Search Results

To detect or image the distribution of radionuclides in the body or organ, using the following techniques:

• Multiplanar Reconstruction (MPR) .
• Maximum/Minimum Intensity Projection (MIP) .
• Image Contrast Manipulation .
• Image Zoom Manipulation .
• Automatic registration with Mutual Information Technique .

Clarity PET is PET intage review software. Clarity PET offers a comprehensive software solution for medical imaging tasks and applications. Clarity PET is a medical diagnostic workstation designed for display, review, 3D MPR, communication and archiving of medical images

This 510(k) submission (K032866) for the Clarity PET device does not contain a study demonstrating that the device meets specific acceptance criteria based on its performance. Instead, it focuses on demonstrating substantial equivalence to predicate devices already on the market.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

There is no table of acceptance criteria or reported device performance metrics in the provided document. The submission relies on establishing equivalency rather than meeting new performance benchmarks.

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

Not applicable. No new performance study (test set, data provenance) is conducted for this 510(k) submission.

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

Not applicable. No new performance study is conducted that involved establishing ground truth with experts.

4. Adjudication Method:

Not applicable. No new performance study requiring adjudication is conducted.

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

No, an MRMC comparative effectiveness study was not done. The submission does not present a study comparing human reader performance with and without AI assistance, as the device is image review software, not an AI-assisted diagnostic tool in the sense of providing automated interpretations.

6. Standalone (Algorithm Only) Performance Study:

No, a standalone performance study was not done. The Clarity PET is described as image review software and thus its "performance" is implicitly tied to its ability to display and manipulate images, similar to predicate devices. It's not an algorithm providing a diagnostic output independently.

7. Type of Ground Truth Used:

Not applicable. No ground truth for a new performance study is established or used in this submission.

8. Sample Size for the Training Set:

Not applicable. The provided document does not describe a training set for an algorithm, as the device is image review software, not a machine learning model.

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

Not applicable.

Summary of the K032866 Submission's Approach:

The K032866 submission for Clarity PET establishes substantial equivalence by demonstrating:

• Equivalent Indications for Use: The device can "detect or image the distribution of radionuclides in the body or organ, using the following techniques: Multiplanar Reconstruction (MPR), Maximum/Minimum Intensity Projection (MIP), Image Contrast Manipulation, Image Zoom Manipulation, Automatic registration with Mutual Information Technique." These are explicitly stated as equivalent to the Medical Image Merge™ device.
• Equivalent Technological Characteristics, Performance Characteristics, and Instructions for Use: The submission asserts that Clarity PET shares these equivalencies with the Medical Image Merge™ device and other predicate devices like Syngo Multi-Modality Workstation, ADAC Laboratories Image Fusion and Review System, and GE Advantage Windows Workstation.

The core of this 510(k) is a comparison to legally marketed predicate devices, asserting that Clarity PET performs the "same functions" and has "equivalent" characteristics, rather than providing new performance data against a specific set of acceptance criteria. The FDA's letter confirms that they reviewed the 510(k) and determined the device is substantially equivalent to legally marketed predicate devices for the stated indications for use.

Ask a specific question about this device

This software is designed to be used in combination with the Toshiba GMS-5500A/UI Nuclear Medicine Medical Image Processor. The software matches the position and size of two tomographic images acquired for the brain of the same patient and superimposes them for display. Nuclear medicine, CT, and MRI images can be processed using this software. This software can be used to perform registration between images of two different modalities and superimpose them. This device employs no intended uses that are not in cleared devices already found in the marketplace.

To detect or image the distribution of radionuclides in the body or organ, using the following technique(s).
Tomographic Imaging (SPECT) for non Positron Emitter

The Automatic Image Registration Software, Model NSFU-050A is a software option for the Toshiba GMS-5500A/UI Nuclear Medical Image Processor. The software matches the position and size of two tomographic images acquired for the same patient and superimposes them for display.

The provided 510(k) summary for the Toshiba Automatic Image Registration Software, Model NSFU-050A, does not contain detailed information about acceptance criteria, specific device performance metrics, or study methodologies that would allow for a comprehensive breakdown as requested. This document is a premarket notification for substantial equivalence, which primarily focuses on comparing the new device to legally marketed predicate devices based on intended use and technological characteristics rather than providing in-depth performance study results.

However, based on the absence of such information in this specific 510(k), we can infer several points relevant to your questions.

Here's an analysis of what can be extracted and what information is missing:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not specified. The 510(k) summary does not mention any specific test set or the number of cases/patients used to evaluate the device's performance.
• Data Provenance: Not specified. There is no information regarding the country of origin of data or whether any testing was retrospective or prospective.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The summary does not provide any details about experts or how ground truth was established for any performance testing.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified. Since no test set or ground truth establishment is described, no adjudication method is mentioned.

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

• MRMC Study: Not reported. The 510(k) summary does not mention any MRMC study or any comparison of human reader performance with or without AI assistance. This type of study would typically involve a human-in-the-loop component, which is not a focus of the provided summary for this image registration software.

6. Standalone (Algorithm Only) Performance Study

• Standalone Study: Not explicitly described as a formal study. While the device itself is a standalone software component, the 510(k) summary does not present specific performance metrics from a standalone study. It focuses on the device's function (matching and superimposing images) and its substantial equivalence to predicate devices, implying its ability to perform this function, but without quantitative evidence for this specific submission.

7. Type of Ground Truth Used

• Type of Ground Truth: Not specified. There is no indication of whether expert consensus, pathology, outcomes data, or any other method was used to establish ground truth for testing.

8. Sample Size for the Training Set

• Sample Size: Not specified. The 510(k) summary does not provide any information about a training set, suggesting that the submission does not rely on a machine learning model that requires a dedicated training set in the modern sense. Given the 1999 date, this is consistent with software development practices of that era, where rule-based or algorithmic approaches were more common and typically didn't involve "training sets" in the current AI/ML context.

9. How Ground Truth for the Training Set Was Established

• Ground Truth Establishment: Not applicable/Not specified. Since no training set is mentioned (see point 8), there's no information on how its ground truth would have been established.

Summary of what the 510(k) does communicate regarding evidence for meeting intended use:

The 510(k) for the Toshiba Automatic Image Registration Software, Model NSFU-050A, primarily relies on substantial equivalence to predicate devices. It asserts that:

• The device's intended uses are not new and are found in already cleared devices (predicate devices: Toshiba GMS-5500A/UI Nuclear Medicine Image Processor and ADAC Image Fusion and Review System).
• The technological characteristics are "the same as that of the predicate devices."
• "Multimodality image fusion is well understood and is documented in peer-reviewed scientific publications."

This suggests that rather than providing a detailed performance study with specific acceptance criteria and outcome metrics for this new product, the submission argues that the underlying technology and its application are already proven and legally marketed through the predicate devices. The FDA's clearance (DEC - 3 1999) indicates acceptance of this argument for substantial equivalence.

Ask a specific question about this device