K Number
K071806
Date Cleared
2007-08-28

(57 days)

Product Code
Regulation Number
892.1750
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The ECLOS Computed Tomography system is an x-ray imaging device that produces cross-sectional images of the body at different angles. The system reconstructs, processes, displays, and stores the collected images. The device output can provide an aid to diagnosis when used by a qualified physician and is intended for general purpose CT applications.

Device Description

The ECLOS is a multi-slice computed tomography system that uses x-ray data to produce cross-sectional images of the body at various angles. The ECLOS system consists of a gantry, operator's workstation, patient table, highfrequency x-ray generator, and accessories.

AI/ML Overview

Here's a summary of the acceptance criteria and study information for the KD 71806 ECLOS Computed Tomography system, based on the provided text:

Acceptance Criteria and Device Performance

Acceptance Criteria CategorySpecific CriteriaReported Device Performance
Physical CharacteristicsSystem consists of a gantry, operator's workstation, patient table, high-frequency x-ray generator, and accessories.The ECLOS system consists of a gantry, operator's workstation, patient table, high-frequency x-ray generator, and accessories. (Stated as similar to predicate device).
Performance MetricsEquivalent or similar performance to predicate device (Hitachi PRESTO CT, K040902) across various imaging parameters."The evaluation results of the ECLOS were comparable to the predicate device and support our conclusion that the ECLOS CT system is substantially equivalent."
Specific non-clinical evaluations as stipulated in 21 CFR 1020.33(c), including: dose profile, image noise, modulation transfer function (MTF), slice thickness and sensitivity profile, slice plane location, and CT dose index.The ECLOS and predicate device were subjected to "the same non-clinical evaluations as stipulated in 21 CFR 1020.33(c). Evaluations include: dose profile, image noise, modulation transfer function (MTF), slice thickness and sensitivity profile, slice plane location, and CT dose index."
Technological EquivalenceAcquire data in the same manner as the predicate device.The ECLOS CT system acquires data in the same manner as the predicate device.
Operation of the system virtually identical to the predicate.The operation of the system is virtually identical to the predicate because both systems were produced using the same essential design concepts. The ECLOS operating system software is essentially the same, as well as the user interface.
Safety and EffectivenessSystem is safe and effective for the indicated use."Testing has proven that the system is safe and effective for the indicated use."
No new safety issues compared to the predicate device."Risk and hazard analysis shows that there are no new safety issues associated with this system as compared with the predicate device."

Study Details

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

    • The document does not specify a test set sample size in terms of patient images or specific test cases.
    • The evaluations were "non-clinical evaluations," suggesting the use of phantoms or laboratory-based testing rather than clinical patient data.
    • Data Provenance: Not explicitly stated as retrospective or prospective, but the focus on non-clinical evaluations suggests a controlled laboratory environment rather than a clinical trial. The country of origin is not specified, but the applicant is Hitachi Medical Systems America, Inc.
  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • The document does not specify the use of human experts to establish ground truth for image data. The evaluations were non-clinical, focusing on objective performance metrics of the hardware and software without human interpretation as the primary endpoint.
  3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

    • None reported. The evaluation relies on direct measurement and comparison of physical and technical performance parameters against a predicate device and regulatory standards (21 CFR 1020.33(c)) rather than subjective expert adjudication.
  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:

    • No MRMC comparative effectiveness study was done. This device is a foundational CT imaging system, not an AI-assisted diagnostic tool.
  5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

    • Yes, in essence. The entire evaluation is inherently "standalone" in the sense that it assesses the intrinsic physical and technical performance of the CT system itself (e.g., dose profile, image noise, MTF) without a human-in-the-loop diagnostic task being the primary endpoint. The device's output is intended to "provide an aid to diagnosis when used by a qualified physician," but the performance metrics are about the image quality and physical properties of the system, not the diagnostic accuracy of an algorithm.
  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • The ground truth was established by objective physical measurements and engineering specifications as defined in regulatory standards (21 CFR 1020.33(c)). Parameters like dose profile, image noise, MTF, slice thickness, etc., are measured directly from the system's output or test phantoms, not from clinical pathology or expert consensus on patient images.
  7. The sample size for the training set:

    • Not applicable / Not specified. This device is a CT scanner, not an AI/machine learning algorithm requiring a "training set" in the conventional sense. Its design and validation rely on engineering principles, physics, and comparison to a predicate device, rather than learning from a large dataset.
  8. How the ground truth for the training set was established:

    • Not applicable. As the device does not use a training set for machine learning, there is no ground truth established in this manner. The "ground truth" for its development and validation would be adherence to scientific and engineering principles, and performance matching established physical standards and predicate device characteristics.

§ 892.1750 Computed tomography x-ray system.

(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.