Search Results

The Scenium display and analysis software has been developed to aid the Clinician in the assessment and quantification of pathologies taken from PET and SPECT scans.

The software is deployed via medical imaging workplaces and is organized as a series of workflows which are specific to use with particular drug and disease combinations.

The software aids in the assessment of human brain scans enabling automated analysis through quantification of mean pixel values located within standard regions of interest. It facilitates comparison with existing scans derived from FDG-PET, amyloid-PET, and SPECT studies, calculation of uptake ratios between regions of interest, and subtraction between two functional scans.

Scenium VD10 display and analysis software enables visualization and appropriate rendering of multimodality data, providing a number of features which enable the user to process acquired image data.

Scenium VD10 consists of three workflows:

• Database Comparison
• Ratio Analysis
• Subtraction

These workflows are used to assist the clinician with the visual evaluation, assessment and quantification of pathologies with different imaging agents, such as using Amyloid imaging agents for dementia and Alzheimer's Disease, DaTSCAN(1-123) for Parkinson's Disease and FDG-PET for epileptic seizures.

The modifications made to the Scenium VD10 software (K133654) to create the Scenium VD20 software include:

• Customized databases can now be imported and exported in the Database Comparison workflow.
• Three new FDG databases normalized to the region of the cerebellum, in addition to whole brain, were added to the Database Comparison workflow.
• Deformable Registration for Amyloid PET has been integrated in the Ratio Analysis workflow with a different algorithm.
• Launch performance decreased the time taken to display patient data in the Ratio Analysis workflow.

This change is based on current commercially available software features and does not change the technological characteristics of the device.

Scenium VD20 Analysis software is intended to be run on commercially available software platforms such as the Siemens syngo.MI Workflow software platform (K133644) or commercially available Siemens scanners (e.g. symbia Intevo (K142006), Biograph mCT (K123737).

This document is a 510(k) premarket notification for the Scenium VD20 software. It claims substantial equivalence to the previously cleared Scenium VD10 software (K133654). The provided text does not include a detailed study proving the device meets specific acceptance criteria with reported performance metrics, expert qualifications, or detailed study methodologies. Instead, it focuses on demonstrating that the modifications introduced in Scenium VD20 do not alter the fundamental technological characteristics or indications for use compared to the predicate device, and thus do not raise new safety and effectiveness concerns.

Therefore, many of the requested details about acceptance criteria and a specific study are not present in this regulatory document.

However, based on the information provided, we can infer some aspects and highlight what is missing:

1. Table of Acceptance Criteria and Reported Device Performance:

The document states: "All testing has met the predetermined acceptance values." This is a general statement and does not provide specific quantitative acceptance criteria or reported performance values.

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

• Sample Size for Test Set: Not specified. The document mentions "Verification and Validation activities" and "All testing," but does not detail the size of the dataset used for these tests.
• Data Provenance: Not specified. There is no mention of the country of origin of the data or whether it was retrospective or prospective.

3. Number of Experts Used to Establish Ground Truth and Their Qualifications:

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The document focuses on software changes and their implications, not on clinical validation involving human readers or expert consensus on a test set.

4. Adjudication Method:

• Not specified. Since details about expert review or test sets are missing, an adjudication method is also not mentioned.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

• No, an MRMC comparative effectiveness study is not mentioned or described. The documentation focuses on demonstrating substantial equivalence based on technical modifications and internal verification/validation, not on comparing human reader performance with and without AI assistance for the new features.

6. Standalone (Algorithm Only) Performance Study:

• No specific standalone performance study with detailed metrics (e.g., sensitivity, specificity, accuracy) is presented in this document. The verification and validation activities likely included internal testing of the algorithms, but explicit results demonstrating standalone performance are absent. The device itself is described as "display and analysis software" intended to "aid the Clinician," implying it is a tool for human-in-the-loop use rather than a fully autonomous diagnostic algorithm.

7. Type of Ground Truth Used:

• Not specified. Given the focus on software modifications and features, the "ground truth" for the verification and validation tests would likely relate to the expected outputs of the algorithms, internal consistency, and comparison with previous versions, rather than a clinical ground truth like pathology or long-term outcomes data.

8. Sample Size for the Training Set:

• Not applicable / Not specified. This device is described as "display and analysis software" and the modifications are primarily related to database functionalities, workflow integration, and an algorithmic change for deformable registration. There is no indication that this update involved a machine learning model that required a specific "training set" in the conventional sense of deep learning or AI model development. The "new FDG databases" are likely pre-computed reference datasets, not training data for a learning algorithm within Scenium VD20 itself.

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

• Not applicable / Not specified. As there's no mention of a traditional training set for a new machine learning algorithm, there's no information on how a ground truth for such a set would have been established.

Summary of what the document focuses on instead:

The document primarily provides evidence for substantial equivalence to a predicate device (Scenium VD10, K133654) by stating that:

• The modifications (customized database import/export, new FDG databases, deformable registration algorithm change, improved launch performance) do not change the technological characteristics of the device.
• There are no differences in the Indications for Use.
• No new issues of safety and effectiveness are raised by the modifications.
• Risk Management (ISO 14971:2012) and adherence to industry standards (ISO 13485, IEC 62304) were followed.
• Verification and Validation activities were successfully performed, and "All testing has met the predetermined acceptance values." This last point is the closest to an "acceptance criterion" statement, though it lacks specificity.

Ask a specific question about this device

The Siemens MR-PET system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information, acquired simultaneously and isocentrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and / or PET imaging.

These systems are intended to be utilized by appropriately trained health care professionals to aid in the detection, localization, and diagnosis of diseases and disorders.

The MR is intended to produce transverse, sagittal, coronal and oblique crosssectional MR images, spectroscopic images and/or spectra, and displays the internal structure and/or function of the human body. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, approved contrast agents may be used, as described in their labeling. This system may also be used for imaging during interventional procedures when performed with MR compatible devices, such as MR-safe biopsy needles.

The PET images and measures the distribution of PET radiopharmaceuticals in humans to aid the physician in determining various metabolic (molecular) and physiologic functions within the human body for evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer.

The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The Biograph mMR systems are combined Maqnetic Resonance Imaging and Positron Emission Tomography scanners. The Biograph mMR systems provide registration and fusion of high-resolution metabolic, physiologic and anatomic information from the two major components of each system (PET and MR) acquired simultaneously and isocentrically.

The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely alianed MR and PET image coordinate systems.

Software syngo MR B20P is a new software version for the Siemens Biograph mMR systems that were previously cleared under K103429 (running software version syngo MR B18P).

New scanners will be manufactured with syngo MR B20P; existing scanners can be upgraded to this software version. The new software version includes new software features, coil modifications and other modified hardware for the Biograph mMR systems.

This 510(k) submission (K133226) from Siemens for "Software syngo MR B20P for Biograph mMR" is a special 510(k), indicating modifications to an already cleared device. As such, the focus of the submission is on demonstrating that the new software and hardware features do not introduce new issues of safety or effectiveness and that the device remains substantially equivalent to its predicate.

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly provide a table of quantitative acceptance criteria with corresponding performance metrics for the software changes in the way one might expect for a novel AI algorithm. Instead, the acceptance criteria are implicitly defined by standard engineering and regulatory practices for medical device modifications. The reported device performance is demonstrated through various tests designed to ensure the modified coils and software functions as intended and meet established standards.

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

The document does not specify a distinct "test set" in the context of AI performance evaluation. The non-clinical tests involved:

• Testing of coils (SNR, image uniformity, heating, hybrid mode).
• Phantom testing for MNO Spectroscopy.
• Verification and validation of all software features.
• PET performance testing in accordance with NEMA NU:2.

The data provenance for these tests is implicitly from Siemens' internal testing environment and phantoms, as no patient data (retrospective or prospective) is mentioned as being used for the testing of the modified features to demonstrate conformance.

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

Not applicable. This submission does not describe a study involving expert-established ground truth on a test set (e.g., for diagnostic accuracy). The evaluation focuses on engineering performance and regulatory compliance for modified features.

4. Adjudication Method for the Test Set

Not applicable, as no expert adjudication of images or data to establish ground truth is described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of Human Readers Improve with AI vs. Without AI Assistance

No, an MRMC comparative effectiveness study was not done. The submission explicitly states: "There were not any clinical tests conducted to support the subject device and the substantial equivalence argument..." This is a software and hardware update, not a new diagnostic AI algorithm requiring such a study.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

This is not applicable in the typical sense for a diagnostic AI algorithm. The software features are enhancements to an existing imaging system, not a standalone diagnostic algorithm. The "standalone" performance here relates to the technical functionality of the new features (e.g., whether the new sequences produce images correctly, whether MNO spectroscopy works on phantoms). These functional tests were performed in a standalone manner (without a human interpreting findings for diagnostic purposes).

7. The Type of Ground Truth Used

The ground truth for the non-clinical tests was based on:

• Physical measurements and engineering specifications: For coil performance (SNR, uniformity, heating, hybrid mode).
• Phantom studies: For MNO Spectroscopy, where the phantom's known characteristics serve as the ground truth.
• NEMA NU:2 standards: For PET performance, adherence to these published standards serves as the ground truth for system performance.
• Software engineering requirements and specifications: For the verification and validation of all software features, ensuring they meet their design intent.

8. The Sample Size for the Training Set

Not applicable. This submission is for modifications to an existing MR-PET system software and hardware. The new software features described (e.g., reconstruction improvements, new sequences, usability improvements) are not typically "trained" in the machine learning sense from a large dataset but rather developed through traditional software engineering and signal processing methods.

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

Not applicable, as there is no mention of a "training set" in the context of machine learning for this device modification.

Ask a specific question about this device