Search Results

The CTXX85 CT Scanner systems are intended to produce images of the head and body by computer reconstruction of xray transmission data taken at different angles and planes. The CTXXX85 CT scanner systems are indicated for head and whole-body X-ray Computed Tomography applications for both pediatric and adult patients. The images delivered by the system can be used by a trained physician and trained healthcare professionals as an aid in diagnosis, treatment preparation and radiation therapy planning.

The CTXX85 CT Scanner is a whole-body, multi-slice CT scanner platform that enables multiple configurations for diagnostic imaging. The systems produce images and calculations that are intended for use by competent medical personnel as part of a clinical diagnosis. There are three (3) models of the CTXX85 CT Scanner: CT1685 (16 slice configuration), CT6485 (64 slice configuration) and CT12885 (128 slice configuration). The CTXX85 system is designed for routine radiological imaging procedures as well as advanced techniques such as coronary CT angiography, brain / organ perfusion, cardiac imaging with gated ECG, and CT-guided procedures. The CTXX85 system is designed with LISA (Low-dose Iterative noise reduction Solution by Analogic), an advanced algorithm which reduces image noise while maintaining (or improving) spatial resolution and Iterative Bone Correction (IBC) in scan protocols associated with Head patient anatomy. The following main subsystems make up the scanner platforms: tilting gantry (X-ray tube, X-ray generator, X-ray beam collimator), data management system (detector array, electronics), patient table with accessories, power distribution unit, and operator console (touchscreen user interface computer, gantry control box). Accessories for the CT scanners include: patient table CT slicker cushion, head holder, foot extension board, wedge knee pad, patient restraints, IV pole and holder, QA phantom and mount, CIVCO table overlay and cardiac trigger module (CTM).

The provided text describes a 510(k) premarket notification for a CT scanner (CTXX85 with software version 1.3). The document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed clinical study with specific acceptance criteria and performance metrics for a novel AI/ML-based device.

Therefore, the document does not contain the information requested in points 1-9 regarding acceptance criteria and a study proving the device meets those criteria, especially in the context of AI/ML performance.

The submission confirms that:

• No clinical studies were required or conducted to support the substantial equivalence claim.
• The device's enhancements are primarily related to software-based algorithms (Metal Artifact Reduction, Extended Field of View), and new accessories/functionalities, rather than a completely new AI/ML diagnostic algorithm requiring extensive clinical validation.
• Performance data was collected through non-clinical test/performance testing (bench testing, phantom tests), adhering to various international and FDA consensus standards related to CT image quality, electrical safety, EMC, and software life-cycle processes.

Without a clinical study, details like sample size for a test set, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, or training set specifics are not available in this document.

Ask a specific question about this device

The Analogic CTXX85 CT Scanner systems are intended to produce images of the head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. The CTXX85 CT Scanner systems are indicated for pediatric and adult patients.

The CTXX85 CT Scanner is a whole-body, multi-slice CT scanner platform that enables multiple configurations for diagnostic imaging. The systems produce images and calculations that are intended for use by competent medical personnel as part of a clinical diagnosis. There are three (3) models of the CTXX85 CT Scanner: CT1685 (16 slice configuration), CT6485 (64 slice configuration) and CT12885 (128 slice configuration).

The CTXX85 CT Scanners includes LISA (Low-dose Iterative noise reduction Solution by Analogic), an advanced algorithm which reduces image noise while maintaining (or improving) spatial resolution.

The following main subsystems make up the scanner platforms: tilting gantry (X-ray tube, X-ray generator, X-ray beam collimator), data management system (detector array, electronics), patient table with accessories, power distribution unit, and operator console (touchscreen user interface computer, gantry control box).

Accessories for the CT scanners include: patient table CT slicker cushion, head holder, foot extension board, wedge knee pad, patient restraints, IV pole and holder and QA phantom and mount.

The provided text describes specific performance data for the Analogic CTXX85 CT Scanner, particularly focusing on the CT1685 model and its iterative reconstruction algorithm (LISA). However, the document does not present a formal table of acceptance criteria with corresponding reported device performance, nor does it detail a clinical study with specific metrics like sensitivity, specificity, or reader performance improvement (MRMC).

Based on the information provided, here's a breakdown of the requested elements:

Acceptance Criteria and Reported Device Performance

The document does not explicitly state a table of acceptance criteria with precise numerical targets. Instead, it indicates that the device's performance was evaluated against a set of standards and for image quality. The general acceptance criterion seems to be that the device "performs as intended" and its image quality is "diagnostic."

Ask a specific question about this device

The Analogic CTXX85 systems are intended to produce images of the head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. The CTXX85 systems are indicated for pediatric and adult patients.

The CTXX85 is a whole-body, multi-slice CT scanner platform that enables multiple configurations for diagnostic imaging. The systems produce images and calculations that are intended for use by competent medical personnel as part of a clinical diagnosis. There are two models of the CTXX85 scanner: CT6485 (64 slice configuration) and CT12885 (128 slice configuration).

The CTXX85 CT Scanners includes LISA (Low-dose Iterative noise reduction Solution by Analogic), an advanced algorithm which reduces image noise while maintaining (or improving) spatial resolution.

The following main subsystems make up the scanner platforms: tilting gantry (X-ray tube, X-ray generator, X-ray beam collimator), data management system (detector array, electronics), patient table with accessories, power distribution unit, and operator console (touchscreen user interface computer, gantry control box).

Accessories for the CT scanners include: patient table CT slicker cushion, head holder, foot extension board, wedge knee pad, patient restraints, IV pole and holder and QA phantom and mount.

The provided text describes a 510(k) premarket notification for the Analogic CT6485 and CT12885 Computed Tomography (CT) systems. It details the device, its intended use, comparison to predicate devices, and performance data to support substantial equivalence.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

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

The document does not specify explicit "acceptance criteria" in a numerical or target performance metric for image quality. Instead, it refers to fulfilling requirements of various consensus standards and demonstrating performance comparable to predicate devices. The reported device performance is described qualitatively as meeting these standards and the images being of diagnostic quality.

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

• Sample Size for Test Set: The document mentions "sample clinical images of the brain, chest, abdomen and extremity," but does not specify the exact number of images or cases used in the clinical evaluation.
• Data Provenance: Not specified. It's unclear if the clinical images were retrospective or prospective, or their country of origin.

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

• Number of Experts: "a board-certified radiologist" (singular).
• Qualifications of Experts: "board-certified radiologist." No further details on years of experience or subspecialty.

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

• Adjudication Method: None specified. The text only states that a single board-certified radiologist evaluated the images.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• MRMC Study: No, an MRMC comparative effectiveness study was not performed. The study description focuses on confirming diagnostic quality by a single reader and benchmarking against physical phantom measurements.
• Effect Size: Not applicable, as no MRMC study was conducted.

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

• Standalone Performance: The non-clinical performance testing on phantom models directly assesses the algorithm's performance without human interpretation (e.g., MTF, low contrast detectability, noise, CT number accuracy). This can be considered a form of standalone performance evaluation for image quality metrics.
  • "Image Quality performance testing for the CTXX85 was conducted on standard phantom models to assess modulation transfer function (MTF), low contrast detectability, noise, CT number accuracy, CT uniformity, axial slice thickness, helical slice sensitivity profile, axial and helical image quality for head and body."
  • "Testing was conducted to evaluate image quality performance of the iterative reconstruction algorithm."

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

• Non-clinical (Image Quality): The ground truth for image quality metrics (MTF, noise, etc.) is established by the physical properties of the phantom models and expected system performance based on established engineering principles and physics.
• Clinical (Diagnostic Quality): For the clinical images, the ground truth was expert opinion/assessment by "a board-certified radiologist" confirming "diagnostic quality." This is a subjective assessment rather than a definitive ground truth like pathology.

8. The sample size for the training set

• Training Set Sample Size: Not specified. The document does not mention the training of the LISA algorithm or any other components, nor does it provide a sample size for a training set. The focus is on the performance of the device as a whole.

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

• Training Set Ground Truth: Not specified. Since the training set sample size and details of the training itself are not provided, how its ground truth was established is also not mentioned.

Ask a specific question about this device

The Sonic Window is intended for the visualization of vessels and vascular access guidance of needles and catheters (Insertion of Peripheral Intra Venous (PIV) Catheters, as an example). The Sonic Window is not indicated for use by a layperson and shall be used by prescription only.

Intended Use: Diagnostic ultrasound imaging and visualization of vessels for vascular access guidance of needles and catheters as follows: Peripheral vascular

The Sonic Window with the addition of software to perform and display ultrasound fluid flow analysis is a fully integrated handheld ultrasound imaging system that displays real-time ultrasound images on a coronal plane at a constant depth from the transducer. The depth is controllable by the operator. The Sonic Window system consists of the Sonic Window handheld device, the Docking Station/Charger and the AC Adapter. The Sonic Window uses an imaging mode, C-Mode, which provides the visualization in the coronal plane of peripheral vessels and assessment of vessels width and depth for needle/catheter placement.

Here's a summary of the acceptance criteria and study information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly state numerical acceptance criteria or detail a specific performance study with measured results for the "Sonic Window" device. It generally states that "predetermined acceptance criteria was met" without specifying what those criteria were or the achieved performance values.

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

The document does not provide any information regarding the sample size used for the test set or the provenance of the data (e.g., country of origin, retrospective/prospective). The studies mentioned are "Performance, verification and validation testing" without specific details about patient data.

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

The document does not provide any information about the number of experts used or their qualifications for establishing ground truth.

4. Adjudication Method for the Test Set:

The document does not provide any information about the adjudication method used for the test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its Effect Size:

The document does not indicate that an MRMC comparative effectiveness study was done, nor does it provide any effect size for human readers improving with AI vs. without AI assistance. The device description mentions a "C-Mode" for visualization and assessment but doesn't describe AI assistance for human readers.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was done:

The document focuses on the device as an imaging system for "visualization of vessels and vascular access guidance." It does not describe a standalone algorithm performance without human-in-the-loop. The system displays images for an operator to use.

7. The Type of Ground Truth Used:

The document does not specify the type of ground truth used. It mentions design validation testing and performance testing but not the method for establishing ground truth for evaluating the device's accuracy in visualizing vessels or guiding access.

8. The Sample Size for the Training Set:

The document does not provide any information regarding the sample size for a training set. The device is described as an ultrasound imaging system, and the submission is a "Special 510(k) Device Modification" which implies changes to an existing device rather than the development of a de novo AI algorithm with specific training data.

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

As no training set is described, the document does not provide any information on how ground truth for a training set was established.

Ask a specific question about this device

The Sonic Window is intended for the visualization of vasular access guidance of needles and catheters (Insertion of Peripheral Intravenous (PIV) Catheters as an example). The Sonic Window is not indicated for use by a layperson and shall be used by prescription only.

The Sonic Window is a fully integrated handheld ultrasound imaging system that combines electronics, transducer, display and battery into the same device. The device is designed and optimized to visualize real-time ultrasound images on a Coronal (Constant Imaging Depth) plane positioned at a distance (depth) from the transducer that is controllable by the user.

The Sonic Window device is an integrated handheld ultrasound imaging system designed for the visualization of peripheral vessels and assessment of vessel width and depth for needle/catheter placement. It is intended for use by medical professionals via prescription.

There is no study described that proves the device meets specific acceptance criteria based on metrics like sensitivity, specificity, or accuracy for its intended clinical use. The document primarily focuses on non-clinical testing for safety and technical equivalence to predicate devices.

Table of Acceptance Criteria and Reported Device Performance

Study Details:

1. Sample size used for the test set and the data provenance: Not applicable. The document describes non-clinical engineering and safety tests, not a clinical test set with patient data.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for clinical performance was not established as part of the described non-clinical testing.
3. Adjudication method for the test set: Not applicable. No clinical test set.
4. 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 device is an ultrasound system, not an AI-assisted diagnostic tool as described in this document.
5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is a hardware device.
6. The type of ground truth used: For the non-clinical tests, the "ground truth" was based on established engineering and safety standards (e.g., maximum permissible acoustic output, compliance with IEC standards for electrical safety and EMC, mechanical and environmental endurance specifications).
7. The sample size for the training set: Not applicable. This document does not describe machine learning or AI components requiring a training set.
8. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

The AN6255 and AN6265 are digital X-ray general radiography systems intended for use by qualified/trained doctor or technician and are designed to perform radiographic exposures of the whole body including skull, spinal column, chest, abdomen, extremitties and other body parts excluding mammography. Radiographic exposures may be taken with the patient in the sitting, standing, or lying in the prone or supine position.

Images from these systems are available for preview by the doctor/X-ray technician on the operator's workstation within seconds of the x-ray exposure. Digital (DICOM) images can be stored on electronic media, or exported to a (DICOMPACS) network, clinical review station or to a film printer.

Digital Radiology Systems

The provided text does not contain information about acceptance criteria, device performance, or any studies conducted to prove the device meets specific criteria. The document is a 510(k) summary and FDA clearance letter for the Analogic AN6255 and AN6265 Digital Radiology Systems, establishing substantial equivalence to a predicate device. It details administrative information like the submitter's name, device name, and indications for use, but lacks any performance study data.

Therefore, I cannot fulfill your request for the specific information regarding acceptance criteria and studies as it is not present in the provided text.

Ask a specific question about this device

The SynePix 4600 is Thallium-doped Cesium Iodide and amorphous Silicon (a-Si) Digital Radiography (DR) detector intended for use by a qualified/trained doctor or technician and is designed to generate radiographic images of human anatomy. If is intended to replace radiographic film/screen systems in all general purpose diagnostic procedures.

The detector will be used with Analogic AN6255 and AN6265 (SyneRad Omni and SyneRad Omni RT) Systems. The AN6255 has a single tall stand and single detector, the AN6265 is a dual detector system with a tall stand and short stand.

The detector is not for use for mammography.

The SynePix 4600 is a 17 inch by 17 inch digital detector. It is intended to convert Xrays into electrical signals to create usable images for diagnostic use.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Analogic Corporation SynePix 4600 Detector:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific numerical acceptance criteria for the SynePix 4600 Detector. Instead, it relies on a comparison to a predicate device.

Acceptance Criteria (Implied): Substantial equivalence to the legally marketed predicate device (Kodak DirectView DR System Detector, K051483) in terms of technological characteristics and performance.

2. Sample Size for the Test Set and Data Provenance

The provided text does not specify a sample size for any test set or the data provenance (e.g., country of origin, retrospective/prospective). The claim of substantial equivalence is made based on "testing," but details of this testing are absent.

3. Number of Experts and Qualifications for Ground Truth Establishment

The provided text does not mention the number or qualifications of experts used to establish ground truth for any test set. Given the nature of a 510(k) submission primarily focused on substantial equivalence based on technological characteristics and non-clinical testing, explicit details about clinical expert reviews for ground truth are often not included unless a specific clinical study with human review is part of the submission.

4. Adjudication Method for the Test Set

The provided text does not specify an adjudication method for any test set.

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

The provided text does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. Therefore, there is no information on the effect size of how much human readers improve with AI vs. without AI assistance. This device is a digital radiography detector, not an AI-powered diagnostic tool, so such a study would not typically be part of its clearance.

6. Standalone (Algorithm Only) Performance Study

The provided text does not describe a standalone (algorithm only) performance study. This device is hardware (a detector) that produces images, not an algorithm that performs interpretations.

7. Type of Ground Truth Used

The provided text does not explicitly state the type of ground truth used. Given that the submission focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing, it's highly probable that the "ground truth" would be based on technical performance metrics derived from phantom studies, physics measurements, and comparisons of image quality against the predicate device, rather than clinical outcomes or pathology.

8. Sample Size for the Training Set

The provided text does not mention a training set sample size. As a digital detector (hardware), rather than an AI/ML algorithm requiring training, the concept of a "training set" in the context of machine learning does not apply here.

9. How Ground Truth for the Training Set Was Established

Since the device is a digital detector and not an AI/ML algorithm, the concept of a "training set" with established ground truth is not applicable to this submission.

Ask a specific question about this device

The FETALGARD Lite-NIBP is a Perinatal Monitoring System for non-invasively measuring and showing graphically abdominal contractions, fetal heart rate, maternal non-invasive blood pressure, and maternal heart rate by means of display on a non-permanent graphical display and optionally on a printer. This data is to aid in assessing the well-being of the fetus and mother during the final trimester of pregnancy (non-stress test). This device is for use only by trained medical personnel located in hospitals, clinics, doctors' offices, and patient's home.

The FETALGARD Lite-NIBP is a compact, lightweight device for measuring, processing, displaying, and printing information derived from four physiological measurements:

• Fetal Heart Rate. Two types of ultrasound transducers can be used to monitor single or twins fetal heart rate and display real-time on the LCD screen or permanently recorded on the optional printer.
• Uterine Activity. Uterine pressure changes via a tocotonometer are used to monitor uterine contractions. The waveforms are displayed real-time on the LCD screen or permanently recorded on the optional printer.
• Maternal non-invasive blood pressure. Blood pressure is measured non-invasively (NIBP) by the oscillometric method.
• Maternal heart rate. The algorithm used to derive maternal heart rate is identical to the derived heart rate parameter used in the C3 Patient Monitor when the NIBP module is the measurement source.
  A printer records fetal heart rate and tocotonometer waveforms, maternal non-invasive blood pressure value, and maternal heart rate value.
  The FETALGARD Lite-NIBP is powered by internal sealed lead-acid batteries or from the mains supply via an external battery eliminator. A fully charged battery will power the monitor for two hours minimum.

The provided document is a 510(k) Summary for the Analogic Corporation's FETALGARD Lite-NIBP. This type of regulatory submission primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving the device meets specific acceptance criteria through a clinical study with detailed performance metrics.

Therefore, the document does not contain the following information:

• A table of acceptance criteria and reported device performance: The document cites various IEC and ANSI/AAMI standards that the device will be tested against, but it does not provide specific acceptance criteria or the numerical results of these tests in a table form.
• Sample size used for the test set and data provenance: No test set is described in terms of sample size or origin.
• Number of experts and their qualifications for ground truth: Ground truth establishment by experts is not mentioned for non-clinical testing.
• Adjudication method for the test set: No adjudication method is described.
• Multi-reader multi-case (MRMC) comparative effectiveness study: This type of study is not mentioned. The document focuses on non-clinical testing.
• Standalone (algorithm only) performance: As this is a medical device, the focus is on the integrated system rather than a standalone algorithm.
• Type of ground truth used: For the non-clinical tests mentioned, the "ground truth" would be compliance with the standards, not clinical outcomes or pathology.
• Sample size for the training set: There is no mention of a "training set" as the device is not an AI/ML algorithm that requires training data in the typical sense.
• How ground truth for the training set was established: Not applicable, as there's no mention of a training set.

What the document does describe in terms of testing and "acceptance" (equivalence):

The document outlines a series of non-clinical tests to demonstrate compliance, performance, and reliability, thereby supporting its substantial equivalence to predicate devices. These tests are primarily focused on safety, electromagnetic compatibility, alarm systems, and specific performance for non-invasive blood pressure monitoring.

Key statements regarding "acceptance criteria" (though not explicitly stated in a quantitative table):

• Compliance with Standards: The device must comply with a range of international and national standards, which serve as its de facto acceptance criteria for various aspects (safety, performance). These include:
  • IEC 60601-1 (and Amendments 1 & 2): Medical Electrical Equipment - General Requirements for Safety
  • IEC 60601-1-2: 2001: Medical electrical equipment - Electromagnetic compatibility emission limits meet Group 1 Class B
  • IEC 60601-1-4: Medical electrical equipment – Programmable electrical medical systems
  • IEC 60601-1-8: General requirements, tests and guidance for alarm systems in medical electrical equipment
  • IEC 60601-2-30: Particular requirements for the safety, including essential performance, of automatic cycling non-invasive blood pressure monitoring equipment
  • IEC 60601-2-49: Particular requirements for the safety of multifunction patient monitoring equipment
  • ANSI/AAMI SP10: Manual, Electronic, or Automated Sphygmomanometers
  • IEC 60068 series of standards: Mechanical shock and vibration tests
  • ISTA; Project 2A: Shipping container transportation tests (packaging)
• Other Tests:
  • Altitude tests (to ensure operation at higher altitudes does not adversely affect electrical safety or performance).
  • Tests to verify enclosure material robustness and resistance to cleaning materials.

Study Proving Acceptance (Substantial Equivalence):

The document refers to a "test schedule" of non-clinical tests that will be performed. The conclusion drawn is that "The test schedule of the FETALGARD Lite-NIBP combined with 'Information for Manufacturers,' September 1997, Track 1 tests already performed demonstrate that the FETALGARD Lite-NIBP and its associated safety and effectiveness is substantially equivalent to the performance of the FETALGARD Lite and the C3 Patient Monitor predicate devices cited in Section 5 of this summary."

In summary, for a 510(k) submission like this, "acceptance criteria" are generally understood as compliance with recognized standards and the demonstration of equivalent performance and safety to a predicate device through non-clinical bench testing. Specific quantitative performance metrics or clinical study results are typically not required unless a significant difference in technological characteristics or a new indication for use is introduced that cannot be assured through non-clinical data.

Ask a specific question about this device

The SyneRad Impact 60, SyneRad Impact 72 and Analogic AMS1600 are Computed Tomography X-ray Systems intended to produce images of the head and whole body by computer reconstruction of X-ray transmission data at different angle and planes. This device may include signal analysis and display equipment, patient, and equipment supports, components and accessories.

The SyneRad IMPACT 60, SyneRad IMPACT 72 and Analogic AMS1600 Multislice Computed Tomography Systems consist of a gantry, a patient table and an operator console. All three CT Systems are virtually identical. The physical size of all three systems is the same and they use the same control console, operating system and software. The Analogic AMS1600 is the platform from which the two Anexa systems are built and is identical in construction (except for cosmetics created by the covers) to the SyneRad IMpact 72. The difference between the SyneRad IMPACT 60 and the SyneRad IMpact 72 is the output rating of the High Voltage Power Supply mounted on the gantry. The SyneRad IMPACT 60 has a 60 kW PSU whereas the SyneRad IMpact 72 has a 72 kW PSU. The kVp levels are the same for both systems. The upper mA setting for the 60 kW system is 500 mA. The upper mA setting for the 72 kW system is 600 mA. The High Voltage Power Supply provides feedback to the control computer which selects the upper mA limit. These 16-slice CT scanners have a gantry aperture opening of 70 centimeters. They are based on proven Analogic computed tomography technology. They have a 16-row detector and a 0.50 second minimum scan time. High-speed image reconstruction is from an innovative reconstruction engine. The operator console is supplied with two 20-inch high resolution monitors. 3D software is standard. Workflow and patient throughput requirements are supported by local archiving and DICOM-based interconnectivity features.

The provided document describes the Analogic Corporation's SyneRad IMPACT 60, SyneRad IMPACT 72, and Analogic AMS1600 Computed Tomography X-ray systems. It is a 510(k) submission, meaning the company is seeking to demonstrate substantial equivalence to previously cleared devices, rather than conducting new clinical trials for effectiveness. Therefore, the information typically associated with acceptance criteria being met by a study might not be present in the same format as for novel devices.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a quantitative performance metric sense (e.g., sensitivity, specificity for a diagnostic task). Instead, it relies on demonstrating comparable technological characteristics and performance (measured on phantoms) to predicate devices.

The key performance comparison is presented in the "Key Parameters Comparison Chart":

Acceptance Criteria (Implicit via Substantial Equivalence): The implicit acceptance criterion is that the new devices perform as well as or better than the predicate devices in the listed image quality parameters, and share similar functional characteristics and intended uses.

Reported Device Performance: As seen in the table, the SyneRad systems show comparable or slightly better high-contrast spatial resolution (e.g., 0% MTF of 17.25 lp/cm vs. 15.4 lp/cm for GE, 50% MTF of 8+ lp/cm vs. 8.5 lp/cm for GE) and identical low-contrast resolution (5 mm @ 0.30%) to the predicate devices. Other features like displaying CTDI and DLP are also matched.

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

The document states: "Their X-ray power and technique factors are comparable to the predicate devices. They also have comparable image quality performance (measured on phantoms) as the predicate devices."

• Sample Size for Test Set: Not explicitly stated as a number of patients or cases. The testing was conducted on phantoms, which are inanimate objects designed to simulate human tissue for specific measurements. The specific number of times each phantom was scanned or the variety of phantoms used is not detailed.
• Data Provenance: The data appears to be prospective bench testing conducted internally by Analogic Corporation on their new devices in comparison to characteristics of predicate devices. There is no mention of country of origin for patient data as no patient data was used for performance comparison.

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

Not applicable. Ground truth for phantom-based image quality measurements is typically established by physical measurements and the inherent design parameters of the phantoms themselves, not by human expert interpretation in the same way as clinical diagnostic studies.

4. Adjudication Method for the Test Set

Not applicable. As no human expert interpretation or clinical decision-making was involved in establishing the "ground truth" for the phantom testing, no adjudication was necessary.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No. This is a 510(k) submission for a new CT scanner system, not an AI-powered diagnostic algorithm. Therefore, no MRMC study or assessment of human reader improvement with AI assistance was performed or is relevant to this submission.

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

Yes, in a way. The performance evaluation was essentially "standalone" in that it focused on the device's technical specifications and image quality capabilities (phantom-based measurements) without involving human interpretation or clinical outcomes. The "algorithm" here is the CT reconstruction and imaging process itself.

7. The type of ground truth used

The ground truth for the core image quality metrics (High Contrast Spatial Resolution, Low-Contrast Resolution) was established through phantom measurements. These phantoms (e.g., "CATPHAN") have known physical properties and are used in a standardized way to objectively quantify imaging performance.

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. The "training" for the device, if one could apply the term, would be its engineering design, calibration, and manufacturing processes.

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

Not applicable, as there is no training set in the context of this traditional medical imaging device.

Ask a specific question about this device

The device is for use on individual adult and pediatric patients in hospital areas and hospital-type facilities, such as clinics. Clinical users may use the monitor during hospital transport. These indications were previously cleared under K030931 and K041434.

The purpose and function of the LIFEGARD II Family is to monitor:

• ECG
• Heart rate
• Non-invasive blood pressure (NIBP)
• Functional arterial oxygen saturation (SpO2)
• Respiration rate
• Temperature and
• End-tidal carbon dioxide (EtCO2)
• Impedance Cardiography (ICG)
• Arrhythmia with ST segment detection
• Continuous non-invasive blood pressure (CNIBP)

The Impedance Cardiography (ICG) is intended for use on individual adult patients that meet the limits specified below:

• Height: 4 ft - 7 ft - 6 in (122 - 229 cm)
• Weight: 67 - 350 lbs (30 - 159 Kg)

The CNIBP is a non-invasive blood pressure monitor which uses a pressure sensor placed on the wrist over the radial artery. This device is intended to be used on patients by trained medical personnel to continuously monitor systolic, diastolic and mean blood pressure and pulse rate. This pressure information is intended to guide clinicians in the therapeutic management of their patients by providing accurate and frequent updated blood pressure information in a safe, non-invasive, easily obtained and comfortable manner.

The LIFEGARD II Family is a compact, lightweight device for measuring, processing, printing, and displaying information derived from nine physiological measurements:

• Electrocardiogram (ECG). A three lead or five lead ECG is acquired and a waveform can be displayed real-time on the LCD screen or permanently recorded on the optional printer. The design of the ECG function is derived directly from the predicate devices, the parent C3 Family of patient monitors.
• Respiration. Waveform and numeric respiration rate value from ECG. Airway respiration rate from EtCO2 if available. The design of the respiration parameter is derived directly from the predicate devices, the parent C3 Family of patient monitors.
• Arrhythmia with ST segment analysis software performs five distinct operations: beat detection, lead selection, beat classification, ventricular tachyarrhythmia detection, and ST segment measurement. The design of arrhythmia with ST segment function provides VF and ST segment deviation functionality similar to the predicate device, M3046A (M2/M3/M4) Compact Portable Patient Monitor
• Pulse Oximetry (SpO2). Functional Oxygen Saturation is calculated from the ratio of light transmissivity through the capillary bed at two wavelengths. The SpO2 subsystem uses software and firmware that is used in the OxiMAX Pulse Oximetry System and Sandman SD20 Amplifier patient monitor and system.
• The temperature is measured using thermistor probes for continuous temperature measurements. These are pre-amendment devices.
• Blood pressure is measured non-invasively (NIBP) by the oscillometric method. This is the same as in the predicate devices, parent C3 Family of patient monitors.
• Continuous non-invasive blood pressure (CNIBP) is a non-invasive blood pressure monitor which uses a pressure sensor placed on the wrist over the radial artery. This is the same technology as in the predicate device, Vasotrac APM205A.
• End-tidal CO2 (EtCO2) This method pulls a constant sample flow of exhaled breath from the patient, and analyzes it with a remote CO2 sensor built into the measurement system. This is the same as in the predicate devices, parent C3 Family of patient monitors.
• Impedance Cardiograph (ICG). This mode uses Thoracic Electrical Bioimpedance (TEB). This is identical in all aspects to the predicate device, the C3 ICG.
• An internal thermal printer records waveforms, hemodynamic parameters and tabular trends on a 50-mm wide strip chart.
• External USB printing identical to the parent C3 Family.

The LIFEGARD II Family is powered by internal sealed lead-acid batteries or from the mains supply via a battery eliminator. A fully charged battery will power the monitor for three hours.

The provided text describes a 510(k) summary for the Analogic Corporation LIFEGARD II Family of patient monitors. It extensively details the device's characteristics, intended use, and comparison to predicate devices, focusing on regulatory equivalency rather than specific detailed clinical study results to demonstrate acceptance criteria performance.

Therefore, much of the requested information regarding a detailed study proving the device meets acceptance criteria, including sample sizes, expert qualifications, adjudication methods, and ground truth establishment for AI performance, is not present in this document. This document primarily outlines non-clinical tests and regulatory compliance to establish substantial equivalence with predicate devices.

However, based on the information available, I can construct the table of acceptance criteria (as inferred from the non-clinical tests) and indicate the reported device performance in a general sense where mentioned.

Here's the breakdown of what can be extracted and what cannot:

1. Table of acceptance criteria and the reported device performance

The document lists various non-clinical tests and standards that the device will be subjected to. These standards implicitly define the acceptance criteria for various aspects of the device's safety and performance. The "reported device performance" is generally stated as "will be conducted" or "demonstrates that the performance... is substantially equivalent."

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

• Not provided. The document focuses on non-clinical testing and regulatory compliance rather than detailed clinical study results with specific sample sizes. The "AAMI EC 57 tests already performed" implies some test data exists, but details are absent.

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

• Not provided. This information would typically be found in a clinical study report, which is not part of this 510(k) summary.

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

• Not provided. This information is absent.

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 / Not provided. The LIFEGARD II Family device is a patient monitor, not an AI-assisted diagnostic tool that would typically involve human readers interpreting results in a comparative effectiveness study. The "Arrhythmia with ST segment analysis software" is an algorithm within the device, not an AI for human interpretation enhancement. The document primarily focuses on the device's technical specifications and equivalency, not its impact on human reader performance.

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

• Yes, implicitly. The context of the "Arrhythmia with ST segment analysis software" and other measurement parameters (SpO2, NIBP, EtCO2, etc.) indicates these perform their functions as standalone algorithms within the device. The document states: "Arrhythmia with ST segment analysis software performs five distinct operations: beat detection, lead selection, beat classification, ventricular tachyarrhythmia detection, and ST segment measurement." Similarly, SpO2 calculates saturation, and NIBP measures blood pressure. These are inherent functions of the device's algorithms.

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

• Not explicitly detailed, but inferred from testing standards. For parameters like ECG, NIBP, SpO2, and EtCO2, ground truth would typically be established by established reference methods or highly accurate (often invasive or laboratory-grade) measurement devices during testing against the standards mentioned (e.g., AAMI EC 57 for ECG, ANSI/AAMI SP10 for NIBP, EN 865 for SpO2, EN 864 for EtCO2). The document suggests that the performance of these integrated modules is evaluated against these industry-accepted standards, implying that the "ground truth" is defined by such reference methods.

8. The sample size for the training set:

• Not applicable / Not provided. This device pre-dates the widespread use of deep learning and large-scale training sets for medical devices, particularly for a summary from 2005. The mention of "design of the ECG function is derived directly from the predicate devices" and "SpO2 subsystem uses software and firmware that is used in the OxiMAX Pulse Oximetry System" points to established, possibly rule-based or conventional signal processing algorithms, rather than models requiring large training sets in the modern AI sense.

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

• Not applicable / Not provided. As mentioned above, the concept of a "training set" with ground truth in the current AI/ML context is likely not relevant to this device's development as described in a 2005 510(k) summary. The algorithms' development would have relied on engineering principles, signal processing, and testing against known physiological signals and reference measurements, rather than ground truth established for a statistical learning model.

Ask a specific question about this device