Search Results

AutoAS is a software application intended to assist medical professionals in the assessment of moderate/severe aortic stenosis (AS). The software uses an artificial intelligence (AI) algorithm to process previously acquired two-dimensional transthoracic echocardiography (2D-TTE) images to provide a suggestion of moderate/severe aortic stenosis along with an associated confidence metric that can be a diagnostic aid to a physician in a point of care or similar setting in determining if further evaluation is needed, including whether a full echocardiogram (2D, Doppler) needs to be performed.

The results of AutoAS are not intended to be used on a stand-alone basis for clinical decision making and are not intended to supplement or replace a full echocardiographic examination. AutoAS results, along with the obtained ultrasound images, must be reviewed by a qualified physician. The AutoAS product is not intended to be used on patients who have prosthetic valves and/or have had prior valve repair or replacement.

AutoAS software is indicated for use in adult patients and is intended to be an accessory to compatible ultrasound systems in environments where healthcare is provided.

Automated Aortic Stenosis Software (AutoAS) is a breakthrough software product that assesses the presence and severity of aortic stenosis (AS) in B-mode cardiac ultrasound scans. The software can be integrated with a compatible ultrasound device in a headless manner. The AutoAS software is intended to be an accessory to compatible ultrasound systems. The AutoAS software is intended for use in adult patients undergoing transthoracic cardiac ultrasound examinations in whom assessment for aortic stenosis (AS) is clinically relevant. The indicated population includes patients who are being evaluated for the presence or likelihood of moderate to severe aortic stenosis as part of a routine or targeted echocardiographic study.

AutoAS processes relevant ultrasound images acquired from a concurrent and/or previously acquired ultrasound exam, employing advanced algorithms to generate AS predictions and supporting outputs for the user. The AutoAS software operates on B‑mode transthoracic cardiac ultrasound images acquired during a standard ultrasound examination using a compatible GE HealthCare ultrasound system. The reading protocol is designed to ensure that AutoAS outputs are used as adjunctive information and are interpreted within the context of a comprehensive clinical and echocardiographic evaluation by a qualified physician. The AS prediction, severity, and supporting outputs are summarized as a report that is available after the exam for the user to review. The report can also be exported to an archive with the ultrasound images ensuring seamless integration with the patient's record and facilitating downstream clinical workflows.

The software's algorithms process specific views obtained during an ultrasound study. These views may include the parasternal long axis (PLAX), parasternal short axis at the aortic valve level (PSAX-AV), and apical five-chamber (AP5). The AS predictions come in the form of a severity prediction: 1) Suggestive of moderate to severe AS or 2) Not suggestive of moderate to severe AS with associated information on the confidence of the algorithm's prediction.

The AutoAS results along with ultrasound images must be reviewed by a qualified physician as the AutoAS software does not diagnose Aortic Stenosis (AS) but rather indicates the likelihood of AS. Interpretation of AutoAS results must be performed by a qualified physician with training and experience in cardiac ultrasound and echocardiographic interpretation. The results of AutoAS are not intended to be used on a stand-alone basis for clinical decision making and are not intended to supplement or replace a full echocardiographic examination. The physician must review the AutoAS outputs in conjunction with the underlying ultrasound images and relevant clinical information. The user is responsible for determining the clinical relevance of the AutoAS findings and for integrating the software outputs into the overall diagnostic impression.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Standalone Performance Assessment:
  • Sample Size: 401 studies from 401 unique patients.
  • Data Provenance: Retrospectively obtained from four different U.S. institutions. The dataset included echocardiographic studies from multiple ultrasound models from two different manufacturers (GE Healthcare and Philips Healthcare).
• Clinical Performance Assessment (MRMC Study):
  • Sample Size: A subset of 220 unique studies across 220 unique patients from the validation data used in the standalone performance assessment.
  • Data Provenance: Retrospectively obtained from three different U.S. institutions (implies these are also U.S. institutions, similar to the larger validation dataset).

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

• Number of Experts: Three (3) level-III echocardiographers.
• Qualifications of Experts: Described as "level-III echocardiographers," indicating a high level of expertise and experience in echocardiography interpretation.

4. Adjudication Method for the Test Set

• Adjudication Method: Majority vote of the 3 echocardiographers (also known as the statistical mode). Each echocardiographer assessed studies independently, blinded to the interpretations of the other two and the original study's AS interpretation.

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

• Yes, an MRMC study was done.
• Effect Size of Improvement with AI Assistance:
  • Sensitivity: A statistically significant improvement of +5.5% [95% CI: (1.5%, 9.5%)] for "Aided" readers compared to "Unaided" readers.
  • Partial AUROC: An 8.9% [95% CI: 1.2%, 20.5%] difference in partial AUROC, indicating superiority for the "Aided" group in the critical region of the ROC curve.
  • Inter-rater agreement: Aided readers demonstrated higher inter-rater agreement (89.0%) than unaided readers (81.9%), reflecting improved reader consistency.

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

• Yes, a standalone performance assessment was done. The results are presented in the "Standalone Performance Assessment" section and include metrics like Area Under the ROC Curve, Specificity, and Sensitivity.

7. The Type of Ground Truth Used

• Expert Consensus: For the clinical performance assessment (both standalone and MRMC), the reference standard was established by the majority vote of three independent level-III echocardiographers based on a full read of echocardiography studies, adhering to Aortic Valve Area (AVA) per clinical guidelines from the American Society of Echocardiography (ASE).

8. The Sample Size for the Training Set

• The document does not explicitly state the sample size for the training set. It mentions a "validation dataset" of 401 studies for standalone performance and a subset of 220 studies for the MRMC study, but no information is provided regarding the data used to train the AI algorithm.

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

• The document does not explicitly state how the ground truth for the training set was established. Information regarding the training data, including its provenance and annotation methodology, is not provided in this excerpt.

Ask a specific question about this device

Senographe Pristina: The Senographe Pristina system is intended to be used in the same clinical applications as traditional mammographic film/screen systems. It generates digital mammographic images which can be used for screening and diagnosis of breast cancer.

SenoBright HD: SenoBright HD is an extension of the existing indication for diagnostic mammography with Senographe Pristina. The SenoBright application shall enable contrast enhanced breast imaging using a dual energy technique. This imaging technique can be used as an adjunct following mammography and ultrasound exams to help localize a known or suspected lesion

Pristina Serena: The Pristina Serena option provides the three-dimensional location of target lesions, using information obtained from stereotactic pairs of two-dimensional X-ray images. This information provides guidance for a variety of minimally invasive or interventional procedures in the breast such as: vacuum assisted biopsy, core biopsy, pre-surgical localization (e.g. hookwire), and fine needle aspirations (FNA).

Pristina Serena Bright: The Pristina Serena Bright option provides the three-dimensional location of target lesions, using information obtained from stereotactic pairs of two-dimensional X-ray images acquired with Contrast Enhanced Spectral Mammography (CESM) under the same breast compression. This information provides guidance for a variety of minimally invasive or interventional procedures in the breast such as: vacuum assisted biopsy, core biopsy, pre-surgical localization (e.g. hookwire), and fine needle aspirations (FNA). CESM-Biopsy application is indicated for patients with suspicious lesions only seen with certainty when imaged with a contrast agent or that do not have a definite correlate on mammography or ultrasound

Senographe Pristina (Full Field Digital Mammography)

Senographe Pristina is a full field digital mammography system intended for breast cancer screening and diagnostic mammography. The system acquires two dimensional (2D) digital mammography images and provides on screen image display, archiving, networking, and filming capabilities. It incorporates a large detector enabling imaging of large breasts, adjustable paddles for
positioning smaller breasts, and system adjustments to support patient positioning during standard mammography examinations.

SenoBright HD (Contrast Enhanced Spectral Mammography – CESM)

SenoBright HD is the CESM configuration of the Senographe Pristina platform. CESM acquires paired low-energy (LE) and high-energy (HE) images following intravenous administration of an iodinated contrast agent. From these acquisitions, the system generates recombined iodine-specific images to assist in the assessment of suspicious lesions.

Pristina Serena (Stereotactic Biopsy – 2D)

Pristina Serena is a stereotactic biopsy accessory used with the Senographe Pristina imaging platform. The Biopsy Positioner mounts onto the system in place of the Bucky and supports vertical and horizontal biopsy approaches. It includes a needle holder compatible with various needle guides, enabling precise lesion targeting based on 2D angled mammographic views.

Pristina Serena Bright (CESM Guided Biopsy)

Pristina Serena Bright is a CESM guided biopsy option used with Pristina Serena. It acquires paired low-energy and high energy images to produce both conventional mammographic images and iodine specific images to guide biopsy for contrast enhancing lesions.

N/A

Ask a specific question about this device

The LOGIQ Vita / S20 Series are intended for use by a qualified physician for ultrasound evaluation of Fetal / Obstetrics; Abdominal (including Renal, Gynecology/Pelvic); Pediatric; Small Organ (Breast, Testes, Thyroid); Neonatal Cephalic; Adult Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular; Musculo- skeletal Conventional and Superficial; Urology (including Prostate); Transrectal; Transvaginal; Transesophageal and Intraoperative (Abdominal and Vascular).

Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography, Attenuation Imaging and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/PWD.

The LOGIQ Vita / S20 Series are intended to be used in a hospital or medical clinic.

The LOGIQ Vita / S20 Series are full featured, Track 3, general purpose diagnostic ultrasound systems which consists of a mobile console approximately 530 mm wide (Caster), 835 mm deep (front and back handle) and 1314 mm high that provides digital acquisition, processing and display capability. The user interface includes a digital keyboard (physical keyboard as an option), specialized controls, 14-inch high-resolution color touch screen and 23.8-inch Wide screen High-Resolution HDU monitor and 23.8-inch Wide screen High-Resolution LCD monitor.

The provided FDA 510(k) clearance letter and summary do not contain detailed information about specific acceptance criteria, reported device performance metrics, or a study specifically designed to prove that the device meets those criteria.

The submission is for a new diagnostic ultrasound system (LOGIQ Vita / S20 Series) that leverages the design and clinical data of a predicate device (LOGIQ Fortis K253366). The core argument for substantial equivalence is that the new device has "no changes to the features, accessories, or components that require new clinical studies to support substantial equivalence."

This means that the provided document does not describe a new study that proves the device meets acceptance criteria in the way you've requested. Instead, it asserts that because the new device is substantially equivalent to a previously cleared device, the existing evidence for the predicate device's safety and effectiveness applies.

However, based on the information provided, we can infer some details:

1. Table of acceptance criteria and reported device performance:

The document explicitly states: "The subject of this premarket submission, the LOGIQ Vita / S20 Series, leverages the same clinical data as the predicate and no changes to the features, accessories, or components that require new clinical studies to support substantial equivalence."

This implies that the acceptance criteria and reported device performance are identical to those established for the predicate device, LOGIQ Fortis (K253366). Since the details of that predicate device's performance study are not included in this document, we cannot populate this table with specific quantitative metrics.

Regarding the study proving the device meets acceptance criteria:

The document explicitly states: "The subject of this premarket submission, the LOGIQ Vita / S20 Series, leverages the same clinical data as the predicate and no changes to the features, accessories, or components that require new clinical studies to support substantial equivalence."

This means there was no new, independent clinical study conducted for the LOGIQ Vita / S20 Series to demonstrate it meets acceptance criteria beyond what was established for the predicate device (LOGIQ Fortis K253366). The substantial equivalence argument relies on the fact that the changes are minor and do not impact the core safety and effectiveness established by the predicate.

Given this, the subsequent questions, which would typically describe such a study, cannot be answered directly from the provided text for the LOGIQ Vita / S20 Series. If such information exists, it would be found in the 510(k) submission for the LOGIQ Fortis (K253366) predicate device.

Based on the provided document, here's what we can state:

• 2. Sample size used for the test set and the data provenance: Not applicable for a new study. The device "leverages the same clinical data as the predicate," meaning no new test set was used for this 510(k).
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable for a new study.
• 4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable for a new study.
• 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. The document mentions "AI algorithms" in the context of UGAP/UGFF features being identical to the predicate, but it does not describe an MRMC comparative effectiveness study to measure human reader improvement.
• 6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: The document states that the liver assessment features (UGAP/UGFF) utilize AI algorithms, and these are identical to the predicate device. However, it does not describe a standalone performance study specifically for the AI components in this submission. The assertion is that these features have not changed since the predicate.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable for a new study.
• 8. The sample size for the training set: Not applicable for a new study.
• 9. How the ground truth for the training set was established: Not applicable for a new study.

In conclusion, the clearance for the LOGIQ Vita / S20 Series is based on its substantial equivalence to the predicate LOGIQ Fortis (K253366), rather than a new, dedicated study demonstrating its performance against new acceptance criteria. The performance and safety data are derived from the predicate device.

Ask a specific question about this device

The Photonova Spectra, Photonova Spectra Select system is a silicon-based spectral photon counting detector X-ray Computed Tomography scanner.

The system is intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission projection data from the same axial plane taken at different angles.

The system acquires multi-energy data in every scan and natively generates high resolution monochromatic images and material density maps to facilitate visualizing and analyzing information about anatomical and pathological structures.

The system is indicated for head, whole body, cardiac, and vascular CT applications. The system is indicated for patients of all ages. The images can be post-processed to produce additional imaging planes or analysis results.

The system is indicated for lung cancer screening for patients meeting the established inclusion criteria of programs/protocols that have been published by either a governmental body or professional medical society.*

*Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011;365:395-409) and subsequent literature, for further information.

Photonova Spectra is the next iteration of the predicate, the Revolution Apex platform (K213715), introducing a new Deep Silicon (dSi) photon counting detector for CT imaging. Photonova Spectra aims to realize an improvement in both spatial resolution and spectral imaging performance relative to traditional Energy Integrating Detector (EID) systems for diagnostic CT. With photon-counting detectors that can better discriminate energies, spectral CT imaging can natively provide valuable information about tissue composition and material density without the need for active filtration or kVp modulation by performing material decomposition directly from native multi-energy data.

The Photonova Spectra system is an ultra-premium multi-slice CT scanning system comprised of a gantry, a detector, an x-ray tube, a power distribution unit (PDU), a table, a system cabinet, a scanner desktop computer and user interface, and associated accessories. It is designed as a volumetric CT scanner to provide advanced imaging capability for a range of clinical applications.

Compared to the predicate Revolution Apex, the key differences of the Photonova Spectra System consist of a Deep Silicon (dSi) X-ray detector capable of directly converting X-ray photons to electrical signals, advanced detector data acquisition hardware for managing and processing of large volumes of data, advanced computer hardware and an enhanced image chain for generating High Definition (HD) Spectral and Ultra High Definition (UHD) image series.

The Photonova Spectra image chain is developed to calibrate, pre-process, reconstruct, and post-process images for use in medical imaging applications. Customized for photon counting detection physics and capability, Photonova Spectra does not require user to choose between single kV and dual energy acquisition modes. With Photonova Spectra, all acquisitions are spectral with 8 energy bins over the full high-resolution detector, and the data is stored real-time on the rotating side as the acquisition completes over the full scan sequence.

The system will be offered with either an 80 mm dSi detector and 40 mm dSi detector model configurations, commercialized as Photonova Spectra and Photonova Spectra Select, respectively. The detector size is the key differentiator, but all core technology and functionality are identical.

The provided FDA 510(k) clearance letter and summary for the Photonova Spectra CT System do not contain detailed information about specific acceptance criteria for device performance or the full study design typically expected for such information. The document focuses on regulatory compliance, technological characteristics compared to a predicate, and a general overview of verification and validation testing.

However, based on the information provided, we can infer some aspects and present them to the best of our ability, while noting the missing details.

Missing Information:

• Specific quantitative acceptance criteria: The document describes the types of tests performed (e.g., image quality metrics, LCD studies) but does not provide numerical thresholds that the device had to meet.
• Specific quantitative reported device performance: While it states "substantial equivalence of image quality was demonstrated," it doesn't provide the actual measured values for metrics like CT number accuracy, resolution, or noise texture.
• Detailed sample size for the test set: It mentions a "sample clinical covering a wide range of clinical scenarios" for the reader study but no specific number of cases.
• Data provenance for the test set: The document does not specify the country of origin of the data for the reader study's test set or whether it was retrospective or prospective.
• Detailed qualifications of experts for ground truth: It states "US board-certified Radiologists" but doesn't specify years of experience or subspecialty.
• Adjudication method for the test set.
• Effect size for MRMC study: It implies a reader study was done to compare DL levels, but doesn't quantify improvement with AI assistance.
• Sample size for the training set.
• How ground truth for the training set was established.

Acceptance Criteria and Study for Photonova Spectra CT System

Given the limitations of the provided document, the following is constructed based on the available information and educated inferences regarding CT system clearances.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document states "a reader study of sample clinical covering a wide range of clinical scenarios, including Neuro, Body, and Cardiac/Chest." It also mentions "challenging cases from the above-mentioned reader study."

• Sample Size: Not explicitly stated (e.g., number of cases or images).
• Data Provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective).

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

The document mentions: "Images were evaluated by US board-certified Radiologists."

• Number of Experts: Not explicitly stated.
• Qualifications of Experts: US board-certified Radiologists. Specific years of experience or subspecialty (e.g., Neuroradiologist, Cardiothoracic Radiologist) are not provided.

4. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method used for the reader study.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Its Effect Size

A reader study was conducted to compare various levels of user-prescribed denoising. It implies a comparative evaluation between the proposed DL reconstruction and FBP-based reconstruction.

• MRMC Study: Yes, a comparative clinical evaluation of challenging cases was performed by "US board certified Radiologists."
• Effect Size: Not quantified. The qualitative finding was: "No reader identified any added, removed, or reduced diagnostic information in any DLIR setting, and all pathologies were consistently visualized across all DL reconstructions." This suggests that the diagnostic interpretability was maintained, implying no negative effect and potential maintenance or improvement in visualization where denoising was effective, though specific metrics of improvement are not provided.

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

Yes, extensive standalone performance testing was done, referred to as "Image Performance Testing (Verification)" and "Summary of Non-Clinical Testing."

• This included "evaluation of a comprehensive set of image quality metrics" and "acquisitions at varying dose levels and phantom sizes."
• Metrics like "CT number, water accuracy, mean CT number over a range of spectral tasks, in-plane resolution, cross-plane resolution and noise texture (as measured by the noise power spectrum)" were assessed.
• "Low contrast detectability (LCD) studies were conducted incorporating a model observer approach."

7. The Type of Ground Truth Used

Based on the description of the studies:

• For standalone (non-clinical) testing: Phantoms (standard IQ, QA, ACR, anthropomorphic pediatric phantoms) and model observer approaches for objective metrics.
• For clinical (reader) testing: Expert consensus/interpretation by US board-certified Radiologists was used to determine diagnostic utility and whether pathologies were consistently visualized across different reconstructions.

8. The Sample Size for the Training Set

The document states that the "proposed TrueFidelity DL for PCCT is intended for routine clinical use and based on the same framework and training methodology as the reference devices (DLIR and DLIR-GSI)." However, the specific sample size for the training set (e.g., number of images, patients) for the Photonova Spectra's TrueFidelity DL for PCCT is not provided.

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

The document does not explicitly state how the ground truth for the training set was established for the TrueFidelity DL for PCCT, beyond mentioning it uses the "same framework and training methodology" as previously cleared DLIR products. Typically, for deep learning reconstructions in CT, the "ground truth" during training refers to high-quality, often low-noise or high-dose, reference images from which the algorithm learns to denoise or reconstruct lower-quality/lower-dose inputs. These reference images are usually generated from the CT scanner itself (e.g., by repeating scans at very high doses or using iterative reconstruction techniques to establish a cleaner image for comparison). Specific details are not provided.

Ask a specific question about this device

The SIGNA™ Bolt system is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan times. It is indicated for use as a diagnostic imaging device to produce axial, sagittal, coronal, and oblique images, spectroscopic images, parametric maps, and/or spectra, dynamic images of the structures and/or functions of the entire body, including, but not limited to, head, neck, TMJ, spine, breast, heart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body. Depending on the region of interest being imaged, contrast agents may be used.

The images produced by the SIGNA™ Bolt system reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance. These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

SIGNA™ Bolt is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan times, and is designed for improved patient comfort and workflow. The system features a 3.0T superconducting magnet with a 70 cm bore size and can image in the sagittal, coronal, axial, oblique, and double oblique planes, using various pulse sequences, imaging techniques and reconstruction algorithms. SIGNA™ Bolt is designed to conform to NEMA DICOM standards.

The SIGNA™ Bolt system will be offered as two commercial configurations with the following features:

• Magnet: 3.0T superconducting magnet with a wide (70 cm) bore size and active shielding
• Maximum Gradient Strength: 80 mT/m (SuperXG Gradient), 65 mT/m (SuperXF Gradient)
• Maximum Slew Rate: 200 T/m/s (SuperXG Gradient and SuperXF Gradient)
• RF Transmit: A liquid cooled In-Scan-Room RF transmit architecture with a peak power capability of 36 kW and 3.0T Platform Body Coil
• RF Receive Chain: 162 Ch available (SuperXG Gradient), 130 Ch available (SuperXF Gradient)
• Patient Table: Detachable SIGNA One Patient Table with embedded 3.0T AIR PA XL coil and up to four 32-channel high density auto-coil sensing connection ports
• Power Rating: 113 kVA (SuperXG Gradient), 90 kVA (SuperXF Gradient)
• Software: Software platform featuring various productivity enhancement features, designed to improve workflow and reduce scan time
  • AIRx (previously cleared in K183231) – AI-based automated slice prescription tool now extended with new deep learning models for spine and prostate imaging
  • SIGNA One Camera – Real-time AI-enabled image guidance that assists with automated patient positioning
• Gating Options: Wired, wireless, and contactless physiological gating options

This document outlines the acceptance criteria and supporting studies for the SIGNA™ Bolt device, based on the provided FDA 510(k) clearance letter.

Key Features and AI/ML Components of SIGNA™ Bolt:

The SIGNA™ Bolt system includes several AI/Machine Learning components:

1. AIRx: An AI-based automated slice prescription tool, previously cleared for brain and knee imaging (K183231), now extended with new deep learning models for spine and prostate imaging.
2. SIGNA One Camera: Real-time AI-enabled image guidance that assists with automated patient positioning.
3. Contactless Gating: This feature leverages underlying physiological signal detection that might involve advanced signal processing or AI techniques, though the document primarily describes its functional outcome.

Acceptance Criteria and Reported Device Performance

The following table summarizes the acceptance criteria and reported performance for the AI/ML components of the SIGNA™ Bolt device:

Study Details for AI/ML Components:

1. SIGNA One Camera

• Sample Size for Test Set: Data collected from 80 volunteers.
• Data Provenance: US and China (to ensure diverse datasets).
• Number of Experts & Qualifications for Ground Truth: Not explicitly stated for this component. Ground truth is described as "MR system coordinates of the camera-predicted anatomical landmarks against ground truth annotations," suggesting a technical or measurement-based ground truth rather than expert reads.
• Adjudication Method: Not specified.
• MRMC Comparative Effectiveness Study: Yes, a "time on task study" was conducted with 11 MR Scan Operators comparing the AI-powered workflow to conventional laser landmarking.
  • Effect Size: The camera workflow "consistently enabled faster setup times for landmarking." Specific quantitative improvement (e.g., % reduction in time) is not provided in text.
• Standalone Performance: Yes, "Accuracy was evaluated by comparing the MR system coordinates of the camera-predicted anatomical landmarks against ground truth annotations." This indicates an algorithm-only evaluation.
• Type of Ground Truth: MR system coordinates.
• Sample Size for Training Set: Not explicitly stated, but the test dataset was "entirely separate from the training and validation datasets."
• Ground Truth for Training Set: Not specified, but likely established in a similar manner to the test set (MR system coordinates or similar technical measurements).

2. AIRx Spine

• Sample Size for Test Set: 376 subjects.
• Data Provenance: Multiple clinical sites and internal GE HealthCare sites.
• Number of Experts & Qualifications for Ground Truth: Not explicitly stated. Ground truth is implied to be established for "accurate multi-slice, multi-angle prescriptions."
• Adjudication Method: Not specified.
• MRMC Comparative Effectiveness Study: Yes, "Comparative studies demonstrated that AIRx Spine reduced scan prescription times compared to manual workflows and minimized inter-operator variability."
  • Effect Size: "Reduced scan prescription times" and "minimized inter-operator variability" (confirmed by Structural Similarity Index (SSIM) analysis and visual comparisons). Specific quantitative improvement is not provided.
• Standalone Performance: Yes, "Performance testing was conducted on the AIRx Spine deep learning models," indicating an algorithm-only evaluation.
• Type of Ground Truth: Not explicitly stated but implied to be based on accurate anatomical prescriptions suitable for diagnostic imaging. SSIM analysis and visual comparisons suggest a comparison against an ideal or expert-defined prescription.
• Sample Size for Training Set: Not explicitly stated, but the test dataset was "held separate from training and validation data."
• Ground Truth for Training Set: Not specified, but likely established to enable the model to learn "patient-specific spinal curvatures" and "accurate multi-slice, multi-angle prescriptions."

3. AIRx Prostate

• Sample Size for Test Set: 785 exams.
• Data Provenance: Clinical sites in the US and Europe.
• Number of Experts & Qualifications for Ground Truth: Not explicitly stated.
• Adjudication Method: Not specified.
• MRMC Comparative Effectiveness Study: Not explicitly mentioned for this specific feature in the provided text.
• Standalone Performance: Yes, "Performance testing was conducted on the six deep learning models that comprise the AIRx Prostate feature," evaluating automated prostate scan plane prescription, indicating an algorithm-only evaluation.
• Type of Ground Truth: Not explicitly stated but implied to be based on accurate anatomical prescriptions for the prostate, using SSFSE localizer images.
• Sample Size for Training Set: Not explicitly stated, but the test dataset was "kept separate from the training and validation data."
• Ground Truth for Training Set: Not specified, but likely established to enable the model to learn "automated prostate scan plane prescription."

4. Contactless Gating

• Sample Size for Test Set: Not explicitly stated for this particular feature's performance validation.
• Data Provenance: Not specified.
• Number of Experts & Qualifications for Ground Truth: Not specified.
• Adjudication Method: Not specified.
• MRMC Comparative Effectiveness Study: Not mentioned.
• Standalone Performance: Yes, "Verification and validation testing confirmed that the contactless gating feature meets its performance specifications by accurately detecting and displaying respiratory and peripheral cardiac waveforms," indicating a system performance evaluation.
• Type of Ground Truth: Underlying physiological waveforms (respiratory and cardiac).
• Sample Size for Training Set: Not specified.
• Ground Truth for Training Set: Not specified, but likely established from physiological signal data.

Overall Conclusion from Performance Testing:

GE HealthCare concludes that the SIGNA™ Bolt is as safe and effective, with performance substantially equivalent to the predicate device, based on the nonclinical testing, including extensive software verification and validation, as well as specific performance evaluations for its new AI-enabled features. No clinical studies were required to support substantial equivalence.

Ask a specific question about this device

The SIGNA™ Sprint Select is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan times. It is indicated for use as a diagnostic imaging device to produce axial, sagittal, coronal, and oblique images, spectroscopic images, parametric maps, and or spectra, dynamic images of the structures and/or functions of the entire body, including, but not limited to, head, neck, TMJ, spine, breast, heart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body. Depending on the region of interest being imaged, contrast agents may be used.

The images produced by SIGNA™ Sprint Select reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance. These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

SIGNA™ Sprint Select is a whole-body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan time. The system uses a combination of time-varying magnet fields (Gradients) and RF transmissions to obtain information regarding the density and position of elements exhibiting magnetic resonance. The system can image in the sagittal, coronal, axial, oblique, and double oblique planes, using various pulse sequences, imaging techniques and reconstruction algorithms. The system features a 1.5T superconducting magnet with 70cm bore size. The system is designed to conform to NEMA DICOM standards (Digital Imaging and Communications in Medicine).

N/A

Ask a specific question about this device

Indications for Use:
The MAC 7 Resting ECG Analysis System is a non-invasive prescription device.

• The device is indicated for use to acquire, analyze, display and print electrocardiograms.
• The device is indicated for use to provide interpretation of the data for consideration by a physician.
• The device is indicated for use in a clinical setting, by a physician or by trained personnel who are acting on the orders of a licensed physician. It is not intended as a sole means of diagnosis.
• The interpretations of ECG offered by the device are only significant when used in conjunction with a physician over-read as well as consideration of all other relevant patient data.
• The device is indicated for use on adult and pediatric (birth through 21 years of age) populations.

Intended Use:
The MAC 7 Resting ECG Analysis System is intended to acquire, analyze, display, and record electrocardiographic information from adult or pediatric populations. Basic system simultaneously acquires data from each lead. Once the data is acquired, it can be analyzed, reviewed, stored, printed or transmitted. Transmission and reception of ECG data and other clinical data to and from a central clinical information system is optional.

The MAC 7 Resting ECG Analysis System is intended to be used under the direct supervision of a licensed healthcare practitioner, by trained operators in a hospital, medical professional's facility or wherever ECG testing is performed.

The MAC 7 Resting ECG Analysis System is a mobile electrocardiograph designed to acquire, analyze, display, and record ECG signals from surface ECG electrodes.

The device can capture 3, 6, 12 or 15 lead electrocardiograms, provide interpretive analysis, and print reports.

The device can connect to a network, either through a wired LAN connection or via wireless WiFi access points. Once on the network, the device can optionally interface with cardiology information systems such as the GEHC MUSE® system to participate in a complete electrocardiology workflow.

The device provides state-of-the-art information technology security features and a contemporary user interface. Mobility is provided via an optional trolley.

The FDA 510(k) clearance letter for the MAC 7 Resting ECG Analysis System (K251670) does not contain a specific study proving the device meets acceptance criteria. Instead, it establishes substantial equivalence to predicate devices (K203786, K173830, K210560) based on similarities in intended use, indications for use, technology, and performance, along with compliance with voluntary standards and non-clinical testing.

Therefore, the following information is extracted from the provided text to fulfill your request:

1. Acceptance Criteria and Reported Device Performance

The document describes the device's characteristics and compares them to predicate devices, demonstrating substantial equivalence rather than explicit acceptance criteria with numerical performance targets. The "Discussion of Differences" column often highlights that a change does not significantly affect substantial equivalence, implying that the performance remains acceptable.

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

The document states: "Summary of Clinical Tests: The subject of this premarket submission, MAC 7 Resting ECG Analysis System, did not require clinical studies to support substantial equivalence." This indicates that no specific test set data from clinical studies was used for performance evaluation in this submission. The "acceptance" is based on the device's technical characteristics aligning with or improving upon those of legally marketed predicate devices, supported by non-clinical testing and previous clearances for core components (like the 12SL™ analysis algorithm v24).

Therefore, details on sample size, country of origin, or retrospective/prospective nature of a clinical test set are not available in this document.

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

As no clinical studies were required for this submission to support substantial equivalence, there is no information provided regarding experts establishing ground truth for a test set.

4. Adjudication Method for the Test Set

Given that no clinical studies were performed, there is no adjudication method described for a test set.

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

The document does not mention any MRMC comparative effectiveness study. The focus is on establishing substantial equivalence to existing devices, not on demonstrating improved human reader performance with AI assistance.

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

The document states that the "Interpretive Statements are provided by 12SL (v24) ECG Analysis Program which was previously cleared under K221321." This implies that the performance of the 12SL™ algorithm itself (a standalone interpretation algorithm) would have been assessed during its prior clearance (K221321). However, the details of that standalone performance study are not included in this K251670 submission.

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

Since no new clinical studies were performed for this submission, there is no mention of the type of ground truth used for a test set. For the 12SL™ analysis algorithm (v24) which provides interpretation statements, the ground truth would have been established during its prior clearance (K221321), but those details are not provided here.

8. The Sample Size for the Training Set

The document does not provide information on the sample size for any training set. As noted, the approval is based on substantial equivalence and non-clinical testing rather than specific training data for a new algorithm.

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

The document does not provide information on how ground truth was established for any training set.

Ask a specific question about this device

LOGIQ Totus is intended for use by a qualified physician for ultrasound evaluation of Fetal/Obstetrics; Abdominal(including Renal, Gynecology/Pelvic), Pediatric; Small organ(Breast, Testes, Thyroid); Neonatal Cephalic; Adult Cephalic; Cardiac(Adult and Pediatric), Peripheral Vascular, Musculo-skeletal Conventional and Superficial; Urology(including Prostate); Transrectal; Transvaginal; Transesophageal and Intraoperative(Abdominal and Vascular).

Modes of operation includes: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography, Attenuation Imaging and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/PWD.

The LOGIQ Totus is intended to be used in a hospital or medical clinic.

The LOGIQ Totus is full featured, Track 3 device, primarily intended for general purpose diagnostic ultrasound system which consists of a mobile console approximately 490mm wide (monitor width: 545mm), 835mm deep and 1415~1815mm high that provides digital acquisition, processing and display capability. The user interface includes a computer keyboard, specialized controls, 14-inch LCD touch screen and color 23.8-inch LCD & HDU image display.

The provided FDA 510(k) clearance letter and summary for the LOGIQ Totus Ultrasound System (K253370) describes the acceptance criteria and the study for the Ultrasound Guided Fat Fraction for adult imaging (UGFF) software feature. This feature is being added to the LOGIQ Totus and is similar to a previously cleared Siemens UDFF feature.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document describes the performance of the UGFF feature by comparing it to MRI Proton Density Fat Fraction (MRI-PDFF) and, in a separate confirmatory study, to a predicate UDFF device. The "acceptance criteria" are implied by the reported strong correlations and limits of agreement with these reference standards.

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

• Primary Study (UGFF vs. MRI-PDFF):

  • Sample Size: 582 participants
  • Data Provenance: External clinical study in Japan (Population: Asian). The study was retrospective or prospective is not specified, but the phrase "obtained from the liver of five hundred and eighty-two (582) participants" suggests a data collection event rather than a purely retrospective analysis of existing medical records. The study is described as an "external clinical study," further suggesting a dedicated data collection.

• First Confirmatory Study (UGFF vs. MRI-PDFF):

  • Sample Size: 15 US patients and 5 EU patients (total 20 patients)
  • Data Provenance: US and EU patients. Demographic information on the 5 EU patients was unavailable. This was conducted as a "confirmatory study."

• Second Confirmatory Study (UGFF vs. UDFF):

  • Sample Size: 24 EU patients
  • Data Provenance: EU patients. This was conducted as a "confirmatory study."

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

The document does not specify the number of experts or their qualifications for establishing the ground truth.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method. For the UGFF feature, the "ground truth" was objective measurements (MRI-PDFF or a predicate device's UDFF), which typically do not require adjudication by human experts in the same way an image diagnosis might.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC comparative effectiveness study was not done for the UGFF feature as described. The studies focused on comparing the device's output (UGFF index) to an objective reference standard (MRI-PDFF or another device's UDFF), not on how human readers' performance improved with or without AI assistance.

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

Yes, a standalone performance evaluation was done. The UGFF index, based on acoustic property measurements, is compared directly to MRI-PDFF and UDFF. This indicates the algorithm's performance independent of human interpretation or intervention in the final measurement calculation. While a technologist operates the ultrasound system, the UGFF index calculation itself is an algorithmic output.

7. The Type of Ground Truth Used

The type of ground truth used is MRI Proton Density Fat Fraction (MRI-PDFF) measurements, which are quantitative and objective reference standards for liver fat quantification. Additionally, for one confirmatory study, the ground truth was the Ultrasound-Derived Fat Fraction (UDFF) from a Siemens Acuson S3000/S2000, functioning as a predicate device's output. These are akin to "outcomes data" or "established reference standard measurements."

8. The Sample Size for the Training Set

The document states: "During the migration of the AI software feature from LOGIQ E10s (K231989), the algorithm was not retrained and there were no changes to the algorithmic flow or the AI components performing the inferencing." This implies the training set was associated with the original clearance of the Auto Renal Measure Assistant on the LOGIQ E10s (K231989) but the sample size for the training set is not provided in this document.

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

Similarly, since the algorithm was not retrained and the document pertains to the migration of an existing AI feature, the method for establishing the ground truth for the original training set is not provided in this document.

Ask a specific question about this device

LOGIQ Fortis is intended for use by a qualified physician for ultrasound evaluation of Fetal/Obstetrics; Abdominal (including Renal, Gynecology/Pelvic); Pediatric; Small Organ (Breast, Testes, Thyroid); Neonatal Cephalic; Adult Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular; Musculo-skeletal Conventional and Superficial; Urology (including Prostate); Transrectal; Transvaginal; Transesophageal and Intraoperative (Abdominal and Vascular).

Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography, Attenuation Imaging and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/PWD.

The LOGIQ Fortis is intended to be used in a hospital or medical clinic.

The LOGIQ Fortis is a full featured, Track 3, general purpose diagnostic ultrasound system which consists of a mobile console approximately 575 mm wide (keyboard), 925 mm deep and 1300 mm high that provides digital acquisition, processing and display capability. The user interface includes a digital keyboard (physical keyboard as an option), specialized controls, 12-inch high-resolution color touch screen and 23.8-inch High Contrast LED LCD monitor (or 23.8-inch High Resolution LED LCD monitor as an option).

Here's a breakdown of the acceptance criteria and study details for the AI features of the LOGIQ Fortis Ultrasound System, based on the provided FDA 510(k) clearance letter:

AI Features Analyzed:

1. Auto Abdominal Color Assistant 2.0
2. Auto Aorta Measure Assistant
3. Auto Common Bile Duct (CBD) Measure Assistant
4. Ultrasound Guided Fat Fraction (UGFF)

1. Auto Abdominal Color Assistant 2.0

1.1. Acceptance Criteria and Reported Device Performance:

1.2. Sample Size and Data Provenance (Test Set):

• Number of individual subjects: 49
• Number of annotation images: 1186
• Country: USA (100%)
• Retrospective/Prospective: Not explicitly stated, but the description "Before the process of data annotation, all information displayed on the device is removed and performed on information extracted purely from Ultrasound B-mode images" and "Readers to ground truth the 'anatomy' visible in static B-Mode image" suggests retrospective analysis of collected images.

1.3. Number and Qualifications of Experts for Ground Truth (Test Set):

• Number of Experts: Not specified ("Readers to ground truth the 'anatomy'").
• Qualifications: Not specified (generally, these would be qualified ultrasonographers or radiologists).

1.4. Adjudication Method (Test Set): Not specified.

1.5. MRMC Comparative Effectiveness Study: No, this study evaluates the standalone performance of the AI model.

1.6. Standalone Performance: Yes, this study was done to evaluate the algorithm's performance in detecting abdominal structures.

1.7. Type of Ground Truth Used: Expert consensus on "anatomy" visible in static B-Mode images.

1.8. Sample Size for Training Set: Not explicitly stated, but implied to be separate from the test set.

1.9. How Ground Truth for Training Set Was Established: Not explicitly stated, but implied to be similar to the test set, with experts annotating B-mode images.

2. Auto Aorta Measure Assistant

2.1. Acceptance Criteria and Reported Device Performance:

2.2. Sample Size and Data Provenance (Test Set):

• Long View Aorta:
  • Subjects: 36 (11 Male, 25 Female)
  • Country: 16 Japan, 20 USA
• Short View Aorta:
  • Subjects: 35 (11 Male, 24 Female)
  • Country: 15 Japan, 20 USA
• Retrospective/Prospective: Not explicitly stated, but "Validation images were collected on LOGIQ Fortis" and the truthing process suggests retrospective analysis of collected images.

2.3. Number and Qualifications of Experts for Ground Truth (Test Set):

• Number of Experts: Not specified ("Readers to ground truth...").
• Qualifications: Not specified.

2.4. Adjudication Method (Test Set): An "arbitrator to select most accurate measurement among all readers" was used. This suggests a form of adjudication, possibly 2+1 or similar, where the arbitrator acts as the tie-breaker/final decision-maker.

2.5. MRMC Comparative Effectiveness Study: Yes, this study directly compares human performance with and without AI assistance by measuring keystrokes and accuracy.

• Effect Size (Keystrokes):
  • Long View Aorta: Reduction of ~2.896 keystrokes (4.132 - 1.236)
  • Short View Aorta: Reduction of ~4.743 keystrokes (7.05 - 2.307)
    (While not a traditional effect size like AUC improvement, this quantifies human workflow improvement).

2.6. Standalone Performance: Partially. The accuracy measurements compare AI baseline against an arbitrator's selected measurement, indicating standalone algorithm accuracy, but the primary focus is on human-in-the-loop efficiency.

2.7. Type of Ground Truth Used: Expert consensus on measurements, with an arbitrator for final selection.

2.8. Sample Size for Training Set: Not explicitly stated, but independence from the test set is ensured by "exam site origin."

2.9. How Ground Truth for Training Set Was Established: Not explicitly stated, but implied to be similar to the test set, with experts performing measurements.

3. Auto Common Bile Duct (CBD) Measure Assistant

3.1. Acceptance Criteria and Reported Device Performance:

3.2. Sample Size and Data Provenance (Test Set):

• Subjects: 25 (11 Male, 14 Female)
• Countries: USA (40%), Japan (60%)
• Retrospective/Prospective: Not explicitly stated, but "Validation images were collected on LOGIQ Fortis" and the truthing process suggests retrospective analysis of collected images.

3.3. Number and Qualifications of Experts for Ground Truth (Test Set):

• Number of Experts: Not specified ("Readers to ground truth...").
• Qualifications: Not specified.

3.4. Adjudication Method (Test Set): An "arbitrator to select most accurate measurement among all readers" was used.

3.5. MRMC Comparative Effectiveness Study: Yes, this study directly compares human performance with and without AI assistance by measuring keystrokes and accuracy (specifically, accuracy with and without segmentation scroll edit, which implies human interaction with AI).

• Effect Size (Keystrokes): Average reduction of 1.62 keystrokes.

3.6. Standalone Performance: Partially. The measurement accuracy with and without segmentation scroll edit provides insight into the algorithm's performance and the benefit of human refinement, but the primary focus is on human-in-the-loop efficiency and accuracy.

3.7. Type of Ground Truth Used: Expert consensus on measurements, with an arbitrator for final selection.

3.8. Sample Size for Training Set: Not explicitly stated, but independence from the test set is ensured by "exam site origin."

3.9. How Ground Truth for Training Set Was Established: Not explicitly stated, but implied to be similar to the test set, with experts performing measurements.

4. Ultrasound Guided Fat Fraction (UGFF)

4.1. Acceptance Criteria and Reported Device Performance:

4.2. Sample Size and Data Provenance (Test Set): This section describes the clinical studies used for validation of the UGFF index, rather than a traditional AI test set.

• Primary Study (Development/Validation of UGFF Index):

  • Subjects: 582 participants
  • Country: Japan
  • Retrospective/Prospective: "external clinical study in Japan" implies prospective data collection, with subsequent analysis.

• Second Confirmatory Study:

  • Subjects: 15 US patients, 5 EU patients (Total 20)
  • Country: US and EU
  • Retrospective/Prospective: Not specified.

• Third Confirmatory Study (Comparison with Predicate):

  • Subjects: 24 EU patients
  • Country: EU
  • Retrospective/Prospective: Not specified.

4.3. Number and Qualifications of Experts for Ground Truth (Test Set):

• UGFF Study: The ground truth is established by a reference imaging modality (MRI-PDFF) and a comparison device (UDFF), not directly by human experts interpreting ultrasound images for the purpose of the study. The study involves acoustic property measurements.

4.4. Adjudication Method (Test Set): Not applicable, as the ground truth is based on MRI-PDFF and UDFF, not human interpretation requiring adjudication.

4.5. MRMC Comparative Effectiveness Study: No, this is a clinical validation against a reference standard and a comparative study against a predicate device.

4.6. Standalone Performance: Yes, the UGFF index is an algorithm-generated value based on acoustic properties, and its performance is evaluated in a standalone manner against established reference methods (MRI-PDFF) and a legally marketed predicate (UDFF).

4.7. Type of Ground Truth Used: Quantitative measurements from a reference imaging modality (MRI Proton Density Fat Fraction - MRI-PDFF %) and a comparative device (Ultrasound-Derived Fat Fraction (UDFF, Siemens)).

4.8. Sample Size for Training Set: The UGFF index is based on a least squares fit (estimation) between acoustic property measurements and MRI-PDFF measurements from the primary 582-subject study. This study effectively serves as the "training" dataset for establishing the correlation and the estimation model.

4.9. How Ground Truth for Training Set Was Established: MRI-PDFF measurements were obtained from the liver of these 582 participants.

Ask a specific question about this device

AIR Recon DL is a deep learning based reconstruction technique that is available for use on GE HealthCare 1.5T, 3.0T, and 7.0T MR systems. AIR Recon DL reduces noise and ringing (truncation artifacts) in MR images, which can be used to reduce scan time and improve image quality. AIR Recon DL is intended for use with all anatomies, and for patients of all ages. Depending on the anatomy of interest being imaged, contrast agents may be used.

AIR Recon DL is a software feature intended for use with GE HealthCare MR systems. It is a deep learning-based reconstruction technique that removes noise and ringing (truncation) artifacts from MR images. AIR Recon DL is an optional feature that is integrated into the MR system software and activated through purchasable software option keys. AIR Recon DL has been previously cleared for use with 2D Cartesian, 3D Cartesian, and PROPELLER imaging sequences.

The proposed device is a modified version of AIR Recon DL that includes a new deep-learning phase correction algorithm for applications that create multiple intermediate images and combine them, such as Diffusion Weighted Imaging where multiple NEX images are collected and combined. This enhancement is an optional feature that is integrated into the MR system software and activated through an additional purchasable software option key (separate from the software option keys of the predicate device).

This document describes the acceptance criteria and the studies conducted to prove the performance of the AIR Recon DL device, as presented in the FDA 510(k) clearance letter.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Nonclinical Testing:
  • Phantom testing was conducted for the DLPC and PC-ARDL models. No specific sample size (number of phantom scans) is provided, but it implies a sufficient number for evaluation.
• In-Vivo Performance Testing:
  • ADC Accuracy: Diffusion-weighted brain images were acquired at 1.5T with b-values = 50, 400, 800, 1200 s/mm². The number of subjects is not explicitly stated, but it's referred to as "diffusion images" and "diffusion-weighted brain images."
  • Low-Contrast Detectability: Raw data from 4 diffusion-weighted brain scans were used.
• Quantitative Post Processing (Repeatability Study):
  • 6 volunteers were recruited. 2 volunteers scanned on a 1.5T scanner, 4 on a 3T scanner.
  • Scanned anatomical regions included brain, spine, abdomen, pelvis, and breast.
  • Each sequence was repeated 4 times.
  • Data Provenance: The document states "in-vivo data" and "volunteer scanning was performed simulating routine clinical workflows." This suggests prospective scanning of human subjects, likely in a controlled environment. The country of origin is not specified, but given the FDA submission, it's likely U.S. or international data meeting U.S. standards. The statement "previously acquired de-identified cases" for the Clinical Image Quality Study refers to retrospective data for that specific study, but the volunteer scanning for repeatability appears prospective.
• Clinical Image Quality Study:
  • 34 datasets of previously acquired de-identified cases.
  • Data Provenance: "previously acquired de-identified cases" indicates retrospective data. The country of origin is not specified.

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

• Nonclinical Testing: Ground truth established through phantom measurements and expected physical properties (e.g., signal bias, noise floor). No human experts involved in establishing ground truth here.
• In-Vivo Performance Testing:
  • ADC Accuracy: "Average ADC values were measured from regions of interest in the lateral ventricles." This implies expert selection of ROIs, but the number of experts is not specified. The ground truth for ADC is the expected isotropic Gaussian diffusion in these regions.
  • Low-Contrast Detectability: "The contrast ratio and contrast-to-noise ratio for each of the inserts were measured." This is a quantitative measure, not explicitly relying on expert consensus for ground truth on detectability, but rather on the known properties of the inserted synthetic objects.
• Quantitative Post Processing:
  • ADC Repeatability: Ground truth for repeatability is based on quantitative measurements and statistical analysis (coefficient of variability). ROI placement would typically be done by an expert, but the number is not specified.
  • Phase Correction Effectiveness: Ground truth is based on the theoretical expectation of signal distribution in real/imaginary channels after ideal phase correction.
• Clinical Image Quality Study:
  • One (1) U.S. Board Certified Radiologist was used.
  • Qualifications: "U.S. Board Certified Radiologist." No explicit number of years of experience is stated, but Board Certification indicates a high level of expertise.

4. Adjudication Method for the Test Set

• Nonclinical/Phantom Testing: No explicit adjudication method described beyond passing defined acceptance criteria for quantitative metrics.
• In-Vivo Performance Testing: Quantitative measurements (ADC values, contrast ratios, CNR) were used. Paired t-tests were conducted, which is a statistical comparison method, not an adjudication process as typically defined for expert readings.
• Quantitative Post Processing: Quantitative measurements and statistical analysis (coefficient of variability, comparison of real/imaginary channels).
• Clinical Image Quality Study: A single U.S. Board Certified Radiologist made the assessment. There is no stated adjudication method described, implying a single-reader assessment for clinical image quality.

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

• An MRMC comparative effectiveness study was not explicitly described as a formal study design in the provided text.
• The "Clinical Image Quality Study" involved only one radiologist, so it does not qualify as an MRMC study.
• There is no reported effect size of how much human readers improve with AI vs. without AI assistance. The study rather focused on the AI-reconstructed images' standalone diagnostic quality.

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

• Yes, performance was evaluated in a standalone manner.
  • Nonclinical Testing: Phantom studies directly evaluate the algorithm's output against known physical properties and defined metrics.
  • In-Vivo Performance Testing: ADC accuracy and low-contrast detectability were measured directly from the reconstructed images, which is a standalone evaluation of the algorithm's quantitative output.
  • Quantitative Post Processing: Repeatability and effectiveness of phase correction in real/imaginary channels are algorithm-centric evaluations.
  • Even the clinical image quality study, while involving a human reader, assessed the standalone output of the algorithm (AIR Recon DL with Phase Correction) for diagnostic quality.

7. Type of Ground Truth Used

• Expert Consensus: Not explicitly stated as the primary ground truth for quantitative metrics, but one radiologist's assessment served as the primary clinical ground truth.
• Pathology: Not used as ground truth in the provided study descriptions. While some datasets "included pathological features such as prostate cancer... hepatocellular carcinoma," the assessment by the radiologist was on "diagnostic quality" of the images, not a comparison against pathology reports for definitive disease identification.
• Outcomes Data: Not used as ground truth.
• Other:
  • Physical Properties/Known Standards: For phantom testing (e.g., signal bias, noise floor, SNR, sharpness), and for theoretical expectations of ADC values in specific regions (lateral ventricles).
  • Known Synthetic Inserts: For low-contrast detectability.
  • Theoretical Expectations: For phase correction effectiveness (signal in real, noise in imaginary).

8. Sample Size for the Training Set

• The document does not provide any specific sample size for the training set used for the deep learning models (DLPC and PC-ARDL). It only states that the models are "deep learning-based."

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

• The document does not provide any information on how the ground truth for the training set was established. It only describes the testing of the final, trained models.

Ask a specific question about this device