(15 days)
The Viatronix V3D Explorer is intended to be used for the display and 2D/3D visualization of medical image data derived from CT, MRI, PET and SPECT scans of the human body including any organ. The volume , linear and angular measurement functions are intended for the evaluation and quantification of turnor or selected organ volume/linear measurements, angular location/ displacement, study/ analysis and evaluation of both hard and soft tissues as well as other internal organ structures for polyp, lesion, mass, implants, fracture, aneurysms, stenoses etc or evaluation of any abnormality / malformation in specified organs obtained from scanning. It also supports the interactive segmentation of any organ by removing certain structure(s) from display for critical evaluation of selected part(s) of organ. It is intended for use by radiologists, clinicians and referring physicians to acquire, process, render, evaluate, archive, print and distribute DICOM 3.0 compliant specified organ image studies, utilizing PC hardware.
The V-3D Explorer is a software device for evaluating scanned images of selected human organ. It is an additional image processing option added to our V-3D visualization system for which pre-market clearance was granted by the FDA vide K#002780, dated November 17, 2000. It is a general software module, designed for use as a part of our V-3D visualization system core technology. The system consists of a V-3D processor and a V-3D viewer in two computer configuration or V-3D processor and V3D viewer in a stand alone one computer configuration. Upon receipt of a multi-slice CT or MR scan image for any selected organ in a DICOM format, the V-3D processor converts the DICOM image data into an internally recognized volume data format using our core software. technology. The V-3D viewer provides interactive orthogonal and multiplanar reformatted 2D and 3D images from the V-3D processor and user can evaluate these images for any abnormality or malformation in specified organs obtained from scanned images. The volume, linear and angular measurement features provided in the software for the evaluation and quantification of organ volume, linear measurements, angular location/displacement for hard and soft tissues as well as internal organ structures for polyp, lesion, mass, tumor, implants, fracture, aneurysms, stenoses etc. The software also supports interactive segmentation of any organ from removing certain structure from display for critical evaluation of selected part of organ. The intended user can use the software device to acquire, process, render, evaluate, archive, print and distribute DICOM 3.0 compliant images of any organ, utilizing PC hardware.
Here's an analysis of the provided text regarding the acceptance criteria and study for the Viatronix V3D Explorer:
Summary of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Functional Equivalence | The V3D Explorer software module provided interactive orthogonal and multiplanar reformatted 2D and 3D images from datasets to detect and evaluate known abnormalities or status of organs. The volume, linear, and angular measurement features were used to evaluate and quantify abnormalities or status of internal organ structures. |
| Accuracy (Phantom Datasets) | Testing on phantom datasets determined its level of accuracy, which correlates perfectly with pre-calculated values. |
| Reliability & Ease of Use | The product has shown itself to be reliable and easy to use. |
| DICOM 3.0 Compliance | Capable of evaluating DICOM 3.0 compliant scanned images of any human organs. |
| Clinical Equivalence (Patient Data) | Evaluation results of both the predicate device and the V3D Explorer device were the same, and no significant differences were detected in the results of evaluation when using scanned images of various patient organs with known abnormalities or status. It was established that the V3D Explorer application is substantially equivalent to the predicate devices in its ability to review, analyze, and evaluate CT/MR scan images to facilitate analysis and evaluation of abnormality or malformation. |
| Safety & Effectiveness | Concluded to be as safe and effective as the predicate devices and poses no new questions of safety and effectiveness. |
Study Information:
-
Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Not explicitly stated as a number of cases or patients. The document vaguely mentions "various patients organs with known abnormalities or status" for non-clinical tests and "Patients' various organs" for clinical tests.
- Data Provenance: The data used for testing was "Scanned image datasets of various patients organs" and "Patients' scanned organs images." The country of origin is not specified, but it implies retrospective use of existing patient data.
-
Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:
- Not specified. The document indicates that "known abnormalities or status" were used, implying a pre-established understanding of the pathologies in the patient data. It doesn't detail how this "known status" was determined for the purpose of the study, nor does it mention a specific number or qualification of experts establishing this ground truth for the test set itself.
-
Adjudication Method for the Test Set:
- Not explicitly described. The study compares the V3D Explorer against predicate devices, stating that "evaluation results of both predicate device and V3D Explorer device were same and no significant differences were detected." This implies a direct comparison rather than an adjudication process typically used to reconcile expert discrepancies for ground truth.
-
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No, a formal MRMC comparative effectiveness study is not described. The study performed was a comparison of the device's functionality and output against predicate devices, not an evaluation of human reader performance with and without AI assistance.
- Effect Size: Not applicable, as no MRMC study was performed.
-
Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:
- Yes, the non-clinical and clinical tests described appear to be primarily standalone evaluations of the software's ability to process images and provide measurements and visualizations comparable to predicate devices. While the software is intended for use by radiologists and clinicians, the evaluation itself focuses on the software's output, not on how human users integrate the software's output into their diagnostic process or how their performance changes. The phrasing "evaluated various organs using the predicate device and recorded the results" and "evaluated all Patients' various organs using V3D Explorer application, and recorded the results" suggests an assessment of the device's output rather than human performance.
-
Type of Ground Truth Used:
- The ground truth referenced for the test set is "known abnormalities or status" within patient organ images. For phantom datasets, the ground truth was "pre-calculated values." This implies a combination of expert consensus/clinical diagnosis (for patient data) and empirical measurements (for phantom data). Pathology or outcomes data are not explicitly mentioned as ground truth sources.
-
Sample Size for the Training Set:
- Not specified. The document describes the V3D Explorer as "an additional image processing option added to our V-3D visualization system for which pre-market clearance was granted by the FDA vide K#002780." It mentions "core software technology" developed in a manner consistent with accepted software development standards and unit/system integration testing. It does not provide details on a specific "training set" in the context of machine learning, as this predates widespread deep learning applications for medical image analysis. The "training" likely refers to standard software development and testing practices rather than machine learning model training.
-
How Ground Truth for the Training Set Was Established:
- Given that the document describes software developed under standard engineering practices rather than a machine learning model, the concept of a "training set" with ground truth (as understood for AI/ML) is not directly applicable or discussed in the text. The "ground truth" for the software's development likely refers to functional requirements specifications, expected outputs, and successful execution of unit and integration tests against these specifications. For phantom data, "pre-calculated values" would serve as the ground truth.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).