(158 days)
OncoTrac™ is a software based Picture Archiving and Communication System (PACS) used with general purpose computing hardware for the display and visualization of medical image data. It provides for communication, storage, processing, rendering, and display of DICOM compliant image data derived from various sources including CT and MRI, measurement of lesions identified by trained users, tabulation of measurements, categorization of tumor response in accordance with user selected standards, and generation of a structured imaging report.
OncoTrac™ is intended for use as a diagnostic, review, and analysis tool by trained professionals such as physicians, technologists, and nurses. When interpreted by a trained physician, reviewed images may be used as an element for diagnosis. OncoTrac™ does not provide or claim any automatic detection or automatic diagnosis of abnormal anatomy, structure, or function.
OncoTrac™ is not intended for use for mammography.
OncoTrac™ is a software based Picture Archiving and Communication System (PACS) used with general purpose computing hardware for the display and visualization of medical image data. It provides for communication, storage, processing, rendering, and display of DICOM compliant image data derived from various sources including CT and MRI.
OncoTracTM runs on either a native or virtualized Microsoft Windows platform. Available functions include communication, storage, processing, rendering, and display of DICOM compliant image data derived from various sources including CT and MRI. measurement of lesions identified by trained users, tabulation of measurements, categorization of tumor response in accordance with user selected standards, and generation of a structured imaging report. The user controls these functions with a system of interactive menus and tools.
The provided text is a 510(k) summary for the OncoTrac™ software, dated November 18, 2011. This document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study showing the device meets specific acceptance criteria. Based on the provided text, a comprehensive study proving acceptance criteria has not been detailed in a way that allows for the creation of the requested table and detailed analysis.
Here's what can be extracted and what information is missing:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not explicitly state formal acceptance criteria with numerical targets. Instead, it relies on comparison to a predicate device (GE AW Server K081985) and internal testing for software quality. The "features" table (Document 2) serves as the closest resemblance to acceptance criteria, where the OncoTrac™ is compared functionally to the predicate.
| Feature | Acceptance Criteria (Implied by Predicate) | Reported Device Performance (OncoTrac™) |
|---|---|---|
| DICOM compliance | Yes | Yes |
| 2D Imaging | 2D image viewer | 2D image viewer |
| Interactive user controls | Yes | Yes |
| Lesion measurement | Yes | Yes |
| Body region(s) | Multiple | Multiple |
| Modalities | CT, MRI | CT, MRI |
| Quantitative oncology response assessment | RECIST, WHO | RECIST, WHO |
| Generation of structured report | ||
| Prescription Use | Yes | Yes |
| Intended Users | Trained Professionals | Trained Professionals |
| Software Testing | Passed critical tests for patient safety, acceptable overall performance. | Passed all tests considered critical in terms of patient safety and demonstrated an overall acceptable performance. |
| Hazard Analysis | Conducted | Conducted (level of concern classified as moderate) |
Missing Information/Cannot Determine from Text:
- Specific quantitative performance metrics: The document confirms feature presence but doesn't provide success rates, accuracy figures, or error margins for tasks like lesion measurement accuracy, response assessment concordance, or reporting completeness/accuracy.
- Detailed acceptance criteria for software itself: While "passed all tests considered critical" is stated, the specific criteria for these tests (e.g., bug count, performance benchmarks, usability scores) are not provided.
2. Sample Size Used for the Test Set and Data Provenance:
The document mentions that "The OncoTrac™ software has been extensively tested on Windows 64 bit systems by members of the development and quality control teams." However, it does not specify:
- The sample size of medical images or patient cases used for testing.
- The provenance of this data (e.g., country of origin, retrospective or prospective nature).
- Whether a specific "test set" in the context of machine learning model evaluation was used, as this is a PACS software, not an AI model in the modern sense.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications:
Not applicable or not mentioned in the provided text. The document refers to "lesions identified by trained users" and "categorization of tumor response in accordance with user selected standards," implying human interpretation. However, there's no mention of a formal ground truth establishment process involving a specific number of experts or their qualifications for a dedicated test set used to validate the software's performance against a gold standard.
4. Adjudication Method for the Test Set:
Not applicable or not mentioned. Given the nature of a PACS for display and measurement, and the lack of a defined test set for "ground truth" establishment by multiple experts, an adjudication method is not described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done:
No, an MRMC comparative effectiveness study is not mentioned. The 510(k) relies on substantial equivalence to a predicate device based on functional comparison, not on demonstrating improved human reader performance with or without AI assistance. The OncoTrac™ is described as a tool that "does not provide or claim any automatic detection or automatic diagnosis of abnormal anatomy, structure, or function."
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:
The concept of "standalone performance" as it relates to an AI algorithm is not applicable here. OncoTrac™ is described as a software-based PACS for display, visualization, measurement, and reporting, guided by "trained users" and "trained professionals." It's an interactive tool, not an autonomous diagnostic algorithm. The software performs measurements and categorizations based on user input, not entirely independently.
7. The Type of Ground Truth Used:
The document refers to "user selected standards" for tumor response categorization (RECIST, WHO). This implies that the software's ability to categorize is based on widely accepted clinical standards, where the "ground truth" would be established by the consensus of the medical community on how to apply these standards. For lesion measurements, the "ground truth" would be the manually identified and measured lesion dimensions by a trained user, which the software then processes, tabulates, and reports. There's no mention of pathology or outcomes data being directly used as a ground truth for validating the software's core functions.
8. The Sample Size for the Training Set:
Not applicable. The OncoTrac™ described in this 510(k) is an image viewing, processing, and reporting software, not a machine learning model that requires a "training set" in the conventional sense. The software's development likely involved standard software engineering practices, testing, and debugging, but not a dataset for training an AI model.
9. How the Ground Truth for the Training Set Was Established:
Not applicable, as there is no "training set" for an AI model.
§ 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).