Search Results

Digidelca provides the radiologists or pneumologists the ability to acquire chest xray images by filmless radiography (digital radiography), based on CCD technology. The x-ray transmission profile of the chest is converted into an electronic, digital image in real-time. Chest images become available for preview by the x-ray technician on the operators workstation only seconds after the x-ray exposure. After acceptance by the tech, digital (DICOM) images can be stored on electronic media, as e.g. CD-ROM, magnetic disk, or be exported to a (DICOM/PACS) network, c.q. clinical review station or to a film printer.

Digidelca is a product which was developed around hardware and software components which are already market within the United States and therefore substantial equivalence is claimed to Electrodelca for the electrical, mechanical and optical system layout and to AMBER-DU and HyperPACS for the software configuration:

• The Oldelft Electrodelca (tm) mass chest x-ray system (K892659) for the camera . housing basic design, the image intensifier tube, the elevator stand basic design and the compatible x-ray tube and high voltage generator selection. The image capturing device in Digidelca is a TDI CCD sensor, instead of radiographic film.
• The Rogan HyperPACS (tm) software package (K950343) for the principal software ● tasks for the Operators Workstation: image acquisition and storage, image export, network interfacing.
• The Oldelft Amber-DU (K973219) software package (reconfigured) for user interfacing . at the Operators Workstation.

The Operators Workstation displays screens to the operator for data input and for data and image display. The Digidelca software is configured as a dedicated shell around the Rogan software which operates in the background to perform essential functions for data acquisition, image storage and image export. The OWS allows for importing patient demographic information and exportation of digital images into which patient demographics have been incorporated (DICOM compatible data structures).

The Date Entry System is an additional pc platform which is used to copy patient demographics to a card formation carrier by a thermal printing process. The card is handed out to the examinee who will submit it to the Digidelca(-M) operator prior to making his/het x-rays. Patient demographics are scanned from the card by a two dimensional barcode reader and thereby entered into the Digidelca(-M) operators workstation.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Digidelca device:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific numerical acceptance criteria for the Digidelca device in terms of performance metrics (e.g., sensitivity, specificity, resolution targets with numerical thresholds). Instead, the performance is described qualitatively and comparatively to the predicate device, Electrodelca.

Therefore, the table below reflects the implied acceptance criteria based on the claims of substantial equivalence and the qualitative performance descriptions.

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: The document does not specify a numerical sample size for the clinical test set. It only mentions that the device is "clinically used for both in-patients and out-patients" at a beta test site.
• Data Provenance: The clinical testing was conducted at a "beta test site in The Netherlands (Twenteborg Hospital, Almelo)." The data is prospective as it describes ongoing clinical use since mid-1997.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Number of Experts: The document does not explicitly state the number of experts. It refers to "radiologists" (plural), implying more than one.
• Qualifications of Experts: The experts are described as "radiologists." No further details on their experience level (e.g., years of experience) are provided.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (e.g., 2+1, 3+1). It states that "images are generally appreciated by radiologists as 'better' then those from Electrodelca," which suggests a qualitative assessment by multiple radiologists, but not a formal adjudication process to establish a definitive ground truth.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was it done? The document does not describe a formal MRMC comparative effectiveness study in the sense of a controlled study comparing human readers with and without AI assistance.
• Effect Size: Therefore, no effect size of human readers improving with AI vs. without AI assistance is reported.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The Digidelca device, as described, is an x-ray system for acquiring digital images. While it mentions "Digital augmentations," these are enhancements to the imaging process, not a standalone AI algorithm for interpretation or diagnosis. Therefore, a standalone (algorithm only) performance study as typically understood for AI diagnostic tools was not performed or described in this document. The focus is on the imaging system itself, with human radiologists performing the interpretation.

7. Type of Ground Truth Used

The ground truth used for assessing image quality was expert consensus/opinion from radiologists. They appreciated the images as "better" than those from the predicate device. This is a subjective assessment of image quality and clinical utility, rather than an objective "ground truth" derived from pathology, outcomes data, or a strict consensus protocol.

8. Sample Size for the Training Set

The document does not mention a training set in the context of an AI algorithm learning from data. The device's "software configuration" is based on existing market software packages (Rogan HyperPACS and Oldelft Amber-DU), which would have had their own development and testing, but not a specific training set for an AI component of Digidelca itself.

9. How the Ground Truth for the Training Set Was Established

Since no training set for an AI algorithm is mentioned, this information is not applicable to the provided text. The device primarily concerns hardware and software integration for image acquisition and display, not a learned diagnostic model.

Ask a specific question about this device