Search Results

axis PACS is a software application intended to perform operations relating to acquisition, display, digital processing, review, transfer, archive, measurements, teleradiology exchange of medical images and patient demographic information. axis PACS receives digital images and data from various modalities, including but not limited to; Computed Radiography (CR), Computed Tomography (CT), Magnetic Resonance (MR), Ultrasound (US), Fluoroscopy (RF), secondary screen captures devices, scanners, digitizers, or other imaging sources.

It is intended for use by the physician to aid diagnosis and used by medical professionals whenever they require access to medical images and patient demographic information. Users have access to a variety of measurement tools and image processing to aid them in viewing digital images.

This device may be used to archive mammography images (MG) but is not intended for primary diagnostic viewing of mammography images.

axis PACS can integrate with a health care institution's or physician's office Health Information System (HIS) or a Radiology Information System (RIS) for a fully integrated electronic patient record.

axis PACS is a Picture Archiving and Communication System (PACS) designed for the management, and Procession, manipulation, and processing of DICOM 3.0 images from modalities in a diagnostic viewing, artiming, axis PACS consists of the axis PACS Web software application on a server and the axis imaging secting. "Alle Prob on client computers connecting to the Server via the HTTPS protocol. axis PACS r Nos viewer ver DICOM 3.0 images over a medical imaging network, as well as export images to other applications.

Here's an analysis of the acceptance criteria and study information for the axis PACS device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes a PACS (Picture Archiving and Communication System) device. For such devices, acceptance criteria are typically related to their functionality, image quality, comparison to a predicate device, and compliance with regulations.

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

• Sample Size for Test Set: The document mentions "DICOM calibration images and actual patient images" were used for non-clinical testing. For the clinical test, it states "DICOM images were already obtained by the modalities." However, specific numbers for the test set sample size (i.e., how many cases or images) are not provided in the document.
• Data Provenance:
  • Non-clinical tests: "DICOM calibration images and actual patient images." The source of these "actual patient images" is not specified beyond being "used in both systems during the comparison testing."
  • Clinical tests: "DICOM images were already obtained by the modalities." These tests were conducted at Bedford Medical Center in Bedford, Indiana. The data appears to be retrospective as the images were already obtained.

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

• Number of Experts: For the clinical test, it states the test was conducted "under the supervision of the hospital's radiologist." This implies at least one radiologist was involved in the clinical comparison.
• Qualifications of Experts: "hospital's radiologist." No specific experience level (e.g., "10 years of experience") is mentioned.

4. Adjudication Method for the Test Set

The document describes a "side-by-side" comparison of axis PACS with the predicate device (e-Film Workstation) during both non-clinical and clinical tests. The clinical test involved direct supervision by a radiologist. This suggests a direct comparative assessment rather than a formal adjudication method like 2+1 or 3+1. The adjudication method appears to be a direct comparison by the supervising radiologist(s) to determine if axis PACS "performed as well as or exceeded" the predicate device.

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

• Was an MRMC study done? No.
• Effect Size: Since no MRMC study was performed to assess human reader improvement with AI assistance (as axis PACS is a PACS, not an AI diagnostic tool in this context), there is no reported effect size for human readers improving with AI vs. without AI assistance. The study focuses on the PACS system's performance relative to a predicate PACS.

6. Standalone (Algorithm Only) Performance Study

• Was a standalone study done? Yes, in a sense. The entire evaluation of axis PACS is a standalone performance study in relation to its predicate. The device itself (the software) is evaluated for its functionality and capabilities without being solely an "AI algorithm." The "algorithm" here essentially refers to the PACS software's core functions. The non-clinical and clinical tests described are evaluations of the device's standalone performance in comparison to a predicate device.

7. Type of Ground Truth Used

The ground truth for the comparison was primarily based on:

• Functional Equivalence: Assessing if axis PACS could perform the same operations and display information comparably to the predicate device. This is a functional ground truth checked against expected PACS behavior and predicate performance.
• Expert Comparison: The radiologist's assessment during the "side-by-side" clinical test served as the ground truth for performance and equivalence in a clinical setting. This falls under expert comparison/assessment.
• DICOM Standards: The use of "DICOM calibration images" suggests adherence to DICOM standards as part of the ground truth for image processing and handling.

8. Sample Size for the Training Set

The document does not specify a training set size. PACS systems, like axis PACS, are generally conventional software applications for image management and display, not AI/machine learning models that typically require explicit training data sets in the same manner. Its development would involve software engineering and testing cycles, rather than data-driven machine learning training.

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

As axis PACS appears to be a conventional PACS software and not an AI/ML diagnostic algorithm, the concept of "ground truth for a training set" as typically understood for AI models is not directly applicable. The "ground truth" for the development and verification of such software would be defined by engineering specifications, user requirements, and adherence to established medical imaging standards (like DICOM). This would be established through a combination of:

• Software requirements specifications.
• Industry standards (DICOM 3.0).
• User feedback and operational needs.
• Benchmarks against existing, legally marketed predicate devices.

Ask a specific question about this device