(91 days)
ASTRA is software image management intended to receive, process, review, display, print and archive medical images and data from imaging modalities (e.g., CR and DR), Images and data can be stored, communicated, and displayed within the system or across computer systems. ASTRA is comprised with three configurations depending upon the requirements of the user and desired options: ASTRA Plus , ASTRA Lite, and ASTRA Mobile. ASTRA runs on a PC workstation, iPad, or iPhone and may be interfaced with verified and validated image acquisition devices from Candelis or other PACS systems. Diagnosis is not performed by the software but by Radiologists, Clinicians or referring Physicians. Typical users of this system are trained professionals, e.g. physicians, radiologists, nurses, medical technicians, and assistants.
ASTRA Plus is used to:
- share reports and studies with other ASTRA peers .
- review reports and studies .
- . download and save reports
- send reports to local EMR, EHR, RIS, HIS or PACS systems (HL7 send) .
- . route studies to PACS, Workstations, or other ASTRA peers
ASTRA Lite is used to:
- share reports and studies with other ASTRA peers .
- . review reports and studies
- download and save reports .
- send reports to local EMR, EHR, RIS, HIS or PACS systems (HL7 send) .
ASTRA Mobile is used to:
- share reports with other ASTRA peers .
- review reports .
- . download and save reports
- . send reports to local EMR, EHR, RIS, HIS or PACS systems (HL7 send)
Only pre-processed DICOM for presentation images can be interpreted for primary image diagnosis in mammography. Lossy compressed Mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 Megapixel resolution and meets other technical specifications reviewed and accepted by FDA.
ASTRA is a web-enabled software application that provides image processing and viewing tools and access to studies and reports from a Local Area Network. Wide Area Network, remote workstation, personal computer, or an iPhone, or iPad via a Virtual Private Network connection. Diagnosis is not performed by the software but by Radiologists, Clinicians or referring Physicians. The software application conforms to the DICOM 3.0 standard to allow interoperability with other DICOM compliant systems.
The provided text is a 510(k) summary for the ASTRA Picture Archiving Communications System. It describes the device's function and its intended use, but it does not contain detailed information about specific acceptance criteria or the study used to prove the device meets those criteria, especially in the context of diagnostic accuracy or performance metrics of AI systems.
The document states:
"The complete system configuration has been assessed and tested at the factory and the device has passed all in-house testing criteria without significant failures. The data presented in the submission demonstrates that the ASTRA device performs all required actions according to the functional requirements specified in the SRS and User Manual with no errors that had an impact on safety or efficacy."
This indicates that there was internal testing against functional requirements, but it does not provide the specific metrics, methodologies, or results typically expected for a detailed AI device performance study.
Given the information provided, I cannot populate the requested table or answer most of the questions related to acceptance criteria and a definitive study demonstrating performance. The device, ASTRA, is described as a "Picture Archiving Communications System" and explicitly states: "Diagnosis is not performed by the software but by Radiologists, Clinicians or referring Physicians." This means it is a tool for image management and viewing, not a diagnostic AI system that would have performance metrics like sensitivity, specificity, or accuracy in lesion detection.
Therefore, many of the requested categories are not applicable to the information contained in this 510(k) summary. I will answer the questions based on the available information and explicitly state when the information is not present.
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Functional) | Reported Device Performance |
|---|---|
| Performs all required actions according to SRS and User Manual | Passed all in-house testing criteria without significant failures. Performs all required actions with no errors impacting safety or efficacy. |
| Interoperability with other DICOM compliant systems | Conforms to the DICOM 3.0 standard. |
| Web-enabled software application | Yes |
| Provides image processing and viewing tools | Yes |
| Access to studies and reports from various network types | Local Area Network, Wide Area Network, remote workstation, personal computer, iPhone, or iPad via VPN. |
| Stores, communicates, and displays images and data | Yes |
| Supports multiple configurations (ASTRA Plus, ASTRA Lite, ASTRA Mobile) | Yes, each with specific functionalities (sharing, reviewing, downloading, sending reports). |
| Interfaced with verified/validated image acquisition devices | Yes, from Candelis or other PACS systems. |
Note: This table reflects functional and interoperability criteria for an image management system, not diagnostic performance metrics for an AI algorithm.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not provided in the document. The testing described is "in-house testing criteria" based on functional requirements, not a clinical study with a defined test set of medical images from patients.
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)
This information is not provided and is not applicable given that the device does not perform diagnosis and its testing focused on functional requirements rather than diagnostic ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided and is not applicable for the reasons stated above.
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
There is no indication that an MRMC comparative effectiveness study was conducted. This device is an image management system, not a diagnostic AI that assists human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
A standalone performance study focused on diagnostic accuracy was not done as the device is not intended for diagnosis. The documentation explicitly states: "Diagnosis is not performed by the software but by Radiologists, Clinicians or referring Physicians."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Ground truth in the diagnostic sense (e.g., expert consensus for lesions, pathology results) was not used for the testing described, as the device is not a diagnostic AI. The "ground truth" for its testing was adherence to "functional requirements specified in the SRS and User Manual."
8. The sample size for the training set
This information is not provided as the device is not described as a machine learning/AI diagnostic tool that would typically involve a training set.
9. How the ground truth for the training set was established
This information is not provided as there is no mention of a training set or associated ground truth in the context of an AI model.
§ 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).