(80 days)
The DICOM Video software package is intended for use by authorized personnel to acquire individual or sequences of images and to allow the user to input patient demographics related to the image. The device transforms imaging studies to DICOM format before they are made available to other locations in the network. The DICOM Video is indicated to receive studies in various digital formats (text, still images and video) or digitized video signals from acquisition host devices. The device operations include capturing the data, recording, storing, editing and transferring it to the clinic PACS as DICOM files.
The DICOM Video is a software package, which is installed in an Off - The - Shelf Host PC. The device is interfaced and configured to a hospital Local Area Network (LAN). The DICOM Video receives patients' list from the Hospital Modality Work List (MWL ) server and digital files input data (in text, images or video formats). The device records the received data, stores it, transfers the studies into standard DICOM files, and transmits the DICOM files via the LAN to the Hospital PACS. The DICOM Video can be interfaced to a Host Acquisition Device in order to receive analog video signals. The data is digitized, stored, optionally edited, transferred into standard DICOM files, and transmitted as DICOM files via the LAN to the Hospital PACS. The device can also retrieve DICOM studies from the PACS and display them on the user screen.
Here's a breakdown of the acceptance criteria and the study information for the DICOM Video device, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document (K132183) for the DICOM Video device does not explicitly list "acceptance criteria" in a quantitative or pass/fail table as one might expect for a diagnostic AI device. Instead, the performance is described in terms of compliance with standards and successful functionality testing.
| Acceptance Criteria Category / Performance Aspect | Reported Device Performance |
|---|---|
| Design Verification and Validation | Complied with 21CFR 820.30 regulations. |
| DICOM Conformance | Tested in conformance to NEMA PS 3.1 - 3.20 (2011) DICOM set and found conforming. |
| Software Performance (Bench Data) | Verified by testing the software with respect to a predefined software test plan. |
| Device Validation (End-User Environment) | Validated by testing the performance with respect to a predefined test plan in an end-user environment. |
| Safety & Effectiveness | Methods of testing safety & effectiveness adhere to state-of-art standards. Test results demonstrated that the device output meets the design input and supports the indications for use. |
| Intended Use & Indications for Use | The device is intended for use by authorized personnel to acquire individual or sequences of images, input patient demographics, transform imaging studies to DICOM format, and transfer to PACS. It receives various digital formats (text, still images, video) or digitized video signals. These operations include capturing, recording, storing, editing, and transferring. |
| Equivalence to Predicate Device | Demonstrated substantial equivalence in intended use, indications for use, and technological characteristics to the predicate device (K000411 CHILI VIDEO/VIDEO PRO), without raising different questions of safety and effectiveness. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify a numerical sample size for any test set or provide details on data provenance (e.g., country of origin, retrospective/prospective). The testing described is functional and compliance-based, rather than clinical efficacy studies involving patient data.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
Not Applicable. The device is a "Medical Image Digitizer" (a software package that converts various image and video formats into DICOM files and manages them). It does not perform diagnostic interpretations of medical images that would require expert consensus ground truth. Its "ground truth" would be related to the accurate and complete conversion and transfer of data according to DICOM standards and its stated functionalities.
4. Adjudication Method for the Test Set
Not Applicable. As explained above, this device does not involve diagnostic interpretations requiring an adjudication method by experts.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No. The document explicitly states: "Clinical Data: Clinical data is not included." An MRMC study assesses the impact of a device on human reader performance, which requires clinical data and human interpretation. This device is a data processing and management tool, not a diagnostic aid for human readers.
6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance Study
Yes, in essence. The "Bench data" described indicates standalone performance testing of the software itself: "The device performance has been verified by testing the software with respect to predefined software test plan." The "device validation" in an end-user environment further confirms its performance without explicitly relying on human interpretation of diagnostic findings, but rather on its functional execution.
7. Type of Ground Truth Used
The "ground truth" for this device's performance is based on:
- Compliance with specifications and standards: Adherence to NEMA PS 3.1 - 3.20 (2011) DICOM set.
- Functional correctness: Output meeting "design input" and supporting "indications for use" as demonstrated by predefined software test plans and end-user environment testing.
- Regulatory compliance: Conformance to 21CFR 820.30 regulations.
8. Sample Size for the Training Set
Not Applicable. This device is a pre-AI era software for data digitization and management. It is not an AI/Machine Learning model that would typically have a "training set" in the context of learning patterns from data. Its functionality is rule-based and standard-compliant.
9. How the Ground Truth for the Training Set Was Established
Not Applicable. As this is not an AI/Machine Learning device that requires a training set, the concept of establishing ground truth for a training set does not apply.
§ 892.2030 Medical image digitizer.
(a)
Identification. A medical image digitizer is a device intended to convert an analog medical image into a digital format. Examples include Iystems employing video frame grabbers, and scanners which use lasers or charge-coupled devices.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std.). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.