K Number
K051315
Manufacturer
Date Cleared
2005-06-15

(26 days)

Product Code
Regulation Number
892.2050
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Sectra IDS5 device is intended for the manipulation and displaying of medical images, including mammograms. It can show images from different modalities and interfaces to various image storage and printing devices using DICOM or similar interface standards.

Device options make possible mammography reading, telecommunications; fast demonstration; prosthesis CAD; 3-D and angiography, etc.; and teleconferencing.

Lossy compressed mammographic images are not intended for diagnostic review. Mammographic images should only be viewed with a monitor approved by FDA for viewing mammographic images.

Typical users of this system are trained professionals, including but not limited to physicians, radiologists, nurses, medical technicians, and assistants.

Device Description

The Sectra IDS5 Workstation is mainly a software product. It is used for visualization and processing of digital medical images. The IDS5 is used as a client together with a Sectra provided server (Class I Exempt). The system runs on PCs under the Windows operating systems. Most notably two or more monitors are used.

The Sectra IDS5 Workstation is in fact a family of devices, including several workstations or types of workstations, e.g. the following:

  • Primary diagnostics workstation and the most powerful version of IDS5 -. IDS5/dx.net. It contains tools for assisting advanced users, e.g. the radiologists, in making a diagnosis.
  • Dedicated workstation for mammography IDS5/mx.net. It has all functionality as an . IDS5/dx.net but with an additional mammography package. Reading of mammographic images shall only be conducted with IDS5/mx.net.
  • Quality assurance workstation, mainly used by the technologists to prepare the images . for the reviewing radiologist.
  • Clinicians workstation used by the clinicians within the hospital to view the medical . images and to read the report.
  • . "Web" workstation that can be used by remote clinics to view images and reports.
  • "At-home" workstation that can be used by users, e.g. radiologists, over a low . bandwidth connection.
AI/ML Overview

The provided document (K051315) is a Special 510(k) submission for the Sectra IDS5 Workstation, which is primarily a software product for visualizing and processing digital medical images. However, the document does not contain specific acceptance criteria or a detailed study proving the device meets those criteria with quantitative performance metrics.

Instead, it's a "Substantial Equivalence" submission, which means the manufacturer is asserting that their new device is as safe and effective as a legally marketed predicate device (in this case, another version of the Sectra IDS5 Workstation, K050196). This type of submission often relies on demonstrating that the new device has "technological characteristics" and "performance data" that are similar to the predicate, rather than conducting new, large-scale clinical studies with specific performance targets.

Here's a breakdown of the information that is available based on your request, and where the document is lacking for other points:

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

  • Acceptance Criteria: Not explicitly stated as quantitative performance metrics. The implicit acceptance criteria appear to be substantial equivalence to the predicate device.
  • Reported Device Performance:
    • Developed according to ISO 9001:2000.
    • Complies with ACR/NEMA Digital Imaging Communications in Medicine (DICOM) version 3.0.
    • Functions as an Image Processing System (LLZ).
    • The document implies that the device performs its intended functions (image manipulation and displaying, mammography reading, etc.) reliably and safely, similar to the predicate.
Acceptance Criteria (Implicit)Reported Device Performance (as stated in the document)
Substantially equivalent to predicate device (K050196)"Based on the information supplied in this Special 510(k), we conclude that the subject device is safe, effective, and substantially equivalent to the predicate device."
Compliance with relevant standardsDeveloped according to ISO 9001:2000. Complies with ACR/NEMA Digital Imaging Communications in Medicine version 3.0.
Safe and effective visualization/processing of medical images"The Sectra IDS5 Workstation is mainly a software product. It is used for visualization and processing of digital medical images."
Appropriate for diagnostic interpretation by medical professionals"Images and information being reviewed, processed, relayed, and or transmitted are interpreted by a physician or trained medical personnel..."

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

  • Not provided. The document does not describe a test set or any specific data used for a performance study. This is typical for a 510(k) where substantial equivalence is claimed based on compliance with standards and functional similarity to a predicate.

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/Not provided. No explicit test set or ground truth establishment process is described in this document. The device is a viewer/processor, and its "performance" is primarily assessed against technical standards and functional equivalence, not diagnostic accuracy requiring ground truth. The primary diagnostics workstation (IDS5/dx.net) "contains tools for assisting advanced users, e.g. the radiologists, in making a diagnosis," but the performance of this assistance is not quantified here.

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

  • Not applicable/Not provided. No adjudication method is described as there is no specific test set or diagnostic study outlined.

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 document predates widespread AI assistance in such systems and does not describe any MRMC study or AI-related performance enhancement. The purpose of this device is image display and processing, not AI-driven diagnostic assistance.

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

  • No. The device is an image display and processing workstation that is inherently designed for "human-in-the-loop" operation. The document explicitly states: "Images and information being reviewed, processed, relayed, and or transmitted are interpreted by a physician or trained medical personnel, providing ample opportunity for competent human intervention."

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

  • Not applicable/Not provided. No ground truth is described as no diagnostic performance study of the device itself (beyond its functional capabilities and adherence to standards) is detailed.

8. The sample size for the training set

  • Not applicable/Not provided. This document does not describe any machine learning component or a "training set" in the context of AI.

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

  • Not applicable/Not provided. As there's no described training set, there's no ground truth establishment process for it.

In summary:

This document is a regulatory submission focused on demonstrating "substantial equivalence" of the Sectra IDS5 Workstation to a previously cleared predicate device, based on shared technological characteristics, adherence to quality management systems (ISO 9001:2000), and compliance with industry standards (DICOM). It explicitly states that "Images and information being reviewed, processed, relayed, and or transmitted are interpreted by a physician or trained medical personnel, providing ample opportunity for competent human intervention." Therefore, it does not contain the detailed performance study data, acceptance criteria (in terms of quantitative metrics), or ground truth establishment methods typically associated with AI/CADe devices or diagnostic accuracy studies.

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).