(494 days)
RadAlly™ is a software Medical Image Management and Processing System (MIMPS) intended to transfer, display, archive, and review medical images in DICOM format for diagnostic use by a licensed practitioner, such as a radiologist or any physician maintaining the correct licensing criteria to read and interpret medical images. RadAlly™ supports multimodality imaging such as Ultrasound (US), Digitized X-Ray Film (SC), Digital Radiography (DR), Computed Radiography (CR), Computed Tomography (CT), Magnetic Resonance (MR) Imaging. RadAlly™ is not intended for use with mammography - either film or full field digital mammography (FFDM) or tomosynthesis (Tomo or 3D Mammo). It is also not intended for use with nuclear medicine, PET, SPECT or CT fusion imaging.
RadAlly™ is not indicated for use on mobile displays. RadAlly™ may be interfaced with other DICOM modalities or MIMPS systems. All pertinent patient information may be displayed simultaneously. The viewer includes standard image measurement tools such as distance. RadAlly™ also includes manual measurement tools for use with ultrasound cardiac imaging, including Pressure-Half Time (PHT), Velocity-Time Integral (VTI), Aortic Valve Area (MVA).
RadAlly™ is a software MIMPS designed to receive, archive, and display medical images. RadAlly™ offers viewing tools such as zoom, pan, magnification, and window/level. It also offers manual measurement tools including distance measure, angle, and ultrasound cardiology measurements including PHT, VTI, AVA, and MVA.
The user is intended to be a licensed practitioner, who uses the software to receive and view medical images as well as patient data.
The software is designed for use on the following operating systems: Windows 10 and higher, MAC 10.10 and higher. RadAlly is compliant with ACR/NEMA DICOM 3.1-3.20. The software product may be installed on any PC or Mac hardware which is capable of running the stated operating systems. The hardware should include monitor, keyboard, mouse suitable for performing medical interpretation as stated for each modality by the ACR. The hardware must be web-enabled.
The device s self-contained software and is not bundled with any other device. It does not have any separable modules or additional options. RadAlly™ is the only model number.
RadAlly™ is software used to review medical images and patient information. It does not come into contact with patients, nor does it contain biologics or drugs. It is intended to be used to review multiple images sets. There are no coatings or additives. It does not require sterilization.
This submission package does not contain sufficient information to comprehensively answer all questions. Here's a breakdown of the available information and what's missing:
Acceptance Criteria and Device Performance Study
The submission does not explicitly state specific quantitative acceptance criteria for the RadAlly™ device. Instead, it relies on demonstrating that the device successfully underwent functional testing, software verification and validation, and performs comparably to a predicate device.
The reported device performance section is descriptive rather than quantitative, focusing on the successful completion of various tests and the device's equivalence to the predicate.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Explicitly Stated) | Reported Device Performance |
|---|---|
| Not explicitly stated as quantitative targets. | Successfully undergone functional testing. |
| Software verification and validation testing conducted. | |
| Measurements provided by the device validated using bench testing against images with known measurements. | |
| Measurements provided by the device validated through head-to-head comparison with the predicate device (when applicable). | |
| Found to have a safety and effectiveness profile similar to the predicate device. | |
| Passed all Verification and Validation testing. | |
| Features, functions, and technology demonstrated to perform well. | |
| Performs comparably to the predicate device. |
2. Sample Size for the Test Set and Data Provenance
- Sample Size: Not specified in the provided document. The submission states that measurements were validated "against images with known measurements" and "through head-to-head comparison with the predicate device," but the number of images or cases used for these tests is not mentioned.
- Data Provenance: Not specified. It's unclear if the images used were retrospective or prospective, or their country of origin.
3. Number of Experts Used to Establish Ground Truth and Qualifications
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified. The document only mentions that the device is intended for use by a "licensed practitioner, such as a radiologist or any physician maintaining the correct licensing criteria to read and interpret medical images." It does not clarify if such experts were involved in establishing ground truth for testing.
4. Adjudication Method for the Test Set
- Adjudication Method: Not specified.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study: The document does not mention that an MRMC comparative effectiveness study was done.
- Effect Size of Human Readers with AI vs. without AI: Not applicable, as no MRMC study with AI assistance is described.
6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop)
- Standalone Performance: Based on the description, the RadAlly™ is a software Medical Image Management and Processing System (MIMPS) for transferring, displaying, archiving, and reviewing medical images. It offers viewing tools and manual measurement tools. The "performance data" describes validation of the measurements and overall software functionality. This suggests that the studies focused on the accuracy of the integrated tools and overall system functionality, rather than a standalone AI algorithm generating interpretations without human interaction. The text implies a human-in-the-loop scenario where a licensed practitioner uses the software as a tool for diagnostic use.
7. Type of Ground Truth Used
- Type of Ground Truth: The document states that "measurements provided by the device were validated using bench testing against images with known measurements." This implies that for measurement-related validation, a predefined, accepted "true" measurement was available for comparison. For other functional aspects (e.g., viewing, archiving), the ground truth would inherently be defined by the expected behavior of such a system. The comparison with a predicate device also serves as a form of "ground truth" for demonstrating equivalence.
8. Sample Size for the Training Set
- Sample Size for Training Set: Not applicable. RadAlly™ is described as a MIMPS with viewing and manual measurement tools. There is no indication that it contains a machine learning or AI algorithm that requires a "training set" in the conventional sense (i.e., for learning to perform a task like image classification or detection). The device description focuses on its functionality as a software system, not an AI diagnostic tool.
9. How the Ground Truth for the Training Set Was Established
- How Ground Truth for Training Set Was Established: Not applicable, as there is no mention of a training set for an AI algorithm.
§ 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).