Search Results

The HeartVista Workstation with the RTHawk application software is an accessory to 1.5T and 3.0T whole-body magnetic resonance diagnostic devices (MRDD or MR). The HeartVista Workstation with the RTHawk application software is intended to operate alongside, and in parallel with, the existing MR console to acquire real-ime and accelerated images. The Heart Vista Workstation with the RTHawk application software is indicated for Cardiovascular MR (CMR) applications.

The HeartVista Workstation with the RTHawk application software produces static and dynamic transverse, coronal, sagittal, and oblique cross-sectional images that display the internal structures and/or functions of the entire body. The images produced reflect the spatial distribution of nuclei exhibiting magnetic resonance. The magnetic resonance properties that determine image appearance are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2) and flow. When interpreted by a trained physician, these images provide information that may assist in the determination of a diagnosis.

The HeartVista Workstation with the RTHawk application software is intended for use as an accessory to the following OEM, MRI system, and software release versions:

· GE Healthcare (GEHC) Signa HDxt 1.5T, 3.0T. Software versions 15 and 16.

The HeartVista Workstation with the RTHawk application software is an accessory to 1.5T and 3.0T whole-body magnetic resonance systems. The HeartVista Workstation with the RTHawk application software is intended to operate alongside, and in parallel with, the existing MR console to acquire real-time and accelerated images. No hardware modifications are required to be made to the MR system or console to support full functionality of the HeartVista Workstation with the RTHawk application software.

The HearlVista Workstation with the RTHawk application software temporarily controls the existing MR system to acquire MRI raw data and related information accordina to pulse sequence programs within the Workstation, Image reconstruction, post-processing, and image display are performed on the Workstation, independent of the MR system or console. No existing GE scanner functionality is removed or modified, and GE scans may be interleaved with HeartVista scans during the same patient exam.

The HeartVista Workstation with the RTHawk application software and dedicated hardware product intended to provide a platform for efficient real-lime MRI data acquisition, data transfer, image reconstructive scan control, and display of static and dynamic MR imaaing data.

The HeartVista Workstation consists of a stand-alone linux-based computer workstation, color monitor, keyboard and mouse. A private ethernet network connects the HeartVisia Workslation to the MR scanner computer. When not in use, the HeartVista Workslation may be detached from the MR scanner with no detrimental, residual impact upon MR scanner function, operation, or throughput.

RTHawk is a linux operating system-level software application that is intended to control the MR scanner, acquiring high quality, real-time MRI image data and performing post-processing. The RTHawk software includes optimized image acquisition applications, a pipelined raw data image reconstruction engine, a rich graphical user interface for interactive scan control, real-time adjustment of pulse sequence parameters, and display of reconstructed images, and drivers and protocols for communications with, and control of, the OEM MR scanner console,

RTHawk applications ("Apps") support real-time interactive imaging, high-resolution imaging, and system tuning and shimming calibration modules. RTHawk apps are currently optimized for cardiovascular MR (CMR) imaging and measurements.

The provided document describes the HeartVista Workstation with RTHawk application software and its 510(k) submission (K133848) for FDA clearance. The performance data section focuses on non-clinical and a brief mention of clinical tests for the device itself, rather than a study proving the device meets a specific set of acceptance criteria for a diagnostic task.

The document highlights the device's technical performance and safety, comparing it to a predicate device (GE Signa Excite 1.5T and 3.0T MR Systems, K041476) to establish substantial equivalence.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present a formal table of "acceptance criteria" for a specific diagnostic task or a detailed "reported device performance" against those criteria in the way one might expect for an AI-powered diagnostic device. Instead, the acceptance is based on demonstrating substantial equivalence to a predicate MR system and compliance with recognized standards.

2. Sample Size Used for the Test Set and Data Provenance

The document states, "Clinical images were acquired using RTHawk, and were compared to images acquired on the same patient during the same imaging session using, where possible, equivalent pulse sequences and post-processing as necessary from the predicate device."

• Sample Size: Not specified. It only mentions "Clinical images" and "same patient," implying a paired comparison setup.
• Data Provenance: Not explicitly stated, but the submission is from HeartVista, Inc. in Menlo Park, CA, USA, so it's likely the clinical data originated from the US or was part of a study conducted with US institutions. The study appears to be prospective in the sense that images were acquired specifically for this comparison using both devices.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

• Number of Experts: Not specified.
• Qualifications of Experts: It states, "Images from both devices were evaluated and rated on the basis of diagnostic accuracy and image quality. Where no directly comparable images were available from the predicate device, RTHawk images were evaluated directly based upon radiologist expertise." This indicates that radiologists were involved, but their number and specific experience (e.g., years, subspecialty) are not detailed.

4. Adjudication Method for the Test Set

The document does not provide details on an adjudication method (e.g., 2+1, 3+1). It only states that images "were evaluated and rated" and that RTHawk images were evaluated based on "radiologist expertise" when direct comparison wasn't possible. This suggests individual or potentially consensus-based review, but no formal adjudication process is described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• No, a proper MRMC comparative effectiveness study was not explicitly described. The document mentions a comparison of "Clinical images" by "radiologist expertise" for diagnostic accuracy and image quality, but it does not detail a structured MRMC study setup with a focus on reader improvement with or without AI assistance. The study seems more focused on demonstrating technical image quality and diagnostic comparability rather than quantifying the impact of RTHawk on human reader performance.
• Effect Size of Human Reader Improvement with AI vs. Without AI Assistance: Not applicable, as an MRMC study comparing human reader performance with and without RTHawk assistance was not described.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The RTHawk software itself is an accessory that controls the MR scanner and processes images. The "clinical tests" described focused on the quality and diagnostic utility of the images produced by RTHawk when interpreted by radiologists. The product is an imaging system accessory, not an AI diagnostic algorithm meant to perform a diagnosis independently. Therefore, the concept of "standalone performance" for a diagnostic algorithm isn't directly applicable in the same way. The performance evaluated was of the image acquisition and processing system.

7. The Type of Ground Truth Used

The ground truth for the clinical comparison was effectively based on radiologist expertise interpreting the images. In cases where paired comparisons were made, the "ground truth" implicitly referred to the diagnostic information obtainable from the images from both the RTHawk and the predicate device, evaluated by radiologists. Where direct comparison wasn't available, RTHawk images were evaluated directly by radiologist expertise. There is no mention of pathology or long-term outcomes data being used as ground truth for this comparison.

8. The Sample Size for the Training Set

The document is for the RTHawk application software, which is described as an accessory to MR systems that performs real-time data acquisition, reconstruction, and display. It does not explicitly mention a "training set" in the context of machine learning, suggesting that RTHawk itself is not primarily an AI diagnostic algorithm "trained" on a dataset in the way modern AI devices are. Instead, the "training" (development) of the RTHawk applications ("Apps") involved optimization, presumably through engineering and testing, potentially using internal data or phantoms to refine pulse sequences and reconstruction.

If any machine learning models were implicitly part of its reconstruction or post-processing, details about their training sets are not provided.

9. How the Ground Truth for the Training Set Was Established

As noted above, a distinct "training set" with established ground truth for a machine learning model is not described. The RTHawk "Apps" are optimized for cardiovascular MR (CMR) imaging and measurements. This optimization process would typically involve engineering and signal processing expertise, likely leveraging known physics of MRI and potentially clinical experience in cardiovascular imaging, rather than a formal "ground truth" derived from a specific labelled dataset for training an AI model.

Ask a specific question about this device