(25 days)
CharruaPACS System™ is a software based device that receives digital images and data from various sources (e.g. CT scanners, MR scanners, ultrasound systems, computed & direct radiographic devices, secondary capture devices, scanners, imaging gateways, etc.). Images and data can be captured, stored, communicated, processed and displayed within the system and or across computer networks at distributed locations. Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretation. Mammographic images may only be interpreted using an FDA cleared monitor.
The CharruaPACS System™ consists of the CharruaPACS Workstation/Server and the DICOM Viewer (CWS). The device is a software system to be used to handle and view DICOM compliant studies, which are stored within the device or specified network locations. The System supports DICOM C-STORE SCP for most used SOP classes, with uncompressed Transfer Syntax and JPEG lossless, JPEG lossy and JPEG 2000 Transfer Syntaxes, C-FIND and C-MOVE SCP Study Root model and C-ECHO Verification as SCP. It is composed of four applications: Admin, DICOM Server, WEB Server, and HTTP Client. The servers run as Windows Services. It also uses the Independent JPEG group library for JPEG compression/decompression and the OpenJPEG group library for JPEG 2000 compression/decompression. The advanced version uses PostgreSQL as database. WebServer is based on Indy Project TIdHTTPServer. The CharruaPACS System™ is intended for professional use, as a viewing tool for imaging studies, and is a 'Continuous Use' device. This device is also compliant with HIPAA regulations regarding patient privacy. There is no direct patient interaction with the device. The CharruaPACS System is intended to work as a standalone service that provides common PACS functionality.
The provided text describes a 510(k) submission for the CharruaPACS System™, a Picture Archiving and Communications System (PACS). For devices like PACS, substantial equivalence is often demonstrated through a comparison with a predicate device and verification that the new device does not introduce new safety or efficacy issues. The testing performed for such devices typically focuses on functional performance, cybersecurity, and adherence to relevant standards, rather than clinical performance for diagnostic accuracy.
Based on the provided text, the device itself (CharruaPACS System™) is a PACS for handling and displaying medical images, not an AI-powered diagnostic tool. Therefore, the "acceptance criteria" and "device performance" are related to its functionality as a PACS, and the "study" is a nonclinical verification and validation process against these functional requirements.
Here's a breakdown of the requested information based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance:
The document indicates that CharruaPACS System™'s performance was assessed against its predicate device (InstaRad K080334) through a feature-by-feature comparison and nonclinical testing. The "acceptance criteria" can be inferred from the features listed as "No difference" or where differences were determined to have "no impact on safety or efficacy" after testing. The "reported device performance" is that these criteria were met.
| Feature/Function | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Hardware Server | Functional operation with Intel i5 processor, Windows 7, Minimum 4GB RAM, Minimum 400GB HDD. | Tested and validated; no impact on safety or efficacy. |
| Workstation Client Hardware | Functional operation with Intel i5 processor, Windows 7, Minimum 4GB RAM, Minimum 400GB HDD. | Tested and validated; no impact on safety or efficacy. |
| Image Viewing Layout | Display standard formats (at least up to 2*3). | Meets this criterion; deemed a user preference and no impact on safety or efficacy. |
| Report Formats | Support DICOM SR for reporting. | Supports DICOM SR; deemed superior to predicate's MS Word for interoperability, no impact on safety or efficacy. |
| Other Shared PACS Features | Must provide features like WW/WL, Zoom, Hounsfield Measurement, Linear/Angle measurements, Series Comparison, Scout line, Stack mode, Gray scale invert, Filters, Rotate, Key Image selection, DICOM Print, Windows print, Query/Retrieve, Image compression (lossless streaming), Selection tools (thumbnails), Reporting Interface, Report Template Support, Digital Signature, Link to HIS/RIS, Electronic patient record (via broker), HIPAA compliance, RAID storage. | All these features were present and deemed equivalent ("No difference") or differences had no impact on safety or efficacy after testing. |
| General Functionality | Handle and view DICOM compliant studies, store within device/network, support DICOM C-STORE SCP, C-FIND, C-MOVE SCP Study Root model, C-ECHO Verification. | Confirmed through description and assumed to be validated by nonclinical testing. |
| Safety and Efficacy Equivalence | No new potential safety risks, equivalent in performance to existing legally marketed devices. | Nonclinical tests demonstrated device is as safe, as effective, and performs as well as the predicate device. |
| Integration and Installation Verification | Performance against acceptance criteria prior to release to client (if installed by CharruaSoft SA). | Performed by designated individuals; results demonstrated predetermined acceptance criteria were met. |
| All Input/Output Functions & Actions | All functions and actions in each operational mode must pass. | Passed all in-house testing criteria and verification/validation. |
2. Sample Size Used for the Test Set and Data Provenance:
The document does not specify a "sample size" in terms of patient cases or images for testing the PACS system's functionality. The testing described is "nonclinical testing" against functional requirements and a comparison to a predicate device's features. There is no mention of patient data.
- Test Set Sample Size: Not explicitly stated as a number of cases/images. The testing appears to be functional validation of the software system itself.
- Data Provenance: Not applicable, as this is a nonclinical validation of a PACS system's functionality, not an AI diagnostic algorithm tested on patient data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
This is not applicable. The CharruaPACS System™ is a PACS for image management and display, not an AI-powered diagnostic device requiring expert-established ground truth for diagnostic accuracy. The "ground truth" for this device relates to its functional specifications and adherence to DICOM standards, which would be assessed by software testers, engineers, and potentially quality assurance personnel familiar with PACS systems and relevant standards.
4. Adjudication Method for the Test Set:
Not applicable. There is no mention of multiple reviewers or an adjudication process for establishing a "ground truth" related to diagnostic findings, as this is a functional validation of a PACS.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. without AI Assistance:
No. An MRMC study is typically performed for AI-powered diagnostic tools to assess their impact on human reader performance. The CharruaPACS System™ is a PACS, not an AI diagnostic algorithm.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done:
Not applicable. The CharruaPACS System™ is a PACS, whose primary function is to manage and display images for human interpretation, not to provide standalone diagnostic interpretations.
7. The Type of Ground Truth Used:
For a PACS system, the "ground truth" for validation typically refers to:
- Functional Specifications: Whether the system performs its intended functions (e.g., storing images correctly, displaying them, executing tools like zoom, measurements).
- DICOM Conformance: Adherence to DICOM standards for image storage, transfer, and display.
- System Stability and Reliability: Absence of crashes, data corruption.
The document refers to "predetermined acceptance criteria" and "all verification and validation activities" confirming these criteria were met during nonclinical testing.
8. The Sample Size for the Training Set:
Not applicable. The CharruaPACS System™ is a PACS and is not described as involving machine learning or AI algorithms that require a "training set" of data.
9. How the Ground Truth for the Training Set Was Established:
Not applicable, as no training set for an AI algorithm is mentioned or implied.
§ 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).