uPMR 790
Shanghai United Imaging Healthcare Co., Ltd. • Radiology • 05/24/2024
Device Purpose
The uPMR 790 is a hybrid imaging system designed for simultaneous acquisition of high-resolution anatomical (MR) and metabolic/physiological (PET) data. It integrates PET detectors within a 3.0T MR bore, utilizing advanced MR pulse sequences, RF coils, and AI-driven image reconstruction (DeepRecon, ACS) and processing techniques to provide fused, iso-centrically acquired images with MR-based attenuation correction for PET.
Summary
The uPMR 790 is an advanced medical imaging system that combines Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) capabilities. Its primary purpose is to provide simultaneous, iso-centrically acquired, high-resolution physiological and anatomical information. The system allows for independent MR or PET imaging, or combined operation where PET detectors integrated within the MR bore capture metabolic data while the 3.0T MR component acquires detailed anatomical images of the head, body, and extremities. A key feature is the use of MR data for radiation-free attenuation correction maps for PET studies, with precisely aligned coordinate systems ensuring inherent anatomical reference for the fused images. The system supports Time of Flight (ToF) for PET and utilizes comprehensive software for patient and data management, scan control, image reconstruction, and archiving, adhering to NEMA and DICOM standards. This iteration of the uPMR 790 introduces significant modifications, including new RF coils (SuperFlex Body-24, SuperFlex Large-12, SuperFlex Small-12) and a host of new and updated MR pulse sequences and options. It incorporates advanced MR imaging processing methods such as 2D/4D Flow, CEST, T1rho, and DeepRecon (a deep-learning algorithm for de-noising and super-resolution), alongside new PET processing methods like Hyper DPR and Digital Gating. A notable addition is AI-assisted Compressed Sensing (ACS) for MR image reconstruction, which, like DeepRecon, demonstrated improved SNR and resolution while maintaining image quality in non-clinical testing. Further enhancements include new workflow features (EasyCrop, MoCap-Monitoring, QGuard-Imaging), expanded spectroscopy capabilities (Liver, Breast), and an MR conditional implant mode, all aimed at improving diagnostic utility and operational efficiency.
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.
Keywords
Device Metadata
Relevant Clinical Questions
- Q1. How does the integration of PET detectors within the MR bore specifically impact image quality or potential for artifacts compared to sequential PET and MR scanning?; What are the quantitative improvements in diagnostic accuracy or patient throughput observed with the new AI-assisted Compressed Sensing (ACS) and DeepRecon algorithms compared to previous reconstruction methods?; Could you elaborate on the clinical scenarios where the new pulse sequences (e.g., gre_fine, fse_arms_dwi) and processing methods (e.g., CEST, T1rho) offer the most significant diagnostic advantages?; How does the 'MR conditional implant mode' adjust scanning parameters to ensure patient safety, and what types of implants are covered under this mode?; What is the specific mechanism and performance benefit of 'radiation-free attenuation correction maps for PET studies' generated by the MR component, particularly in complex anatomical regions?
Risk Classification
ESL AnalysisFDA Class II via 510(k) pathway; IEC 62304 Class B (software safety classification); Post-§524B but no clear network capability detected
Learn how Parasoft automates IEC 62304 compliance testing →Cybersecurity Evidence
Powered by SBOMator™Based on AI-generated device summaries, not the full FDA submission. Items not detected here may still be present in the complete submission package.
Supply Chain BOM Evidence
Based on the CycloneDX / OWASP ECMA-424 xBOM ecosystem. Detection is from the AI-generated summary.
Analysis:
• Analysis is based on the AI-generated device summary, not the full FDA submission package. Click "Analyze Full FDA PDF" below to scan the actual submission document.
• Evidence of ML-BOM, OBOM detected in AI-generated device summary.
• SBOM not mentioned in AI-generated device summary. Under §524B (effective Oct 2023), cyber devices must provide a SBOM.
• Cybersecurity risk assessment not referenced in AI-generated device summary. FDA cybersecurity guidance (2023) expects this for cyber devices.
• Not detected in AI-generated device summary: SBOM, SaaSBOM, HBOM, CBOM, VDR/VEX. These may be present in the full FDA submission.
Preparing a similar submission?
ESL takes complete ownership of your software evidence work - SBOM & CVE remediation with SBOMator™, static analysis & unit testing with Parasoft, traceability, and full IEC 62304 lifecycle support.
Assess Your Readiness →Or contact ESL directly