Search Results

The system is intended for use by Nuclear Medicine (NM) or Radiology practitioners and referring physicians for display, processing, archiving, printing, reporting and networking of NMI data, including planar scans (Static, Whole Body, Dynamic, Multi-Gated) and tomographic scans (SPECT, Gated SPECT, dedicated PET or Camera-Based-PET) acquired by gamma cameras or PET scanners. The system can run on dedicated workstation or in a server-client configuration. The NM or PET data can be coupled with registered and/or fused CT or MR scans, and with physiological signals in order to depict, localize, and/or quantify the distribution of radionuclical structures in scanned body tissue for clinical diagnostic purposes.

The DaTQUANT optional application enables visual evaluation of 1231-ioflupane (DaTscanTM) images. DaTQUANT Normal Database option enables quantification relative to normal population databases of 1231ioflupane (DaTscanTM) images. These applications may assist in detection of loss of functional dopaminergic neuron terminals in the striatum, which is correlated with Parkinson disease.

The O.Lung application may aid physicians in:

· Diagnosis of Pulmonary Embolism (PE), Chronic Obstructive Pulmonary Disease (COPD), Emphysema and other lung deficiencies.

• Assess the fraction of total lung function provided by a lobe or whole lung for Lung cancer resection requiring removal of an entire lobe, bilobectomy, or pneumonectomy.

The Q.Brain application allows the user to visualize and quantify relative changes in the brain's metabolic function or blood flow activity between a subject's images and controls, which may be resulting from brain functions in: · Epileptic seizures

· Dementia. Such as Alzheimer's disease, Lewy body dementia, Parkinson's disease with dementia, and frontotemporal dementia.

• · Inflammation
• · Brain death
• · Cerebrovascular disease such as Acute stroke, Chronic and acute ischemia

· Traumatic Brain Injury (TBI)

When integrated with the patient's clinical and diagnostic information may aid the physician in the interpretation of cognitive complaints, neuro-degenerative disease processes and brain injuries.

The Alcyone CFR application allows for the quantification of coronary vascular function by deriving Myocardial Blood Flow (MBF) and then calculating Coronary Flow Reserve (CFR) indices on data acquired on PET scanners and on stationary SPECT scanners with the capacity for dynamic SPECT imaging. These indices may add information to physicians using Myocardial Perfusion Imaging for the diagnosis of Coronary Artery Disease (CAD).

The Exini Bone application is intended to be used with NM bone scans for the evaluation of adult male patients with bone metastases from prostate cancer. Exini Bone quantifies the selected lesions and provides a Bone Scan Index value as adjunct information related to the progression of disease.

The Q.Liver application provides processing, quantification, and multidimensional review of Liver SPECT/PET and CT images for display, segmentation, and a calculation of the SPECT 'liver to lung' shunt value and the patient's Body Surface Area (BSA) for use in calculating a therapeutic dose for Selective Internal Radiation Therapy (SIRT) treatment using a user defined formula.

The Xeleris V Processing and Review Workstation is a Nuclear Medicine Software system that is designed for general nuclear medicine processing and review procedures for detection of radioisotope tracer uptake in the patient's body, using a variety of individual processing applications orientated to specific clinical applications.

Xeleris V is a modification to the predicate device, Xeleris 4.0 Processing and Review Workstation. It includes all the clinical applications and features in the current production version Xeleris 4.0 and introduces new clinical applications and enhancements to previously cleared clinical applications.

With Xeleris V, the customer now has an option where they can purchase the Xeleris V software, and have it installed on a remote server.

New Clinical Applications

Exini Bone: The Exini Bone application is intended to be used with NM bone scans for the evaluation of adult male patients with bone metastases from prostate cancer. The application automatically segments bone lesions based on 2D whole-body planar bone scans and requires the user adjust and/or accept the final segmentation before proceeding. Exini Bone quantifies the selected lesions and provides a Bone Scan Index value as adjunct information related to the progression of disease.

Q.Liver: The Q.Liver application is a comprehensive application that provides processing, quantification, and multidimensional review of liver SPECT/CT exams for display and segmentation. The application provides the user with tools to calculate a therapeutic dose for Selective Internal Radiation Therapy (SIRT) treatment.

Enhancements to Clinical Applications

Q.Lung: The Q.Lung application provides processing, quantification, and multidimensional review for pulmonary scintigraphy for display and quantification of global and regional ventilation and perfusion on SPECT and SPECT/CT studies. The change introduced in Xeleris V is the introduction of an optional lung fissure automatic detection using a Deep Learning based model.

Myovation: The Myovation application is used for the evaluation of patients with suspected or known coronary artery disease. Myovation reconstructs and reformats the SPECT raw data and helps to analyze the myocardial perfusion and function in rest, stress, and viability studies. The change for Xeleris V is the introduction of a new optional, non-Al Automatic Recognition of Cardiac Structures (ARCS) algorithm for improved heart detection and orientation.

Q.Volumetrix MI: The Q.Volumetrix MI application is a compressive tool for processing and reading non-cardiac volumetric data, including NM SPECT and hybrid SPECT-CT, PET-CT, external CT/MR (i.e. CT/MR from a separate nonhybrid scan). The enhancement for Xeleris V is a new, optional, DL-based automatic kidney segmentation algorithm.

Q.Brain: The Q.Brain application is used to process, quantify, and review brain studies obtained that include SPECT , SPECT/CT , PET/CT, and MR datasets. Q.Brain processing includes reconstruction, reorientation, rigid registration, and non-rigid registration of single or sequential tomographic brain data. The enhancement introduced with Xeleris V is that the display of the CT images registered to the template is now included along with other currently available image types.

The system is intended for use by Nuclear Medicine (NM) or Radiology practitioners and referring physicians. The intended use of the system is to provide digital processing, review and reporting of medical images, including data display, quality control, image manipulation and quantification analysis, transfer, storage and printing capabilities.

The system operates in a variety of configurations. The hardware components may include computer workstations, communications devices, video monitors, data storage and hardcopy devices.

Software components provide functions for performing operations related to image display, manipulation, enhancements, analysis and quantification and can operate on dedicated workstations and client-server architectures.

The provided document describes the Xeleris V Processing and Review System, which includes new deep learning (DL) based algorithms for lung fissure segmentation and kidney segmentation. While the document states that no clinical studies were required to support the determination of equivalence for the overall system, it does detail performance testing conducted specifically for these DL-based algorithms.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Stated Acceptance Criteria:

The document doesn't explicitly list quantitative acceptance criteria in the format of a table with thresholds (e.g., "Accuracy > 90%"). Instead, the acceptance criteria are implicitly defined by the rigor of the design control and performance testing, aiming to demonstrate substantial equivalence to a predicate device and ensure that the new features do not raise new safety or effectiveness questions.

The key overarching acceptance criteria are:

• Successful completion of all design control testing per GE Healthcare's quality system and compliance with relevant standards (NEMA PS3.1 - 3.20, IEC62304).
• No new safety questions or risks identified by testing.
• Algorithm performance demonstrated through testing with representative clinical exams.
• Acceptable scientific methods used to evaluate effectiveness.
• Substantial equivalence demonstrated to the predicate device, meaning the proposed device is as safe and effective for its intended use, with no new intended use introduced.

Table of Acceptance Criteria and Reported Device Performance (Implicit):

• As safe and effective as predicate.
• No new Intended Use. | - "The testing did not raise any new safety questions or identify any new risks."
• "Xeleris V is designed and will be manufactured under the Quality System Regulations of 21CFR 820 and ISO 13485."
• "GE believes Xeleris V is of comparable type and substantially equivalent to the predicate and reference devices, and hence is safe and effective for its intended use."
• "Xeleris V's Indications for Use do not create a new Intended Use." |
  | Design Control & QA | - Successful completion of all design control testing.
• Compliance with relevant standards (NEMA PS3.1 - 3.20, IEC62304). | - "Xeleris V and its clinical applications successfully completed all design control testing per GE Healthcare's quality system and also verified compliance with the relevant standards..."
• "The software was developed, verified, and validated under GE Healthcare's QMS including software development lifecycle." |
  | DL Algorithm Performance (Lung Fissure & Kidney) | - "Algorithm clinical performance testing using test datasets of representative clinical exams where the ground truth and evaluations were performed by clinicians."
• "The scientific methods used to evaluate the effectiveness of Xeleris V are acceptable and support the determination of substantial equivalence." | - Performance testing for DL-based algorithms was "successfully completed."
• "The test datasets were comprised of representative clinical exams that were manually segmented by experienced NM Physicists and Physicians and were used as ground truth."
• NM Physicists and Physicians reviewed segmentation results and "scored them using a 5-point Likert scale." (No specific quantitative results from Likert scale are provided in this summary, but the general statement implies positive outcomes.) |

Study Details (Performance Testing for DL-based Algorithms):

1. Sample sizes used for the test set and the data provenance:

   • Test Set Sample Size: The document refers to "test datasets of representative clinical exams" but "does not specify the exact number of cases or images" in these test sets for either the lung fissure or kidney segmentation algorithms.
   • Data Provenance: The document does not specify the country of origin of the data. It states the data comprised "representative clinical exams," implying real patient data. It does not explicitly state whether the data was retrospective or prospective, but "representative clinical exams" typically implies retrospective use of existing data for testing.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Number of Experts: The document states that the ground truth was "manually segmented by experienced NM Physicists and Physicians." It uses plural ("Physicists and Physicians") but does not specify the exact number of individuals.
   • Qualifications of Experts: They are described as "experienced NM Physicists and Physicians." No further details on their specific years of experience or board certifications are provided.

3. Adjudication method for the test set:

   • The document states that the test datasets were "manually segmented by experienced NM Physicists and Physicians and were used as ground truth." It also mentions that these experts "reviewed the segmentation results and scored them using a 5-point Likert scale."
   • This implies a consensus ground truth was established by these experts through manual segmentation. However, it does not explicitly describe a formal adjudication method (e.g., 2+1, 3+1, or how disagreements were resolved if multiple experts were involved in the initial ground truth creation) beyond stating they created the ground truth and then evaluated the algorithm's output.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and if so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No MRMC comparative effectiveness study was explicitly stated. The testing described is performance testing of the algorithm itself, with human experts creating ground truth and then evaluating the algorithm's output. The document explicitly states: "Xeleris V did not require clinical studies to support the determination of equivalence."
   • Therefore, no effect size on human reader improvement with AI assistance is provided.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Yes, performance testing of the DL algorithms appears to be a form of standalone evaluation. The algorithms generated segmentations, and these were then compared to the expert-generated ground truth and evaluated by experts. The text states: "...evaluates and demonstrates each algorithm's performance and uses test datasets of representative clinical exams." The output was then "reviewed the segmentation results and scored them." This indicates an algorithm-only performance evaluation against established ground truth.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The ground truth for the DL algorithm performance testing was expert consensus/manual segmentation. Specifically, it was "manually segmented by experienced NM Physicists and Physicians."

7. The sample size for the training set:

   • The document does not specify the sample size for the training set used for the deep learning models.

8. How the ground truth for the training set was established:

   • The document does not explicitly describe how the ground truth for the training set was established. It only details the ground truth for the test set. It is common practice for training data ground truth to be established similarly to test data ground truth (e.g., via expert annotation), but this is not stated in the provided text.

Ask a specific question about this device