Search Results

Volume Interactions Pte Ltd's Image Processing System is a medical device for the display and visualization of 3D medical image data derived from tomographic radiology images, excluding mammography images. It is intended to be used by qualified and trained medical professionals, after proper installation.

Volume Interactions Image Processing System reads DICOM 3.0 format medical image data sets (and other formats) and displays 3D image reconstructions of these data sets through various user selectable industry standard rendering methods and algorithms. The clinical users can spatially manipulate, process to highlight structures and volumes of interest, and measure distances and volumes in the 3D image reconstructions. The processed data can be stored either as 3D image data in a proprietary format, or as 2D picture projections of the 3D image data in TIFF image format. The system runs on commercially available PC compatible computers and hardware components with the Microsoft Windows NT and 2000 operating systems.

The system consists of three product modules namely, RadioDexter™, Dextroscope™ and Dextrobeam™. The modules are described as follows:

RadioDexter™ is software that processes tomographic (e.g.: Computer Tomography, Magnetic Resonance Imaging) data and produces stereoscopic 3D renderings for surgery planning and visualization purposes. The software uses various user selectable industry standard rendering methods and algorithms.

DTI (Diffusion Tensor Imaging) is an add-on module to RadioDexter™. This module allows the user to visualize white matter anatomy in the form of fiber tracks. The intended use of this module is to generate and provide a visual reference of white matter fiber tracks in a 3D virtual reality environment during the process of neurosurgery planning using the Dextroscope™ or during a discussion/collaboration using the Dextrobeam™. It is not intended to be used otherwise.

Dextroscope™ is an interactive console and display system that allows the user to interact with two hands with the 3D images generated by the RadioDexter™ software. The Dextroscope™ user works seated, with both forearms positioned on armrests. Wearing stereoscopic glasses, the user looks into a mirror and perceives the virtual image within comfortable reach of both hands for precise hand-eye coordinated manipulation. The hardware uses various industry standard components.

Dextrobeam™ is an interactive console intended for group collaborative discussions with 3D images using a stereoscopic projection system. The Dextrobeam™ system uses the base of the Dextroscope™ as the 3D interaction interface with the virtual objects. The monitor of the Dextroscope™ is replaced by a screen projection system, so instead of looking into the mirror of the Dextroscope™, the user looks at large stereoscopic screen projections while working with the virtual data in reach of his hands. This enables the discussion of 3D data sets with other specialists in stereoscopic 3D. The hardware uses various industry standard components.

The provided submission describes an "Image Processing System" (RadioDexter™, Dextroscope™, and Dextrobeam™) by Volume Interactions Pte Ltd. This device is for the display and visualization of 3D medical image data from tomographic radiology images. The submission pertains to a 510(k) premarket notification, which focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than on presenting results from specific clinical trials or studies designed to meet detailed acceptance criteria.

Therefore, the document does not contain information typically found in a study demonstrating how a device meets acceptance criteria, such as:

• A table of acceptance criteria and reported device performance.
• Sample sizes for test sets, data provenance, number/qualifications of experts, or adjudication methods for test sets.
• Multi-reader multi-case (MRMC) comparative effectiveness study results.
• Standalone (algorithm-only) performance results.
• Details on the type of ground truth used or the sample size and establishment of ground truth for a training set in a way that would be typical for an AI/ML medical device submission proving performance against acceptance criteria.

The submission is for a device categorized as an "Image Processing System" and "Picture Archiving and Communications System (PACS)." The focus here is on ensuring the device's functionality and safety and technological equivalence to a predicate device, as opposed to demonstrating specific diagnostic performance metrics (e.g., sensitivity, specificity, AUC) that are common for AI/ML-driven diagnostic aids.

Based on the provided text, the following can be extracted and inferred:

1. Acceptance Criteria and Reported Device Performance:

   • The submission does not explicitly define acceptance criteria as performance metrics (e.g., sensitivity, specificity, accuracy) would be for an AI/ML diagnostic device.
   • The "acceptance criteria" in this context are implicitly understood as demonstrating substantial equivalence to the predicate device (K063730).
   • The device's reported "performance" is that it "reads DICOM 3.0 format medical image data sets (and other formats) and displays 3D image reconstructions of these data sets through various user selectable industry standard rendering methods and algorithms." It also allows users to "spatially manipulate, process to highlight structures and volumes of interest, and measure distances and volumes."
   • The DTI add-on module's performance is to "visualize white matter anatomy in the form of fiber tracks" and "generate and provide a visual reference of white matter fiber tracks."

   Table of Acceptance Criteria and Reported Device Performance (Inferred from Substantial Equivalence):

   Acceptance Criterion (Inferred from Substantial Equivalence)	Reported Device Performance
   Use same operating principle as predicate device.	Device reads and displays 3D medical image data.
   Have same technological characteristics as predicate device.	Device uses various user-selectable industry standard rendering methods and algorithms; runs on commercially available PC compatible computers with Microsoft Windows NT and 2000.
   Incorporate similar basic software and hardware design.	System comprises RadioDexter™, Dextroscope™, and Dextrobeam™. Hardware uses industry standard components.
   Have same fundamental scientific technology.	(Identical to predicate)
   DTI module safety and effectiveness.	DTI module "has been verified and validated according to Volume Interactions' procedures for product design and development. The validation proves the safety and effectiveness of the module." (No specific performance metrics are given for "safety and effectiveness" in the document).

2. Sample size used for the test set and the data provenance:

   • The document does not detail specific "test sets" or their sample sizes as would be typical for performance evaluation of a new algorithm. The validation mentioned for the DTI module likely involved internal testing procedures rather than a large clinical test set.
   • Data provenance (country of origin, retrospective/prospective) is not mentioned. The device reads DICOM 3.0 format medical image data, implying it processes medical images from various sources, but the origin of data used for any internal verification/validation is not specified.

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

   • This information is not provided. The nature of the device (image processing and visualization) means "ground truth" might refer to the accuracy of 3D reconstructions or measurements, rather than diagnostic labels.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • This information is not provided.

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

   • This type of study was not mentioned. The device is an image processing and visualization system, not an AI-driven diagnostic aid that would typically undergo such a comparative effectiveness study to measure reader improvement. The DTI module "provides a visual reference" for planning, implying it's a tool for visualization, not a standalone diagnostic interpretation by AI.

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

   • The document implies that the DTI module provides "visual reference" for human professionals ("intended to be used by qualified and trained medical professionals"). It describes functionality ("generate and provide a visual reference") rather than a standalone diagnostic performance metric. Thus, no standalone performance evaluation in the typical sense of a diagnostic algorithm is mentioned.

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

   • This information is not provided in detail. For an image processing system, ground truth might relate to the accuracy of the 3D reconstructions against the original slice data, or the accuracy of measurements compared to known physical dimensions, or the anatomical correctness of fiber tracks as verified by neuroanatomists. The document only states the DTI validation "proves the safety and effectiveness of the module."

8. The sample size for the training set:

   • This information is not provided. The document predates the widespread regulatory focus on AI/ML training data sets. The DTI module would likely have been developed and "trained" or optimized with a set of DTI images, but no details are given.

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

   • This information is not provided.

Ask a specific question about this device