enables radiographic exposures of the whole body including: skull, chest, abdomen, and extremities and may be used on pediatric, adult and bariatric patients. Exposures may be taken with the patient sitting, standing, or in the prone position. The MULTIX Impact system is not meant for mammography.

The MULTIX Impact uses digital detectors for generating diagnostic images by converting x-rays into image signals. The MULTIX Impact is also designed to be used with conventional film/screen or Computed Radiography (CR) cassettes.

The MULTIX Impact Radiography X-ray system is a modular system of X-ray components (floor-mounted X-ray tube, Bucky wall stand, Bucky table, X-ray generator, portable wireless detectors) similar to the predicate the Multix Fusion Max. This 510(k) submission describes modifications to the predicate device the Multix Fusion Max cleared via K162971. The following modifications have been made to the cleared predicate device and the new system will be branded the MULTIX Impact:

1. A new 43x35cm Wireless detector, 3543DR 1.
2. A new X-ray tube and a new generator
3. An optional 40 line grid with grid suppression algorithm
4. Wireless Remote Control Console
5. An optional All-in-one PC containing touch screen function
6. An optional positioning assistance camera
7. Upgrade software to VA10
8. Upgrade operator system from Windows XP to Windows 10

The Siemens MULTIX Impact X-ray system is a modification of the predicate device, the Multix Fusion Max (K162971). The submission focuses on demonstrating substantial equivalence rather than presenting an effectiveness study for a new clinical claim. Therefore, the information provided primarily concerns performance testing to confirm that the modifications do not negatively impact safety or effectiveness.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a submission demonstrating substantial equivalence to a predicate device for an X-ray system, the acceptance criteria are generally focused on demonstrating that various component modifications do not degrade performance below the predicate's established levels, and that the device meets relevant safety and performance standards. Formal "acceptance criteria" for a specific clinical task are not explicitly stated for the device as a whole in the way they would be for a diagnostic AI algorithm. Instead, the comparison is to the predicate and established standards.

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

The document describes modifications to an existing X-ray system and its components. The "test set" here refers to the actual physical device and its components undergoing verification and validation testing, rather than a dataset of medical images for a diagnostic algorithm.

• Sample Size for Test Set: Not applicable in the context of a dataset of cases. The testing was performed on the MULTIX Impact system itself and its components.
• Data Provenance: Not applicable in the clinical data sense. The testing is described as "Non-clinical tests... during product development" and "testing for verification and validation." This implies internal testing by the manufacturer.

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

Not applicable. This is not a study requiring expert clinical read-outs for ground truth. The "ground truth" for this submission is adherence to technical specifications, performance standards (like DQE, MTF), and safety requirements, which are evaluated by engineering and quality control processes.

4. Adjudication Method for the Test Set

Not applicable. There is no mention of clinical image adjudication for ground truth establishment. Technical performance and safety are verified through engineering tests.

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 study was performed or is mentioned. This submission is for an X-ray system, not an AI-powered diagnostic device, and it focuses on demonstrating substantial equivalence of modified hardware and software components, not on comparative effectiveness with human readers.

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

Not applicable. The device is an X-ray system, which is inherently used with human operators. There is no "algorithm only" performance claim. The software modifications are part of the overall X-ray system's functionality.

7. The Type of Ground Truth Used

The "ground truth" for this submission relates to:

• Technical Specifications: Ensuring components meet their specified performance parameters (e.g., DQE, MTF for the detector, power output for the generator).
• Compliance with Standards: Verification that the device adheres to recognized national and international standards (IEC, ISO, NEMA).
• Safety and Effectiveness: Demonstration that modifications do not introduce new safety risks or degrade the overall effectiveness of the predicate device, as evaluated through risk analysis and functional testing.

8. The Sample Size for the Training Set

Not applicable. This is not an AI/machine learning device that requires a training set of data.

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

Not applicable, as there is no training set for an AI algorithm.

Ask a specific question about this device

Ysio Max is a device intended to visualize anatomical structures by converting an X-ray pattern into a visible image. Ysio Max enables radiographic and tomographic exposures of the whole body and may be used on pediatric, adult and bariatric patients. It can also be used for emergency applications.

Ysio Max is not for mammography examinations.

The Ysio Max is a stationary X-ray system for radiography. The main components are the X-ray generator, the X-ray tube with collimator supported by a ceiling rail system. The Ysio Max comes with SSXIs (Solid State X-ray Imagers) that can be mobile or fixed in the Bucky tray. An image processing and data management system (syngo FLC) completes the radiographic suite.

The purpose of this submission is the upgrade to a new software version VF10 and minor hardware changes. The modified Yisio Max will introduce the following new features:

• The operating system will be MS Windows 10
• New cybersecurity features
• Additional pediatric programs
• Implementing a "Virtual Machine" that supports hospital IT
• The SSXIs have been updated
• The EMC (Electromagnetic Compatibility was tested according to the IEC . 4th edition)
• . The image processing algorithms (Diamond view Plus) will be used for exposures without grid.

The provided text is a 510(k) premarket notification for a medical device called Ysio Max. It focuses on demonstrating substantial equivalence to a predicate device after a software upgrade (VF10) and minor hardware changes.

Based on the provided document, the device (Ysio Max with VF10 software) is a stationary X-ray system, not an AI/ML-powered device for which acceptance criteria typically involve performance metrics like sensitivity, specificity, or AUC.

Therefore, the acceptance criteria and study detailed in the document are primarily related to demonstrating that the updated device maintains the same safety and effectiveness as its predicate device and complies with relevant performance standards, rather than proving a specific diagnostic accuracy or improvement in human reader performance using AI assistance.

Here's a breakdown of the information as it applies to this specific submission, addressing your points where relevant:

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

The acceptance criteria are implicitly tied to demonstrating continued substantial equivalence to the predicate device and compliance with applicable industry standards and FDA regulations. Performance is reported through comparisons to the predicate and confirmation of adherence to standards.

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

• Test Set Sample Size: The document does not specify a "test set" in the context of an AI/ML algorithm being evaluated on a dataset of patient cases. Instead, the testing is described as verification and validation (V&V) testing of the software and hardware components, and performance measurements of the X-ray detectors against technical specifications. These are engineering and performance tests, not clinical studies on a patient cohort for diagnostic AI.
• Data Provenance: Not applicable in the context of diagnostic data for AI. The testing is internal to the manufacturer.

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

• Not applicable as this is not an AI/ML diagnostic system requiring expert interpretation as ground truth. The "ground truth" for the device's performance is adherence to engineering specifications and regulatory standards.

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

• Not applicable. This is not a study involving human reader interpretations of medical images that would require adjudication.

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 study was not done. The document explicitly states: "For the subject of this premarket submission, Siemens did not do an evaluation of the clinical image quality as X-ray technology; geometry and SSXI changes are minor." This device is an X-ray system itself, not an AI assistant intended to improve human reader performance.

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

• Not applicable. The Ysio Max is a medical imaging device (a stationary X-ray system), not a standalone diagnostic algorithm. Its performance is measured by its ability to generate images and comply with technical and safety standards.

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

• The "ground truth" for this submission is based on engineering specifications, compliance with standardized test methods (e.g., IEC standards for electrical safety, EMC, radiation protection), and measurable physical characteristics of the detectors (DQE, MTF). It's a technical "ground truth" rather than a clinical diagnostic one.

8. The sample size for the training set:

• Not applicable. This is not an AI/ML device that requires a training set of data.

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

• Not applicable for the same reason mentioned above.

Ask a specific question about this device

The MAMMOMAT Revelation is intended to be used for mammography exams, screening, diagnostics, biopsies and dual energy procedures under the supervision of medical professionals. The Mammography images can be inter hard copy film or soft copy workstation.

With Biopsy Option:

The InSpect feature for MAMMOMAT Revelation with HD Biopsy options is intended to provide digital X-ray images of core biopsy specimens in order to allow rapid verification that the correct tissue has been excised with the biopsy procedure.

MAMMOMAT Revelation is a floor-mounted full field digital mammography system for screening, diagnostic and biopsy procedures on standing, seated or recumbent patients.

The system consists of an examination stand with X-ray generator, a gantry with tube housing assembly and mammography support table including detector, and an acquisition workstation with a radiation shield. The MAMMOMAT Revelation comes with a variety of compression plates and a biopsy attachment for diagnostic adjunct procedures.

The MAMMOMAT Revelation features an updated detector (LMAM 2v2), an upgrade to the MS Windows 10 operating system, the capability to do contrast enhanced mammography and tomosynthesis guided biopsy.

The Siemens MAMMOMAT Revelation device was evaluated in non-clinical bench tests. Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Size and Data Provenance for Test Set:

The provided document does not specify the sample size used for the test set or the data provenance (e.g., country of origin, retrospective or prospective) for the bench tests. These tests are non-clinical and conducted in a laboratory setting.

3. Number of Experts and Qualifications for Ground Truth of Test Set:

Not applicable. The tests described are bench tests focused on technical performance metrics (detector characteristics, image quality, targeting accuracy) and do not involve human readers or expert-established ground truth in the traditional sense of a clinical study. The "ground truth" for these tests would be the established physical and technical specifications or reference measurements.

4. Adjudication Method for Test Set:

Not applicable. As these are bench tests, an adjudication method for human interpretation is not relevant. The results are based on direct measurement and comparison against defined technical criteria.

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

No. The document describes non-clinical bench tests. There is no mention of an MRMC comparative effectiveness study involving human readers.

6. Standalone (Algorithm Only) Performance:

The document describes tests of the physical device's characteristics and its features. It does not specifically detail a "standalone" algorithm performance study without a human-in-the-loop, as the device is a medical imaging system. The "algorithm" here would refer to the internal image processing and AEC calculations, which are components of the system test.

7. Type of Ground Truth Used:

The ground truth for these non-clinical tests is based on:

• Established specifications and performance of the predicate device (for detector characteristics).
• Defined technical standards and internal system test records (for dual energy image quality).
• Physical measurements against a known target in a phantom (for targeting accuracy).

8. Sample Size for Training Set:

Not applicable. The document describes tests for a medical imaging device, not an AI or machine learning algorithm that typically requires a separate training set. The "MAMMOMAT Revelation" is a physical mammography system.

9. How Ground Truth for Training Set Was Established:

Not applicable, as there is no mention of a separate training set for an AI algorithm.

Ask a specific question about this device

The MAGNETOM systems [MAGNETOM Avantofit, MAGNETOM Skyrafit] are indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and/or spectra, and that displays the internal structure and/or function of the head, body, or extremities.

Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These images and/or spectra and the physical parameters derived from the images and/or spectra, when interpreted by a trained physician, yield information that may assist in diagnosis.

The MAGNETOM systems may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room display and MR-Safe biopsy needles.

Not Found

This document is a letter from the FDA to Siemens Medical Solutions USA, Inc. regarding their 510(k) premarket notification for the MAGNETOM Avanto and MAGNETOM Skyra devices. It confirms the substantial equivalence of these magnetic resonance diagnostic devices.

The document does not contain any information about acceptance criteria, device performance, a specific study, sample sizes, expert qualifications, adjudication methods, multi-reader multi-case studies, standalone performance, or ground truth establishment.

Therefore, I cannot provide the requested information based on the provided text.

Ask a specific question about this device

The ACUSON Freestyle™ Utrasound System is intended for diagnostic imaging or fluid flow analysis of the human body including: Fetal. Abdominal, Intraoperative Neurological, Pediatric, Small Organ. Neonatal Cephalic. Cardiac, Peripheral Vessel, Musculoskeletal (Conventional), Musculoskeletal Superficial.

The ACUSON Freestyle™ Ultrasound System is an ultrasound imaging system, which operates with linear, curvilinear, array transducers. The transducers may be used in either a wireless or wired configuration through a cable connected to the system.

The provided text is a 510(k) summary for the ACUSON Freestyle™ Ultrasound System, detailing its substantial equivalence to previously cleared predicate devices. It focuses on the device's technical characteristics, intended use, and compliance with various safety standards.

However, the document explicitly states that "clinical data is not required for substantial equivalence." This means it does not contain information about specific acceptance criteria related to device performance in a clinical setting, nor does it describe a study that proves the device meets such criteria.

Therefore, I cannot provide the information requested in your prompt regarding acceptance criteria and performance studies, including sample size, data provenance, ground truth establishment, or multi-reader multi-case studies, because this type of clinical performance data is not present in the provided text.

The document mainly focuses on comparing the new device's technical specifications and intended uses to those of predicate devices to demonstrate substantial equivalence, rather than providing performance metrics from clinical trials.

Ask a specific question about this device

The ultrasound imaging systems are intended for the following applications: Fetal, Abdominal, Intraoperative, Pediatric, Small Parts, Transcranial, OB/GYN, Cardiac, Pelvic, Neonatal/Adult Cephalic, Vascular, Musculoskeletal, Superficial Musculoskeletal, and Peripheral Vascular applications.

The system also provides the ability to measure anatomical structures {fetal, abdominal, intraoperative, small organ, neonatal cephalic, adult cephalic, trans-esophageal, transvaginal, peripheral vessel, musculoskeletal (conventional), musculo-skeletal (superficial) and calculation packages that provide information to the clinician that may be used adjunctively with other medical data obtained by a physician for clinical diagnosis purposes.

The Arterial Health Package (AHP) software provides the physician with the capability to measure Intima Media Thickness and the option to reference normative tables that have been validated in peer-reviewed studies. The information is intended to provide the physician with an easily understood tool for communicating with patients regarding state of their cardiovascular system. This feature should be utilized according to the "ASE Consensus Statement; Use of Carotid Ultrasound to Identify Subclinical Vascular Disease and Evaluate Cardiovascular Disease Risk: A Consensus Statement from the American Association of Echocardiography; Carotid Intima-Media Thickness Task Force, Endorsed by the Society for Vascular Imaging".

The Acuson Acunav Ultrasound Catheter is intra-cardiac and intra-luminal visualization of cardiac and great vessel anatomy and physiology, as well as visualization of other devices in the heart of adult and pediatric patients.

The ultrasound systems are multi-purpose mobile, software controlled diagnostic ultrasound systems with and on-screen display for thermal and mechanical indices related to potential bio-effect mechanisms. The function is to acquire primary or secondary harmonic ultrasound echo data and display it in B-Mode, Pulsed (PW) Doppler Mode, Continuous (CW) Doppler Mode, Color Doppler Mode, Amplitude, Doppler Mode, a combination of modes, or Harmonic Imaging and 3D/4D Imaging on a Flat Panel Display.

This document is a 510(k) Summary for the Siemens Medical Solutions ACUSON S1000, S2000, S3000 Diagnostic Ultrasound System. It asserts substantial equivalence to previously cleared devices (K152369) and does not describe acceptance criteria or a study proving the device meets specific acceptance criteria in the typical sense of a novel algorithm with performance metrics.

Instead, the submission focuses on demonstrating that the modified systems have the same intended use and technological characteristics as their previously cleared counterparts, and that they conform to established medical device safety standards. Therefore, the "acceptance criteria" here refer to conformance with those safety standards and the equivalence of intended use and technological features.

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

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

The document does not present quantitative acceptance criteria or performance metrics for a novel algorithm. Instead, it asserts equivalence to previously cleared devices and compliance with general safety and performance standards.

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

Not applicable. This submission is for an updated version of a previously cleared device, not a novel AI algorithm requiring a new clinical performance study with a test set of patient data. The non-clinical tests mentioned (e.g., electrical safety, biocompatibility) do not typically involve patient data test sets with provenance.

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. As noted above, this submission relies on demonstrating equivalence to an existing device rather than a clinical performance study with expert-established ground truth.

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

Not applicable. No new clinical performance study was conducted that would require adjudication.

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. No MRMC study was done, as this is a 510(k) for an updated ultrasound system, not an AI-powered diagnostic aide requiring a comparative effectiveness study. The document explicitly states: "Since the S1000, S2000, S3000 systems in this submission use the same technology and principles as existing devices, clinical studies were not required to support substantial equivalence."

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

Not applicable. This is not an AI algorithm with standalone performance being evaluated. It's a diagnostic ultrasound system.

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

Not applicable. New clinical ground truth was not established for this 510(k) submission. The safety and performance are based on compliance with standards and equivalence to the predicate device.

8. The sample size for the training set

Not applicable. There is no mention of an AI algorithm or a training set in this submission.

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

Not applicable. There is no mention of an AI algorithm or a training set in this submission.

Ask a specific question about this device

ADMIRE is a CT reconstruction software. The end user can choose to apply either ADMIRE or the weighted filter back-projection (WFBP) to the acquired raw data. Depending on the clinical task, patient size, anatomical location, and clinical practice, the use of ADMIRE can help to reduce radiation dose while maintaining pixel noise, low contrast detectability and high contrast resolution.

Phantom measurements showed that high contrast resolution is equivalent or improved and pixel noise is equivalent between full dose WFBP images and reduced dose ADMIRE images. Additionally, ADMIRE can reduce spiral artifacts by using iterations going back and forth between image space and raw data space.

Images reconstructed with ADMIRE are not intended to be evaluated with syngo Osteo CT or syngo Calcium Scoring.

ADMIRE is an iterative reconstruction option designed to be used on Siemens currently marketed and future CT devices. Its use has been previously cleared by FDA (K133646, clearance date June 20, 2014). No modifications were made to the algorithm or to the implementation of the feature. The changes proposed within this 510(k) only pertain to an extension of the claims associated with the feature as follows:

• 1. Compared to images reconstructed with WFBP, ADMIRE may simultaneously enable*
  • 80 to 85% dose reduction at the same image quality and .
  • 73 to 77% image noise reduction at the reduced dose and o
  • up to 42% improved high-contrast spatial resolution improvement at reduced o dose and reduced image noise.
• 2. Alternatively, ADMIRE may enable
  • up to 150% improved low contrast detectability (factor 2.5) at the same dose or .
  • up to 90% image noise reduction at constant dose or .
  • up to 87% improved high-contrast spatial resolution improvement at 85% . reduced dose and constant image noise or
  • up to 38% improved high-contrast resolution at 90% reduced image noise and . constant dose.

Furthermore, the following claims have previously been cleared by FDA as part of K133646 (clearance date June 20, 2014) and will be maintained with this clearance:

• 3. Additionally, ADMIRE
  • compared to SAFIRE potentially features a more "FBP-like" noise texture in . terms of the number of "outliers" in the noise texture, especially for higher strength settings of the algorithm and
  • can reduce spiral artifacts by using iterations going back and forth between image 0 space and raw data space and
  • has the potential to result in a higher noise reduction compared to SAFIRE when . reconstructing thick slices.

• Image quality as defined by low contrast detectability using a model observer method for evaluation. Equivalent low contrast detectability can be achieved with 80% to 85% less dose using ADMIRE at highest strength level for thin (0.6 mm) reconstruction slices in measured and simulated body and head phantoms for low contrast objects with different contrasts. See ADMIRE data sheet for further information.

In clinical practice, the use of ADMIRE may reduce CT patient dose depending on the clinical task, patient size, anatomical location, and clinical practice. A consultation with a radiologist and a physicist should be made to determine the appropriate dose to obtain diagnostic image quality for the particular clinical task.

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

Acceptance Criteria and Device Performance Study for ADMIRE

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes performance claims rather than explicit acceptance criteria with specific thresholds for FDA clearance in this section. However, based on the claims being extended and previous clearance, the reported performance is presented below. The "acceptance criteria" are implied by the performance metrics Siemens seeks to claim.

*Image quality defined by low contrast detectability using a model observer method for evaluation.

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

• Sample Size for Test Set: The document mentions "a large number of CT images" were generated for evaluation by using "computer-simulated as well as measured CT data." However, specific numerical sample sizes are not provided for either the simulated or measured data used in the testing.
• Data Provenance: The study utilized "PhantomLabs® CCT189 and CCT191 phantoms" for low-contrast detectability and a "Teflon edge phantom" for high-contrast spatial resolution. This indicates the testing was conducted using phantom data, not human patient data. There is no information on the country of origin of the data, but it is clear it is retrospective (in the sense of being pre-generated data/scans for evaluation) rather than prospective human trials.

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

• The document does not mention the involvement of experts for establishing ground truth in the context of the phantom-based performance evaluation. The evaluation methods described (model observer for LCD, standard deviation for noise, ImPACT CT evaluation group definition for spatial resolution) are quantitative, objective measurements from the phantom images rather than expert interpretation.

4. Adjudication Method for the Test Set:

• Not applicable. Since the ground truth for the test set was established through objective phantom measurements and model observer studies, there was no need for expert adjudication.

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

• No, an MRMC comparative effectiveness study was not done. The device's performance was evaluated using phantom measurements and model observer studies, focusing on quantitative image metrics rather than human reader performance with or without AI assistance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

• Yes, a standalone study was performed. The evaluations of low-contrast detectability, image noise, and high-contrast spatial resolution were conducted on images reconstructed by the ADMIRE algorithm, comparing its output to WFBP reconstructed images or SAFIRE, using objective metrics derived directly from the images. This did not involve a human-in-the-loop component for performance evaluation.

7. Type of Ground Truth Used:

• The ground truth used was phantom-based objective measurements. For low-contrast detectability, a "model observer method" was used. For image noise, "standard deviation across images at all pixel locations" was computed. For high-contrast spatial resolution, it was based on "measured CT data of a Teflon edge phantom as defined by the ImPACT CT evaluation group."

8. Sample Size for the Training Set:

• The document does not provide information on the sample size for the training set for the ADMIRE algorithm. It focuses on the validation of its performance.

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

• The document does not provide information on how the ground truth for the training set was established. Since ADMIRE is an iterative reconstruction algorithm, its training (if applicable, as some iterative methods are rule-based or optimized rather than "trained" in a deep learning sense) would likely involve various simulated or measured data with known properties to optimize the reconstruction parameters. However, the details are not explicitly stated in this summary.

Ask a specific question about this device

The MAGNETOM systems are indicated for use as magnetic resonance diagnostic devices (MRDD) that produce transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and/or spectra, and that display the internal structure and/or function of the head, body or extremities.

Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These images and/or spectra and the physical parameters derived from the images and/or spectra when interpreted by a trained physician, yield information that may assist in diagnosis.

The MAGNETOM systems described above may also be used for imaging during interventional procedures when performed with MR compatible devices such as in-room display and MR-Safe biopsy needles.

The subject device, syngo MR E11C system software, is being made available for the following MAGNETOM MR Systems:

• MAGNETOM Aera,
• MAGNETOM Skyra, ●
• MAGNETOM Prisma and
• MAGNETOM Prisma™ ●

The syngo MR E11C SW includes new sequences. new features and minor modifications of already existing features.

The provided text describes a 510(k) premarket notification for new software (syngo MR E11C) for Siemens MAGNETOM MR systems. However, it does not contain the detailed information required to answer all aspects of your request regarding acceptance criteria and a study proving device performance as typically expected for AI/ML device submissions.

This submission is for a software update to existing Magnetic Resonance Diagnostic Devices (MRDDs), and the focus is on demonstrating substantial equivalence to previously cleared predicate devices. The "study" mentioned is primarily non-clinical performance testing and software verification/validation, rather than a clinical study with acceptance criteria for specific diagnostic outcomes.

Here's an attempt to extract and infer information based on the provided text, highlighting what is present and what is missing:

1. Table of acceptance criteria and the reported device performance

The document does not explicitly state quantitative acceptance criteria for diagnostic performance or specific metrics. Instead, it relies on demonstrating that the new software's features perform "as intended" and maintain "equivalent safety and performance profile" compared to predicate devices.

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

• Test Set Sample Size: "Sample clinical images were taken for particular new and modified sequences." The specific number or characteristics of these images (sample size) is not provided.
• Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It only mentions "sample clinical images," suggesting clinical data was used for assessment.

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. The document states "Image quality assessments... were completed," but does not detail who performed these assessments or how ground truth was established for them. For a diagnostic device, interpretation by a "trained physician" is mentioned in the Indications for Use, but this is a general statement about the device's usage, not specific to the assessment of the new software.

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: "No clinical tests were conducted to support the subject device and the substantial equivalence argument..."
• This submission is not for an AI-enhanced diagnostic tool in the sense of providing automated interpretations or assisting human readers in a measurable way with specific diagnostic outcomes. It's an update to MR imaging acquisition software. Therefore, the concept of "how much human readers improve with AI vs without AI assistance" does not apply in this context.

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

• The device is a Magnetic Resonance Diagnostic Device (MRDD) software update. Its output is images and/or spectra that are "interpreted by a trained physician" to "assist in diagnosis." As such, it is inherently a human-in-the-loop system. The non-clinical tests involved "Image quality assessments" and "Acoustic noise measurements," which are performance evaluations of the acquisition capabilities, not a standalone diagnostic interpretation by the algorithm.
• Therefore, a standalone diagnostic performance evaluation (algorithm only) in the context of providing a diagnosis was not performed or described.

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

• For "Image quality assessments," the type of ground truth is not explicitly stated. It can be inferred that it would likely involve visual assessment by experts against what is considered normal or expected for an MR image, potentially comparing to images acquired with predicate software or known anatomical/pathological features. However, specific ground truth methods like pathology or long-term outcomes data are not mentioned.

8. The sample size for the training set

• The document does not mention a separate training set or details about its size. This submission focuses on software changes and their verification, not on the development of a new AI model that requires a distinct training phase.

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

• Since a separate training set is not mentioned, the method for establishing its ground truth is also not provided.

Summary of what's present and what's missing:

This 510(k) submission primarily focuses on demonstrating that new software features (like quiet diffusion imaging, improved fast TSE, simultaneous multi-slice imaging, and a short acquisition time brain examination protocol) for existing MR systems maintain the fundamental technological characteristics, safety, and effectiveness of predicate devices. The "study" here is a series of non-clinical tests (image quality review, acoustic noise measurements, software V&V) rather than a clinical trial measuring diagnostic accuracy or reader performance. The level of detail you're asking for, especially concerning clinical study design elements like sample size, expert reader qualifications, adjudication methods, and ground truth establishment for diagnostic output, is typically found in submissions for AI/ML diagnostic tools that directly interpret images or provide diagnostic assistance, which is not the primary claim of this particular device update.

Ask a specific question about this device

For ACUSON NX3
The ACUSON NX3 ultrasound imaging system, is intended for the following applications: Fetal, Abdominal (including liver), Pediatric, Small Parts(Small Organ), Transcranial, OB/GYN, Pelvic, Neonatal, Cardiac, Vascular(including Peripheral Vessel), Musculoskeletal, Superficial Musculoskeletal and Urology applications. The systems also provide for the measurement of anatomical structures and for analysis packages that provide information that is used for clinical diagnosis purposes.

Ultrasound is used as an imaging aid, but may have further restrictions specific to in-vitro fertilization (IVF), chorionic villus sampling (CVS), and percutaneous umbilical cord blood sampling (PUBS) procedures. Observe local laws and regulations.

For ACUSON NX3 Elite
ACUSON NX3 Elite ultrasound imaging systems are intended for the following applications: Fetal, Abdominal (including liver, intra-operative), Pediatric, Small Parts(Small Organ including intra-operative), Transcranial, OB/GYN, Pelvic, Neonatal, Cardiac, Vascular(including Peripheral Vessel, intra-operative), Musculoskeletal, Superficial Musculoskeletal and Urology applications. The systems also provide for the measurement of anatomical structures and for analysis packages that provide information that is used for clinical diagnosis purposes.

Ultrasound is used as an imaging aid, but may have further restrictions specific to in-vitro fertilization (IVF), chorionic villus sampling (CVS), and percutaneous umbilical cord blood sampling (PUBS) procedures. Observe local laws and regulations.

The Arterial Health Package (AHP) software provides the physician with the capability to measure Intima Media Thickness and the option to reference normative tables that have been validated and published in peer-reviewed studies. The information is intended to provide the physician with an easily understood tool for communicating with patients regarding state of their cardiovascular system. Note: This feature can be utilized according to the "ASE Consensus Statement; Use of Carotid Ultrasound to Identify Subclinical Vascular Disease and Evaluate Cardiovascular Disease Risk: A Consensus Statement from the American Society of Echocardiography Carotid Intima-Media Thickness Task Force. Endorsed by the Society for Vascular Medicine."

The Siemens ACUSON NX3 Elite™ and ACUSON NX3™ Diagnostic Ultrasound Systems are multi-purpose mobile, software controlled, diagnostic ultrasound systems with an on-screen display for thermal and mechanical indices related to potential bio-effect mechanisms. Its function is to acquire harmonic ultrasound echo data and display it in B-Mode, Pulsed (PW) Doppler Mode, Continuous (CW) Doppler Mode, Color Doppler Mode, Color M mode, Tissue Doppler Image, Amplitude Doppler Mode, a combination of modes, or Harmonic Imaging and 3D Imaging, or Harmonic Imaging and 4D imaging on a Flat Panel Display.

This document is a 510(k) premarket notification for the ACUSON NX3 Elite and ACUSON NX3 Diagnostic Ultrasound Systems by Siemens Medical Solutions USA, Inc. As such, it primarily focuses on establishing "substantial equivalence" to predicate devices rather than providing detailed acceptance criteria and performance studies in the way you might find for novel AI/ML devices.

Therefore, the information you requested regarding acceptance criteria and study details to prove the device meets them is largely based on demonstrating equivalence to existing, legally marketed ultrasound systems, and general safety and performance standards, rather than specific performance metrics for a new AI feature. The document explicitly states: "Since the ACUSON NX3 Elite™ and ACUSON NX3™ Diagnostic Ultrasound Systems use the same technology and principles as existing devices, clinical data is not required." This means there won't be a study demonstrating the device meets specific performance criteria in the sense of a new technology needing to prove its efficacy.

However, I can extract the information related to the device's characteristics and the basis for its clearance:

1. Table of Acceptance Criteria and Reported Device Performance:

Based on the document, the "acceptance criteria" are implied by demonstrating substantial equivalence to predicate devices (ACUSON X700™ Diagnostic Ultrasound System (K141846) and ACUSON X300™ Diagnostic Ultrasound System (K121699)) and adherence to recognized safety standards. The "reported device performance" is essentially that it functions similarly to the predicate devices across a range of applications and modes.

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

• Sample Size: Not applicable in the context of efficacy studies for this type of 510(k). The clinical performance is inferred from the established safety and efficacy of the predicate devices. The document does mention "nonclinical tests" for safety and standards compliance, but does not provide specific sample sizes for these tests (e.g., number of units tested for electrical safety).
• Data Provenance: Not applicable. The FDA's basis for substantial equivalence for this diagnostic ultrasound system does not rely on a new clinical study with a specific test set. It relies on technological comparison to predicate devices and adherence to recognized performance standards. If clinical data were used from predicate devices, their provenance would be relevant, but this is not mentioned.

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

• Not applicable. No ground truth establishment by experts for a novel efficacy claim is described or needed for this 510(k) submission as it relies on substantial equivalence to existing technology. The "ground truth" for the predicate devices' efficacy would have been established historically through their own development and clearance processes.

4. Adjudication Method for the Test Set:

• Not applicable. There is no mention of a test set requiring adjudication in this 510(k) 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 document pertains to the clearance of a diagnostic ultrasound system and its transducers, which are imaging devices. It does not describe an AI-powered diagnostic algorithm or a clinical study that would involve human readers and AI assistance. The "Arterial Health Package (AHP) software" mentioned for the ACUSON NX3 Elite is described as providing "the capability to measure Intima Media Thickness and the option to reference normative tables that have been validated and published in peer-reviewed studies," not as an AI requiring a MRMC study for improved human reading.

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

• Not applicable. This is a 510(k) for an ultrasound imaging system, not a standalone algorithm.

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

• Not applicable for a new efficacy claim. For the purposes of this 510(k), the "ground truth" for demonstrating substantial equivalence is the comprehensive body of knowledge and regulatory clearance history associated with the predicate devices and general ultrasound technology, as well as adherence to established medical device safety and performance standards (e.g., IEC, ISO, AIUM/NEMA).

8. The Sample Size for the Training Set:

• Not applicable. This submission describes the clearance of an imaging hardware system, not a machine learning model that would require a training set.

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

• Not applicable. As there is no machine learning model or training set described in this 510(k) submission, this question is not relevant.

Ask a specific question about this device