Search Results

The KODAK DIGITAL SCIENCE (KDS) Medical Image and Information Library is a DICOM conformant archival product designed for use within a Picture Archiving and Communication System (PACS). The system utilizes a prefetching algorithm to facilitate fast access to previous imagery.

The system consists of three main components: 1) the host CPU (a Sun SPARCstation 5 or 20) with pre-installed propriatary software, 2) the magnetic BI ARCORACIP S OF 201 orage Array RAID subsystem), and 3) a KODAK DIGITAL SCIENCE ADL 150 writeable CD jukebox. The RAID subsystem and the CD jukebox are managed by a hierarchical storage library that presents these two subsystems to the system software running on the host CPU as a single, very large filesystem. The power supply Provides power to operate the unit from a line voltage for 100, 120, 220, or 240 VAC, 50/60 Hz.

This 510(k) notification describes a medical image and information library system, not a device that would typically have performance-based acceptance criteria in the context of diagnostic accuracy or equivalent studies. The device is for image storage, distribution, and archival within a Picture Archiving and Communication System (PACS). As such, the "performance" here relates to its technical specifications and functionality as an archival system, rather than clinical efficacy as a diagnostic tool.

Therefore, the requested information elements (1-9) such as reported device performance, sample sizes for test sets, expert involvement, MRMC studies, standalone performance, and ground truth establishment are not applicable in the traditional sense for this type of device submission.

The "acceptance criteria" for a device like the KODAK DIGITAL SCIENCE Medical Image and Information Library would primarily revolve around its technical specifications, compliance with standards (like DICOM), and functional equivalence to its predicate device. The "study" proving it meets these criteria would be the technical documentation and comparison provided in the 510(k) submission itself.

However, I can extract information related to its technical specifications and comparison to the predicate device, which serves as its form of "performance" and "acceptance criteria" in this context.

Here's an interpretation based on the provided text, modified to fit the context of an archival imaging system:

1. Table of Acceptance Criteria (Technical Specifications) and Reported Device Performance

Note regarding "Acceptance Criteria": For this type of device, the "acceptance criteria" are largely based on demonstrating substantial equivalence to a predicate device and meeting technical specifications and industry standards (e.g., DICOM conformance). The provided "predicate device" column serves as the benchmark against which the new device is compared.

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

• Not Applicable. This device is an image storage and retrieval system. It does not perform diagnostic functions that require a "test set" of patient data in the sense of clinical evaluation for accuracy. The "testing" would involve functional tests, performance benchmarks (e.g., retrieval speed, storage capacity verification), and DICOM conformance tests, not clinical data sets for diagnostic performance.

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

• Not Applicable. See point 2. No ground truth establishment related to diagnostic accuracy is relevant for an image archival system.

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

• Not Applicable. See point 2.

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. This device is an archival system, not an AI-assisted diagnostic tool.

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

• Not Applicable. This device is an infrastructure component (archival system), not an algorithm that performs a standalone task requiring performance evaluation against human interpretation. Its standalone "performance" would relate to its technical specifications for storage, retrieval, and DICOM conformance.

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

• Not Applicable. See point 2. The "ground truth" for this device would be its adherence to technical specifications, proper functioning of its storage and retrieval mechanisms, and compliance with DICOM standards, all verified through engineering and functional testing.

8. The sample size for the training set:

• Not Applicable. This device is a hardware/software system for image archiving, not a machine learning model that requires a "training set."

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

• Not Applicable. See point 8.

Ask a specific question about this device