Search Results

The X-ray system creates data for digital exposures in the maxillofacial area and in subareas for dentistry and pediatric dentistry, for hard-tissue diagnostics within ENT medicine, and carpus exposures.

The proposed Orthophos S is a dental cone-beam CT system (CBCT), which comprises sensor units for 2D cephalometric exposures, 2D panoramic radiograph and 3D volume exposure. The combination of sensors varies depending on the installed device configuration. In the proposed device, the 3D sensor, as well as the 2D cephalometric sensor, are identical to the corresponding sensors utilized in the predicate device (K150217). However, with respect to the 2D panoramic exposures, the proposed Orthophos S device utilizes a CMOS (scintillation) sensor whereas the predicate Orthophos SL (K150217) utilizes a CMOS (direct conversion) sensor.

Orthophos S uses an x-ray beam that rotates around the patient's head. Detectors acquire twodimensional x-ray images at varying radiographic angles. An enhanced software algorithm generates the 2D panoramic and 2D cephalometric images and the reconstruction algorithm reconstructs the 3D volumetric image from the raw image data.

The exposed area can be adapted to a specific region of interest to keep the radiation dose as low as possible for the patient. This is achieved by collimating the x-ray beam and the adjustment of starting and ending points of the sensor/x-ray source movement. Furthermore, the radiation dose can be adapted by various parameters such as program types and exposure technique factors. These functions are available for CBCT, cephalometric and panoramic exposures.

A Class I laser beam is utilized to define reference lines for the correct patient position. The patient is stabilized through different bite blocks and the motoric driven forehead and temple supports.

The obtained digital image data is processed to provide a reconstructed image to the operator/user. The reconstructed images are transferred to the currently marketed SIDEXIS 4 imaging processing software (K132773) and stored in the SIDEXIS 4 software database. The proposed Orthophos S device uses the same SIDEXIS 4 image processing software (K132773) as does the predicate device (K150217) and there are no changes to the SIDEXIS 4 software (K132773) introduced in this premarket notification.

The proposed Orthophos S device includes metal artifact reduction software feature which automatically reduces image artifacts caused by radiopaque objects. This identical software feature is also included in the predicate Orthophos SL (K150217) device and remains unchanged in the proposed device.

A user control panel allows user actions as e.g. height adjustment, selection of programs and exposure parameters and delivers information about the unit status.

For 3D imaging, the proposed Orthophos S allows the user to select volume sizes, within which multiple fields of view, anatomic positions, and collimation may be selected. This is intended to allow the clinician to select the field of view based on the diagnostic need and to minimize the dose exposed to the patient.

The provided document is a 510(k) summary for the Orthophos S device. It primarily focuses on demonstrating substantial equivalence to a predicate device (Orthophos SL, K150217) rather than providing detailed acceptance criteria and a study proving performance against those criteria as would be expected for a novel AI/ML device.

However, based on the information available, we can extract the relevant points regarding the device's performance, even if not presented as a formal study with specific acceptance criteria as you've requested for an AI/ML context. The document describes general performance verification without numerical acceptance criteria or detailed study methodologies typical of AI performance validation.

Here's an attempt to structure the information based on your request, acknowledging the limitations of the provided document for answering all specific points relevant to an AI/ML device.

Device Name: Orthophos S
Device Type: Dental Cone-Beam CT (CBCT) X-ray system

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria for image quality or specific performance metrics as one would find for an AI/ML model. Instead, it relies on demonstrating that the new device meets the design input requirements and performs equivalently to the predicate device.

Note on "Reported Device Performance": The document primarily states that testing was performed and demonstrated substantial equivalence and conformity to standards, rather than providing specific quantitative results for image quality comparison. This is typical for a 510(k) submission where the emphasis is on equivalence rather than detailed, comparative performance reporting against novel metrics.

Detailed Study Information (Based on the document's content, emphasizing what is not present for an AI/ML context)

The provided document describes the Orthophos S as a dental CT system. While it has an "enhanced software algorithm" for 2D panoramic and cephalometric images and a "reconstruction algorithm" for 3D volumetric images, and includes a "metal artifact reduction software feature," the
510(k) submission is for the imaging device itself, not specifically an AI/ML-driven diagnostic or interpretative software. Therefore, many of the questions structured for an AI/ML study (e.g., sample size for training, number of experts for ground truth, MRMC study, standalone performance) are not directly addressed in this type of submission.

Here's an analysis based on the provided text:

2. Sample sizes used for the test set and the data provenance:

   • The document states that "Functional testing as well as performance testing of the proposed device Orthophos S has been performed to verify the design output met the design input requirements and to validate that the device confirm to the intended user needs and the intended use as defined." and "Verification activities for confirmation of the image quality of the proposed device has been performed."
   • Specific sample sizes (e.g., number of patients/images in a test set, number of image acquisitions) are not provided in this 510(k) summary.
   • Data Provenance: Not specified. This type of performance testing typically involves in-house validation with phantoms and potentially healthy volunteers or cadaveric samples, but the document does not elaborate on the origin (country, retrospective/prospective) of any data used for testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Given that this is a 510(k) for an imaging device, not an AI diagnostic software, the concept of "ground truth established by experts" in the clinical sense (e.g., for disease detection) is not explicitly discussed.
   • The "image quality review" mentioned would typically involve internal qualified personnel or engineers comparing images from the new device against the predicate or established quality standards for diagnostic imaging. The number and qualifications of such "experts" are not specified.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • This is not applicable or specified. The testing described appears to be a technical verification of image quality parameters and adherence to standards rather than a clinical interpretation study requiring adjudication.

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 MRMC study was performed or reported. This device is an imaging system, and while it has "enhanced software algorithms," it's not a CAD (Computer-Aided Detection/Diagnosis) or interpretative AI tool that would assist human readers in a diagnostic task. The document specifically states: "Given the differences from the predicate device, no clinical data is necessary to support substantial equivalence." This confirms that comparative effectiveness clinical studies, like MRMC, were not conducted.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Given that this is an imaging device, the concept of "standalone algorithm performance" (like an AI model reading an image) is not directly applicable in the way it would be for an AI diagnostic software. The device's "algorithms" are intrinsic to its function (image reconstruction, artifact reduction) and are part of the overall system performance. The performance tested is the device's ability to produce images of sufficient quality, not the performance of an AI model making a diagnosis.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • For an imaging device, "ground truth" for image quality is typically established through:
     • Physical phantoms: Objects with known properties used to measure spatial resolution, contrast, noise, etc.
     • Technical specifications: Comparing output (e.g., kV, mA, exposure time, FOV) against design specifications.
     • Comparison to predicate device images: Qualitative and quantitative comparison to images from a device already on the market (the predicate).
   • The document does not detail the specific "ground truth" methods used, but implies technical evaluation and comparison to the predicate, rather than biological or clinical ground truth.

8. The sample size for the training set:

   • Not applicable / Not provided. This document does not describe the development of a specific AI model that would have a training set. The "enhanced software algorithm" and "reconstruction algorithm" mentioned are likely deterministic or traditional image processing methods, not machine learning models requiring training data in the sense of AI/ML.

9. How the ground truth for the training set was established:

   • Not applicable. As no AI training set is described, no ground truth establishment for it is mentioned.

Ask a specific question about this device

The X-ray system creates data for digital exposures in the maxillofacial area and in subareas for dentistry, including pediatric dentistry, for hard-tissue diagnostics within ENT medicine, and for carpus exposures.

The device comprises image receptors for cephalometric exposures, 2D panoramic radiographs and 3D volume exposures. The combination of sensors in the device varies depending on the installed options and the regions of interest can be altered. The technology behind this is collimation and different start- and end angles of exposure. These allow for a reduced dosage depending on the program selected. This function is available with some volume, cephalometric and panoramic programs.

Class I laser beam light localizers aid in the positioning of a patient's head which may be fixed through the use of bite blocks and adjustable forehead and temple supports.

From the obtained exposures, reconstructed images can be viewed. The reconstructed 3D volumes, simulated projection exposures and panoramic/cephalometric data can be conveyed to SIDEXIS (an FDA approved Sirona software for acquisition, administration, analysis, diagnosis, presentation and transfer of image data for medical/dental use) and stored in the SIDEXIS database.

An operator control panel allows for height adjustment, selection of mode and program, and indication of machine states. A separate handheld push-button serves for exposure release and an optional remote control is available.

The provided text describes a 510(k) premarket notification for the "ORTHOPHOS SL" dental X-ray system. The document focuses on demonstrating substantial equivalence to predicate devices rather than providing detailed acceptance criteria and a study proving the device meets them in the context of an AI/algorithm-driven device.

Therefore, many of the requested items (e.g., acceptance criteria table, sample size for test set, number of experts for ground truth, adjudication method, MRMC study, standalone performance, training set details) are not applicable or not present in this type of regulatory submission for a conventional medical imaging device without explicit AI involvement.

Based on the provided text, here's the information that can be extracted:

1. A table of acceptance criteria and the reported device performance

• Not applicable for an AI device. This document is for a traditional X-ray system. The "acceptance criteria" discussed are largely related to meeting established X-ray performance standards and demonstrating substantial equivalence to predicate devices. Specific quantitative performance metrics for diagnostic accuracy (e.g., sensitivity, specificity, AUC) against a defined ground truth, as would be expected for an AI device, are not detailed.
• The study focuses on demonstrating that the device's technical specifications and image quality are comparable to predicate devices and comply with relevant international standards.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Test Set Sample Size: "test phantoms" were used for evaluating exposure programs. "Sample clinical images" were provided. No specific numerical sample size for either is given.
• Data Provenance: Not specified beyond "test phantoms" and "sample clinical images." It does not mention country of origin or whether clinical data was retrospective or prospective.

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)

• "Oral Surgeon reports" were provided with the sample clinical images, "asserting the general diagnostic quality of the images."
• Number of Experts: Not specified.
• Qualifications: "Oral Surgeon" is mentioned as the expert type, but no specific experience level is provided.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• None explicitly mentioned. The "Oral Surgeon reports" seem to imply a singular assessment rather than an adjudicated consensus process.

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, an MRMC comparative effectiveness study was not done. This document is for a conventional X-ray system, not an AI-assisted diagnostic tool, so improvement of human readers with AI assistance is not applicable.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Not applicable. This is a hardware X-ray device, not a standalone algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• For technical testing, "test phantoms" were used.
• For clinical images, "Oral Surgeon reports asserting the general diagnostic quality" served as a form of expert assessment of image quality, not necessarily a definitive "ground truth" for specific disease presence/absence.

8. The sample size for the training set

• Not applicable; no training set mentioned. This is a conventional X-ray system, not an AI model that undergoes training.

9. How the ground truth for the training set was established

• Not applicable; no training set mentioned.

Ask a specific question about this device