Xeleris V Processing and Review Systems

The Xeleris V Processing and Review System is designed to provide comprehensive image processing and quantitative analysis capabilities for nuclear medicine practitioners, supporting a wide array of diagnostic applications through the integration of NMI, CT, and MR data. It leverages both established image processing techniques and new Deep Learning algorithms to enhance diagnostic accuracy and workflow efficiency in evaluating conditions such as Parkinson's disease, cancer, cardiovascular disease, and neurological disorders.

The Xeleris V Processing and Review System is an advanced nuclear medicine software designed for practitioners to display, process, archive, print, report, and network nuclear medicine imaging (NMI) data. It supports a wide range of data types, including planar scans (Static, Whole Body, Dynamic, Multi-Gated) and tomographic scans (SPECT, Gated SPECT, PET), acquired from gamma cameras or PET scanners. The system allows for the integration of NMI data with registered or fused CT or MR scans and physiological signals, enabling the depiction, localization, and quantification of radionuclide tracer distribution and anatomical structures for comprehensive clinical diagnostic purposes. Xeleris V can be deployed on dedicated workstations or in a server-client configuration, offering flexibility in its operational environment. As a modification of the Xeleris 4.0 workstation, Xeleris V incorporates all prior functionalities while introducing significant enhancements and new clinical applications. Key new applications include "Exini Bone" for evaluating bone metastases in prostate cancer by quantifying lesions and providing a Bone Scan Index, and "Q.Liver" for processing liver SPECT/PET and CT images to aid in Selective Internal Radiation Therapy (SIRT) dose calculation. Existing applications such as Q.Lung, Myovation, Q.Volumetrix MI, and Q.Brain have been enhanced; notably, Q.Lung now offers optional Deep Learning (DL)-based automatic lung fissure detection, and Q.Volumetrix MI includes an optional DL-based automatic kidney segmentation algorithm. These DL integrations, along with traditional algorithm improvements like the ARCS algorithm in Myovation, aim to improve workflow efficiency and diagnostic capabilities across various conditions including Parkinson's disease (DaTQUANT), pulmonary diseases (Q.Lung), neurological disorders (Q.Brain), and coronary artery disease (Alcyone CFR, Myovation).

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the performance of the new Deep Learning-based automatic segmentation algorithms (for lung fissures in Q.Lung and kidney segmentation in Q.Volumetrix MI) compare to traditional manual or semi-automated methods in terms of accuracy, consistency, and time-efficiency across diverse patient populations and image qualities?; What specific validation processes were used for the DaTQUANT Normal Database, particularly concerning its applicability to different demographic groups (age, sex, ethnicity) and its robustness against variations in imaging protocols or scanner types?; For the Q.Liver application, what is the validated accuracy of the 'liver to lung' shunt value calculation, and how does it account for potential confounding factors such as patient respiratory motion or partial volume effects in SPECT/PET imaging when determining SIRT dosage?; Could the Exini Bone application's Bone Scan Index be integrated with other prognostic markers for prostate cancer, and are there plans to expand its use to other types of cancer or bone conditions?; With the increasing complexity and number of specialized applications (Q.Lung, Q.Brain, Alcyone CFR, etc.), what is the learning curve for new users, and what training or support resources are provided to ensure optimal and consistent utilization of these advanced quantitative tools?