(15 days)
CURVE IMAGE is an internet-based, image management software (PACS) that enables dental offices to keep records of hard and soft tissue charts in a form of digital images. The system uses a Web-based interface and includes acquisition, editing and storage of digital images. Images and data can be stored, communicated, processed and displayed within the system or across computer networks at distributed locations. Images can be acquired from standard dental imaging devices, or can be uploaded directly from the user's computer. Images can be edited (e.g., zoomed, contrast, rotated, etc.), as well as exported. The system is designed to provide images for diagnostic use.
Curve Image is a web-based dental practice image management system that provides Internet access to an image library for each patient in a practice. It also provides tools for dental practices to manipulate patient images and both acquire and upload new images in industry standard formats. Images can be annotated and tagged, and are available for both diagnostic and non-diagnostic use. All of these actions are performed from a secure website, after entering user credentials, similar to other commonly used online applications. The system can be accessed by the user via an internet connection and does not require any software installation on the user's computer.
Curve Image may be sold as a stand-alone product, or may be bundled with a suite of web applications to form a comprehensive dental practice management application called HERO.
The provided text describes a 510(k) submission for the "Curve Image" dental PACS system. However, the document does not contain specific acceptance criteria, performance metrics (like sensitivity, specificity, accuracy), sample sizes for test or training sets, details on expert ground truth establishment, or clinical study results typical for AI/ML device evaluations.
The document focuses on demonstrating substantial equivalence to predicate devices by comparing intended use, environment of use, performance characteristics, and technological characteristics. This type of submission relies on the similar nature of the device to already-cleared devices, rather than a clinical trial demonstrating new performance.
Therefore, many of the requested sections regarding acceptance criteria and study details cannot be filled from the provided text.
Here's an analysis of what information is available:
1. A table of acceptance criteria and the reported device performance
- Acceptance Criteria: Not explicitly stated in terms of performance metrics (e.g., sensitivity, specificity, F1 score, AUC). The "acceptance criteria" for this 510(k) is implicitly demonstrating substantial equivalence to the predicate devices through a comparison of features and capabilities, and successful non-clinical testing.
- Reported Device Performance:
- Non-Clinical Testing Summary: "Curve Dental, Inc. has conducted extensive non-clinical and validation testing of the Curve Image system, as a PACS system that is capable of providing reliable post-processing and display of images for dental applications. All of the different components of the Curve Image software have been stress tested to ensure that the system as a whole provides all the capabilities necessary to operate in a manner substantially equivalent to the predicate devices."
- Tests performed included:
- Product Risk Assessment
- Software modules verification tests
- Software validation test
| Acceptance Criterion (Implicitly based on substantial equivalence to predicates & non-clinical testing) | Reported Device Performance |
|---|---|
| Reliable post-processing and display of images for dental applications | Extensive non-clinical and validation testing conducted, including product risk assessment, software modules verification tests, and software validation tests. The system "provides all the capabilities necessary to operate in a manner substantially equivalent to the predicate devices." |
| Functional equivalence to ChairSide Software Application (K982422) | The comparison table (pages 4-7) details feature-by-feature equivalence in image acquisition, editing, storage, browsing, annotation, manipulation (zoom, crop, rotate, contrast, brightness), as well as administrative, patient management, scheduling, billing, insurance, claims, dental charting, perio charting, patient notes, and prescriptions. |
| Functional equivalence to Centricity PACS Web Diagnostic (Web DX) PACS (K083018) | The comparison table (pages 4-7) details feature-by-feature equivalence in web-based application, secure data transmission (HTTPS), database management, secure server infrastructure, user login, account management, security administration, patient management, image viewing, manipulation (zoom, rotate, brightness, contrast), and DICOM compliance. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not provided. This document does not detail specific image datasets used for a "test set" in the context of clinical performance evaluation. The non-clinical testing is described generally as "software modules verification tests" and "software validation test" without specifying sample sizes for images or data.
- The device is a PACS system, so it manages images from "standard dental imaging devices" or uploads from the user's computer, implying a wide range of potential data, but not a specific test set.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
- Not applicable. This information is not relevant to a 510(k) submission for a PACS system that acts as an image management tool, not an AI diagnostic aid requiring expert-established ground truth for its own diagnostic performance. The device is for "diagnostic use" by dental professionals, but it doesn't perform automated diagnosis itself.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable. See point 3.
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
- No. This type of study is not mentioned or undertaken for this device. The Curve Image system is a PACS, not an AI diagnostic tool designed to assist human readers directly in interpretation (beyond displaying images clearly and providing basic manipulation tools).
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
- Not applicable. The device is a Picture Archiving and Communications System (PACS); it is not an AI algorithm performing diagnostic tasks. Its performance is related to its functionalities as an image management system.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Not applicable. For a PACS system, the "ground truth" would relate to its ability to accurately store, retrieve, display, and manipulate images, which is assessed through software validation and verification, not against clinical ground truth like pathology for specific diagnoses.
8. The sample size for the training set
- Not provided. The device is not an AI/ML system that undergoes "training" in the traditional sense on a dataset. It's a software application.
9. How the ground truth for the training set was established
- Not applicable. See point 8.
§ 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).