(152 days)
Improvis Imaging is a Windows-based software package that allows dental clinicians to acquire images from standard dental imaging devices and commercially available scanners, digital cameras and intra-oral cameras. It is designed to be used as an imaging database for storage and organization of patient digital images and radiographs. Features include resizing, rotating, embossing and sharpening of images.
Improvis Imaging is written using three programming languages (C++, C#, TSQL) and is designed to work with standard personal computers capable of running Windows 2000 or higher.
Intended users of this system are trained professionals, including but not limited to dentists, hygienists and clinical assistants.
Improvis Imaging is a software package that allows dental clinicians to acquire images from standard dental imaging devices and commercially available scanners, digital cameras and intraoral cameras. It is designed to be used as an imaging database for storage and organization of patient digital images and radiographs. Once acquired, images can be enhanced for viewing by applying image processing functions which include resizing, rotating, embossing and sharpening of images. All images are compressed using lossless compression and stored in a shared relational database.
The Improvis software interacts with the medical device software drivers, not the medical devices themselves. This interaction allows the computer system to acquire images captured via webcams, intraoral video cameras, panoramic x-rays, and other solid state sensors. These images are digitized by the outside vendor supplied medical devices, and then communicated via Improvis to the patient record. Once the images have been received by the system, they are embedded within the patient's dental record and can be accessed from any associated practice location.
Radiographic images are compressed via a lossless system and can be manipulated and enhanced to suit the dental care provider's needs. Non-diagnostic images, such as scanned documents, may be compressed using non-lossless methods which optimize image quality and storage requirements. Original compressed images are stored prior to application of any image processing algorithms.
Image processing by Improvis Imaging utilizes industry standard algorithms that do not result in the alteration of an image's or radiograph's content and will not introduce false data or modification into the acquired image. Improvis Imaging does not control the x-ray taking system and does not generate x-ray images directly from the physical device, but does provide the tools that permit the user to enhance images for diagnostic purposes.
Improvis Imaging is a three tier application consisting of user interface, business objects (which provide communication between the user interface and database tiers), and database. The top two tiers of the program are written in Microsoft Visual Studio .NET C#, while the database components are written in Microsoft T-SQL. Improvis Imaging is a Microsoft Windows Forms (non-browser based) 32 bit application designed to run on Windows-compatible personal computers running the Microsoft Windows XP (or higher) operating system. Imaging processing functions are provided through the integration of a third party software development toolkit from Lead Technologies, Inc.
Improvis Imaging is designed for use in a client-server environment in which the user interface portion of the application runs on an individual user's computer workstation as a Windows executable application. The Improvis Imaging shared database is installed on a single or clustered server running Microsoft SQL Server. The workstations and server are connected by a network using Microsoft Windows IP protocols. The application is designed for use in a Microsoft Windows Active Directory domain for authentication and access control, but can also run in non-Active Directory workgroups using internal Improvis access control.
Improvis Imaging is not compliant with DICOM standards.
The request asks for specific details regarding acceptance criteria and a study proving a device meets these criteria. However, the provided document is a 510(k) Summary for the IMPROVIS® Imaging System, which is a dental imaging software. This document primarily focuses on establishing substantial equivalence to predicate devices, rather than presenting a performance study with detailed acceptance criteria for a new algorithmic function.
Therefore, many of the requested details, such as specific acceptance criteria for algorithmic performance, effect size of AI assistance on human readers, details of ground truth establishment for a test set, and sample sizes for training/test sets in the context of an algorithm's performance evaluation, are not available in the provided text. The document describes the software's functionality and its comparison to existing devices.
Here's an analysis of the information that can be extracted or inferred from the provided text, along with a clear indication of what is missing:
1. Table of acceptance criteria and the reported device performance
The document does not explicitly define "acceptance criteria" in the context of quantitative performance metrics for a specific algorithmic function. Instead, its primary "acceptance criteria" for the 510(k) submission is substantial equivalence to predicate devices in terms of intended use and technological characteristics. The reported "performance" relates to the similarity of features rather than measurements against a threshold.
| Comparison Areas | IMPROVIS Imaging Performance (Reported) | Acceptance Criteria (Inferred from Substantial Equivalence Goal) |
|---|---|---|
| Intended Use (Acquisition, viewing, editing, storage of dental radiographs and patient image records) | Same as predicate devices | Must be "Same" as predicate devices |
| Intended Users (Trained dental professionals) | Same as predicate devices | Must be "Same" as predicate devices |
| Operating System Support | Microsoft Windows XP or higher (32 & 64 bit) | Must be comparable or superior to predicate devices (Win 2000+ for Visix, Win 98+ for TigerView) |
| Network Compatibility | Ethernet IP 100 mbps or greater | Must be "Same" as predicate devices |
| Monitor Resolution | 800 x 600 or greater | Must be comparable or superior to predicate devices (1024x768 for Visix, 800x600 for TigerView) |
| User Interaction | Keyboard/Mouse | Must be "Same" as predicate devices |
| CPU | 2 GHz Pentium or higher | Must be "Same" as predicate devices |
| RAM | 1 GB or higher | Must be "Same" as predicate devices |
| Multi-User Capability | Yes | Must be "Same" as predicate devices |
| Image Import/Export | Yes (BMP, TIFF, JPG) | Must be comparable or superior to predicate devices (TIFF, JPG for predicates) |
| Acquisition Devices | Sensor, Camera, Scanner, File Import | Must be "Same" as predicate devices |
| Imaging Interfaces | Microsoft DirectX Version 9.0+, TWAIN 2.0+ | Must be comparable or superior to predicate devices (Proprietary, DirectX, TWAIN for predicates) |
| Image Organization | Create Series, Move Images, Create Series Template | Must be comparable to predicate devices (Mount Images, Move within Mount, Create a Mount) |
| Image Search Available | Yes | Must be "Same" as predicate devices |
| Image Storage (Original data unaltered) | Yes | Must be "Same" as predicate devices |
| Image Storage (Lossless compression of radiographic images) | Yes | Must be comparable (Predicates show Lossless/lossy compression) |
| Image Storage (Full history of enhancements recorded) | Yes | Must be comparable to predicate devices (History of operations) |
| Database Storage | Microsoft SQL Server database | Must be robust and comparable to predicate devices (Filesystem for predicates) |
| Database Software | SQL Server 2005 or higher | Must be robust and comparable to predicate devices (Filesystem for predicates) |
| Image Viewing Features | Zoom, Full Screen, Scale, Rotate, Flip, etc. | Must be "Same" as predicate devices |
| Image Measurement Features | Line, Angle, Calibrate, Line Color/Show/Hide | Must be "Same" as predicate devices |
| Image Annotation Features | Line, Free Line, Circle, Rectangle, Arrows, Text, Color, Width, Show/Hide | Must be comparable to predicate devices (Lines, Freehand, Circle, Square, Arrows, Text, Color, Width, Show/Hide) |
| Image Operations (Enhancement & Manipulation) | Magnifier, Print, Negative, Colorize, Emboss, Sharpen, Original Image, Brightness, Contrast, Gamma | Must be comparable or superior to predicate devices (Magnifying Glass, Print, Negate, Colorize, Pseudo 3D, Sharpen Edge, Original Image, Brightness, Contrast, Gray Shift (Gamma)) |
| Security | Login, admin, and feature access | Must be comparable or superior to predicate devices (Login and admin) |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not applicable / Not provided. The document is for a general-purpose dental image management and enhancement software. It does not describe a clinical study focused on the diagnostic performance of an algorithm that would require a test set of medical images. The software provides tools for image manipulation (e.g., sharpening), but these are standard and not presented as novel AI algorithms requiring validation with 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 / Not provided. No test set performance study is described.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable / Not provided. No test set performance study is described.
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. The document does not describe an MRMC study. The software provides image enhancement tools, but not "AI assistance" in the sense of a diagnostic algorithm being evaluated for its impact on reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- No. This device is a software package for managing, viewing, and enhancing images by human users. It is not a standalone algorithm providing diagnostic outputs. The image processing functions use "industry standard algorithms that do not result in the alteration of an image's or radiograph's content and will not introduce false data or modification into the acquired image."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not applicable / Not provided. No specific ground truth for an algorithmic diagnostic function is relevant or discussed in the document. The "ground truth" for the software's functionality is its ability to perform the stated image management and manipulation tasks as intended and as demonstrated by its feature list, which is compared to predicate devices.
8. The sample size for the training set
- Not applicable / Not provided. This is not an AI/ML diagnostic algorithm that requires a training set.
9. How the ground truth for the training set was established
- Not applicable / Not provided. This is not an AI/ML diagnostic algorithm that requires a training set.
§ 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).