Search Results

The Discovery CT590 RT/Optima CT580 Computed Tomography Systems are intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data taken at different angles and planes, including Axial, Cine, Helical (Volumetric), and Gated (Respiratory and Cardiac) acquisitions for all ages. These images may be obtained either with or without contrast. This device may include signal analysis and display equipment, patient and equipment supports, components and accessories. This device may include data and image processing to produce images in a variety of trans-axial and reformatted planes. Further the images can be post processed to produce additional imaging planes or analysis results.

The GE Discovery CT590 RT/Optima CT580 Computed Tomography Systems are indicated for head, whole body, and vascular X-ray Computed Tomography applications in patients of all ages.

The device output is a valuable medical tool for the diagnosis of disease, trauma, or abnormality and for planning, guiding, and monitoring therapy.

The system is capable of assisting with minimally invasive procedures such as biopsy and ablation of tumors and pathology. The system allows imaging of Bariatrics patients, up to and including the morbidly obese population (BMI > 40).

The system can acquire CT anatomical images that are clinically useful in the simulation and planning of radiation therapy for the treatment of cancer.

If the Deviceless 4D option is included on the system, the system can be used to efficiently provide and display CT images of all phases of a breathing cycle for the evaluation of respiration-induced motion of the chest for use with therapy planning and simulation.

The software calculates the breathing period to determine the Cine acquisition duration and the cine time between images which is automatically imported to the 4D cine acquisition. The software then uses information derived from the imaging for the binning process.

Deviceless 4D is a software option used for capturing the respiratory cycle and binning the image such that the target motion may be obtained for treatment planning. Deviceless 4D has the same intended use and clinical output of Advantaae 4D (A4D,K032915) which was included in the cleared Discovery CT590 RT/ Optima CT580 (K093581) CT system. Deviceless 4D is an alternative and efficient solution for 4D imaging and virtual simulation without the need for an external respiratory monitoring device.

Deviceless 4D first uses a "scout-like" scan type called "SmartBreath" to determine the stable breathing cycle period that is then automatically implemented into the scan parameters for the Cine scans.

D4D incorporates a design that uses internal anatomic features of the respiratory cycle obtained during the Cine scans for image binning. These features are temporally registered to the actual breathing cycle.

The Discovery CT590 RT and Optima CT580 series of systems are composed of a gantry, patient table, operator console, computer, and power distribution unit (PDU), and interconnecting cables. The systems include image acquisition hardware, image acquisition, reconstruction software, associated accessories, and connections/interfaces to accessories.

The current systems are an evolutionary modification to the Discovery CT590 RT and Optima CT580 (K093581) by adding software features, quality fixes, IEC Ed. 3 compliance, and modifications in hardware for RoHS compliance and technology obsolesces.

The "16-slice", system generates cross-sectional images of the body by computer reconstruction transmission data taken at different angles and planes, including Axial. Cine, Helical (Volumetric) and gated acquisition modes. It has a maximum total collimation coverage of 20mm in the z direction.

The Discovery CT 590 RT and Optima CT 580 series of systems are designed to be a head and whole body CT systems incorporating the same basic fundamental operating principles and similar indications for use.

The provided submission focuses on establishing substantial equivalence for the GE Discovery CT590 RT/Optima CT580 with Deviceless 4D Option to its predicate devices, rather than presenting a detailed independent study with explicit acceptance criteria for the new feature or a comparative effectiveness study with human readers.

However, based on the information provided, here's a breakdown addressing the requested points:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in terms of specific performance metrics (e.g., accuracy, sensitivity, specificity) for the Deviceless 4D option. Instead, the "acceptance criteria" are implied through the demonstration of equivalence to the predicate device.

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

• Sample Size for Test Set: The document mentions "clinical datasets from GE's internal development database" were used. However, the exact sample size (number of patients or scans) for this test set is not specified.
• Data Provenance: The data was sourced from "GE's internal development database," implying it's likely internal to GE and potentially collected from various regions where GE conducts development. The document does not specify the country of origin or whether it was retrospective or prospective. Given it's an "internal development database," it's highly likely to be retrospective data collected during prior development or clinical evaluations.

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

The submission does not mention using experts to establish ground truth for the test set or their qualifications. The comparison was primarily performed against the predicate device's output (Advantage 4D) as the reference.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method. The comparison was made directly between the D4D feature's output and the predicate A4D's output using statistical analysis.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done or reported in this submission. The focus was on demonstrating the technical equivalence of the D4D software to the existing A4D software using phantom and internal clinical data. There is no mention of human reader performance or improvements with or without AI assistance.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance evaluation of the Deviceless 4D (D4D) algorithm was performed.

• "Bench testing of and image review of the D4D feature provided additional data that this feature works both as intended and to provide the requisite data to substantiate performance claims, safety and efficacy, and ultimately substantial equivalence."
• "The testing performed included testing using a commercially available breathing phantom... and clinical datasets from GE's internal development database were used to compare the binning and measurement of D4D to the predicate feature A4D."
  This clearly indicates that the algorithm's output was directly compared against a reference (the predicate A4D and phantom measurements).

7. Type of Ground Truth Used

The ground truth used for the D4D evaluation was effectively the output of the predicate device's Advantage 4D (A4D) feature for binning and measurement from clinical datasets, and measurements from a commercially available breathing phantom for assessing breathing periodicity detection. This can be considered a form of "reference standard comparison" where the established performance of a cleared device or a known physical property (phantom) serves as the truth.

8. Sample Size for the Training Set

The document does not specify the sample size for the training set. It only mentions the use of "GE's internal development data base" for clinical datasets used in testing, but it's unclear if this same database was used for training or if other data was used, and if so, how much.

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

The document does not provide information on how the ground truth for the training set was established. Given the nature of a 510(k) submission focused on substantial equivalence to an existing device, a detailed account of training data ground truthing might not be deemed necessary if the underlying technology is largely similar and the primary claim is equivalence rather than novel performance.

Ask a specific question about this device

The Optima CT660 is intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data taken at different angles and planes, including Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisitions. These images may be obtained either with or without contrast. This device may include signal analysis and display equipment, patient and equipment supports, components and accessories.

This device may include data and image processing to produce images in a variety of transaxial and reformatted planes. Further the images can be post processed to produce additional imaging planes or analysis results.

The system is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

The device output is a valuable medical tool for the diagnosis of disease, trauma, or abnormality and for planning, guiding, and monitoring therapy.

The Optima CT660 and its associated configurations/packages is a multi-slice CT scanner system consisting of a gantry, patient table, operator console, power distribution unit (PDU), associated accessories, and connections/interfaces to accessories. The system includes image acquisition hardware, image acquisition & reconstruction software, associated accessories, and connections/interfaces to accessories. ASiR advanced reconstruction technology is also an option on this product and was cleared in K093581.

The Optima CT660 CT system is intended to be a head and whole body CT system incorporating the same basic fundamental operating principles and the same indications for use as the predicate device. Materials and construction are equivalent to our existing marketed products which are compliant with UL 60601-1, IEC 60601-1 and associated collateral and particular standards, and 21 CFR Subchapter J. It has been developed under the same GE quality system and has completed all design controls, including risk management, verification and validation.

Here's an analysis of the provided text regarding the Optima CT660, addressing your questions about acceptance criteria and study details.

Important Note: The provided document is a 510(k) Premarket Notification Summary for a CT Scanner. It's a regulatory submission to demonstrate substantial equivalence to a predicate device, not typically a comprehensive clinical study report for a novel AI algorithm or diagnostic tool. Therefore, many of your questions, especially those related to specific performance metrics like sensitivity/specificity, sample sizes for training/test sets, expert adjudication, or MRMC studies, are not directly addressed in this type of document because they are not usually required for a substantial equivalence claim for a CT scanner itself.

The focus here is on demonstrating that the new device meets established safety and performance standards equivalent to existing devices.

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

Since this is a CT scanner and not a device that produces a diagnostic output that would have metrics like sensitivity or specificity, the "acceptance criteria" are related to compliance with regulations and performance equivalence to a predicate device.

• 21 CFR Subchapter J (for CT X-ray systems).
• UL 60601-1.
• Designed and manufactured under Quality System Regulations of 21 CFR 820 and ISO 13485. |
  | Risk Mitigation (Electrical, Mechanical, Radiation Hazards) | Risks identified through risk management (hazard analysis) and controlled by:
• System verification and validation.
• Adherence and certification to industry and international standards.
• Compliance to applicable CDRH 21CFR subchapter J requirements. |
  | Image Acquisition and Reconstruction Capabilities | Intended to produce cross-sectional images via Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisitions, with or without contrast. Includes signal analysis, display, data/image processing for various planes (transaxial, reformatted, post-processed). |
  | Intended Use (Head, Whole Body, Cardiac, Vascular X-ray CT) | The system is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages. (Matches predicate and unmodified device). |
  | Performance Testing | Completed "performance testing (Verification)" and "comparison testing to the unmodified device." |

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

This document does not describe a test set or data provenance in the context of diagnostic performance studies. The "testing" mentioned refers to engineering verification and validation against technical specifications and regulatory standards, not clinical data performance.

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

Not applicable. This type of information is not present as a clinical diagnostic performance study with expert-adjudicated ground truth was not performed or detailed here.

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

Not applicable. No diagnostic test set or adjudication method is described.

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 Optima CT660 is a CT scanner, not an AI-assisted diagnostic tool for interpretation. There is a mention of "ASiR advanced reconstruction technology" as an option which was cleared in K093581, but no details of an MRMC study for ASiR are provided here.

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

Not applicable. No standalone algorithm performance is described.

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

Not applicable. For a CT scanner, the "ground truth" would relate to its ability to accurately acquire and reconstruct images according to physical specifications, not clinical diagnostic outcomes. The document indicates verification against specifications and comparison to the predicate device.

8. The sample size for the training set

Not applicable. This document is for a CT scanner, not a machine learning model developed with training data.

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

Not applicable. No training set is involved for this submission type.

Summary of the document's relevance to your questions:

This 510(k) summary focuses on demonstrating that the Optima CT660 (a new CT scanner) is substantially equivalent to a legally marketed predicate CT scanner. This means it has the same indications for use, employs the same fundamental technology, and meets the same safety and performance standards. It details engineering verification, validation, and compliance with regulations rather than clinical performance studies typically associated with AI/CAD devices, which would involve test sets, expert ground truth, and specific performance metrics.

Ask a specific question about this device