Search Results

The unit is intended to produce panoramic or cephalometric digital x-ray images. It provides diagnostic details of the dento-maxillofacial, sinus and TMJ for adult and pediatric patients. The system also utilizes carpal images for orthodontic treatment. The device is to be operated by physicians, dentists, and x-ray technicians.

The device is an advanced 2-in-1 digital X-ray imaging system that incorporates PANO and CEPH (Optional) imaging capabilities into a single system and acquires 2D diagnostic image data in conventional panoramic and cephalometric modes.
The device is not intended for CBCT imaging.
VistaPano S is identified as panoramic-only models for VistaPano S Ceph.
ProVecta S-Pan Ceph and ProVecta S-Pan are alternative model for VistaPano S Ceph and VistaPano S respectively.
The subject device has different model names designated for different US distributors:

• -VistaPano S Ceph, VistaPano S: DÜRR DENTAL
• ProVecta S-Pan Ceph, ProVecta S-Pan: AIR TECHNIQUES ।
  Key components of the device
• 1. VistaPano S Ceph 2.0 (Model: VistaPano S Ceph), VistaPano S 2.0 (Model: VistaPano S) digital x-ray equipment (Alternate: ProVecta S-Pan Ceph 2.0 (Model: ProVecta S-Pan Ceph), ProVecta S-Pan 2.0 (Model: ProVecta S-Pan))
• 2. SSXI detector: Xmaru1501CF-PLUS, Xmaru2602CF
• 3. X-ray generator
• 4. PC system
• 5. Imaging software

The provided text describes the substantial equivalence of the new VATECH X-ray imaging systems (VistaPano S Ceph 2.0, VistaPano S 2.0, ProVecta S-Pan Ceph 2.0, ProVecta S-Pan 2.0) to their predicate device (PaX-i Plus/PaX-i Insight, K170731).

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly stated as numerical metrics in a table. Instead, the document focuses on demonstrating substantial equivalence to a predicate device. This is a common approach for medical device clearance, where the new device is shown to be as safe and effective as a legally marketed device. The "performance" in this context refers to demonstrating that the new device functions similarly or better than the predicate, especially for the new "non-binning" mode.

The study aims to show that the new device's performance is equivalent or better than the predicate device, particularly for the new "HD mode (non-binning)" in CEPH imaging. The primary comparison points are:

Study Details:

The provided document is a 510(k) summary, not a detailed study report. Therefore, some specific details about the study methodology (like expert qualifications or full sample sizes for clinical images) are not granularly described. However, we can infer some information:

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

   • The document states "Clinical images obtained from the subject and predicate devices are evaluated and compared." However, the exact sample size for this clinical image evaluation (the "test set" in AI/ML terms) is not specified.
   • The data provenance is implied to be from a retrospective collection of images, likely from VATECH's own testing/development or existing clinical sites that used the predicate device and potentially early versions of the subject device. The country of origin for the clinical images is not explicitly stated, but given the manufacturer is based in Korea ("VATECH Co., Ltd. Address: 13, Samsung 1-ro 2-gil, Hwaseong-si, Gyeonggi-do, 18449, Korea"), it's reasonable to infer some data might originate from there.
   • For the bench testing, the sample size is also not specified, but it would involve phantoms.

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

   • The document mentions "Clinical images obtained from the subject and predicate devices are evaluated and compared." However, it does not specify the number of experts, their qualifications, or how they established "ground truth" for these clinical images. The evaluation is described in general terms, implying a qualitative assessment of general image quality ("general image quality of the subject device is equivalent or better than the predicate device").

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

   • The document does not describe any formal adjudication method for the clinical image evaluation. It simply states "evaluated and compared."

4. 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 study was NOT done. This device is an X-ray imaging system, not an AI-assisted diagnostic tool for interpretation. The study focused on demonstrating the image quality of the system itself (hardware and associated basic image processing software) as being substantially equivalent or better than a predicate system, not on improving human reader performance with AI assistance. The "VisionX 3.0" software is an image viewing program, not an AI interpretation tool.

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

   • This is not applicable in the sense of a diagnostic AI algorithm. The performance evaluation is inherently about the "algorithm" and physics of the X-ray system itself (detector, X-ray generator, image processing pipeline) without human interaction for image generation, but humans are integral for image interpretation. The device's performance (image quality, resolution, DAP) is measured directly, similar to a standalone evaluation of a sensor's capabilities.

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

   • For the bench testing, the ground truth was based on physical phantom measurements (e.g., line pair resolution, contrast using phantoms).
   • For the clinical image evaluation, the "ground truth" or reference was implicitly the subjective assessment of "general image quality" by unspecified evaluators, compared to images from the predicate device. There is no mention of an objective clinical ground truth like pathology or patient outcomes.

7. The sample size for the training set:

   • The document describes an X-ray imaging system, not a device incorporating a machine learning model that requires a "training set" in the conventional sense. Therefore, there is no mention of a training set sample size. The software mentioned (VisionX 3.0) is a general image viewing program, not a deep learning model requiring a specific training dataset.

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

   • Not applicable, as no external "training set" for a machine learning model is described.

Ask a specific question about this device

X Sensor is intended to collect dental x-ray photons and convert them into electronic impulses that may be stored, viewed and manipulated for diagnostic use by dentists.

X Sensor is a digital intraoral sensor which acquires digital intra-oral images. X Sensor acquires intra oral images with a sensor that is connected to a computer to produce an image almost instantaneously following exposure. The primary advantage of direct sensor systems is the speed with which images are acquired. X Sensor includes the firmware for the sensor and the previously cleared imaging software "ExDent-I".

The provided text is a 510(k) summary for the X Sensor, a digital dental intraoral sensor. It describes the device's technical characteristics, intended use, and its comparison to a predicate device (EzSensor XHD). However, this document does not contain the detailed information necessary to fully answer your request regarding acceptance criteria and the study proving the device meets these criteria in the context of AI/ML performance.

Specifically, the document focuses on regulatory clearance for a medical device (an X-ray sensor) based on hardware and image quality performance relative to a predicate device, as well as electrical, mechanical, and software safety. It does not mention any AI/ML components or studies evaluating AI/ML performance.

Therefore, many parts of your request, such as those related to AI/ML specific acceptance criteria, sample sizes for AI/ML test and training sets, expert adjudication, MRMC studies, or standalone algorithm performance, cannot be answered from the provided text.

However, I can extract information related to the device's general performance testing and comparison to the predicate device, which serves as a form of "acceptance" for medical device clearance.

Here's what can be extracted and how it relates to your request, with a clear indication of what information is not present:

Acceptance Criteria and Device Performance (General Device Performance)

Based on the document, the "acceptance criteria" appear to be meeting or exceeding the performance of the predicate device (EzSensor XHD) in key technical metrics and demonstrating adequate image quality for diagnostic use.

Study Information (Based on Available Text)

1. Sample size used for the test set and the data provenance:

   • The document states "The clinical images obtained from the X Sensor and EzSensor XHD were reviewed and rated comparatively."
   • Specific sample size for the clinical images reviewed is NOT provided.
   • Data provenance (country of origin, retrospective/prospective) is NOT provided. Given it's a 510(k) for a device like an X-ray sensor, the "test set" likely refers to physical images generated during bench testing and some limited clinical image capture, rather than a large dataset for AI/ML validation.

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

   • The document states "The clinical images obtained from the X Sensor and EzSensor XHD were reviewed and rated comparatively."
   • The number of experts and their qualifications are NOT specified. This phrasing suggests a qualitative human review of generated images to ensure diagnostic utility.

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

   • Adjudication method is NOT specified. The review appeared to be a comparative assessment of image quality.

4. 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 discussed. This device is an X-ray sensor, not an AI-assisted diagnostic tool in the sense of an algorithm interpreting images for a human. It provides the images.

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

   • This is NOT applicable. The "device" is the sensor itself, which captures images. There is no mention of an algorithm that performs standalone diagnostic interpretations.

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

   • For the image quality assessment, the "ground truth" seems to be clinical utility/diagnostic adequacy as judged by human review of images generated by both the new device and the predicate device. Quantitative metrics (DQE, MTF, NPS) also served as objective performance measures.

7. The sample size for the training set:

   • NOT applicable/NOT provided. This document describes a medical device, an X-ray sensor, not an AI/ML algorithm that requires a "training set" in the context of machine learning. The "training" for such a device would be its engineering and design optimization.

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

   • NOT applicable/NOT provided. As above, there's no mention of a machine learning training set or associated ground truth.

Summary of Limitations:

The provided document is a regulatory submission for an X-ray sensor. It focuses on demonstrating substantial equivalence to a predicate device based on technical specifications, image quality, and regulatory compliance (electrical safety, EMC, software documentation, cybersecurity). It does not describe an AI/ML diagnostic algorithm or any studies related to its performance, and therefore cannot answer the specific questions posed about AI/ML acceptance criteria and validation.

Ask a specific question about this device

The DUO Sensors are USB driven intraoral sensors which are intended to acquire intraoral radiographic images. The DUO Sensors shall be operated by trained healthcare professionals, who are educated and competent to perform the acquisition of intraoral radiographs.

The DUO Sensors can be used either in combination with special positioning devices to facilitate positioning and alignment with the X-ray beam or they may also be positioned by hand with the assistance of the patient.

The DUO sensors are intended for any dental practice that uses X-ray equipment for intraoral diagnostic purposes. DUO sensors can be used by trained dental professionals for patients receiving intraoral X-ray examinations and procedures for capturing digital X-ray images. Captured digital X-ray images can be used for examinations and diagnostic purposes with the help of optional image analysis software. The optional image analysis software is not part of this submission. DUO sensors can be used with dental positioning devices and holders to assist with aligning an X-ray source beam with the sensor and anatomy.

The DUO sensors are USB-driven digital X-ray sensors designed for health care professionals who are already acquainted with the standard procedures for acquiring dental intraoral radiographs. Digital X-ray imaging is an aide for diagnosis and should always be confirmed by the doctor using appropriate additional diagnostic aides, professional judgment, and experience.

The DUO Sensors are indirect converting X-ray detectors. A scintillating material converts the incident Xrays into visible light, this light is coupled optically to a CMOS technology light detection imager, and then converted to digital data.

The design of the sensor assembly supports the automatic detection of incident X-rays to generate digital images for intraoral applications, once armed via a software command. The digital image created is immediately visible on the screen of a personal computer connected to the DUO sensor through the standard USB port. For DUO sensors to be used in a dental practice, an optional image analysis software will be necessary. Image analysis software is not part of the submission. DUO captured X-ray images are suitable for recognition of normal anatomical structures, dental pathologies, and abnormal conditions.

The DUO sensors support USB2.0 connectivity to computers using a dedicated electronic assembly and a sensor software driver. Functions of the DUO sensors are controlled by software drivers and utilities support sensor activation and settings.

The DUO sensors are manufactured with the same device firmware as the predicate device, Brasseler GEM.

This submission describes a dental digital X-ray sensor, DUO1 and DUO2, which is substantially equivalent to the predicate device, Brasseler GEM.

Here's the breakdown of the acceptance criteria and supporting study details:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA submission for K241649 is a 510(k) premarket notification, which relies on demonstrating substantial equivalence to a legally marketed predicate device rather than setting specific quantifiable acceptance criteria for novel claims. Therefore, the "acceptance criteria" here refer to demonstrating comparable performance to the predicate device (Brasseler GEM) for key technical aspects.

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

• Test Set Description: The document refers to "clinical images captured with both the devices in a performance testing report which were evaluated by US dentists."
• Sample Size: The exact number of patients or images in the clinical performance test set is not specified in the provided text.
• Data Provenance: The images were evaluated by "US dentists." It is not explicitly stated whether the data was retrospective or prospective. Given the clinical image evaluation, it suggests real-world acquisition but the exact study design (e.g., controlled prospective collection vs. retrospective existing images) is not detailed.

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

• Number of Experts: The document states that the clinical images "...were evaluated by US dentists." The exact number of dentists is not specified.
• Qualifications of Experts: The experts are described as "US dentists." Specific qualifications such as years of experience, subspecialty (e.g., board-certified oral and maxillofacial radiologists), or academic affiliations are not provided.

4. Adjudication Method for the Test Set

• Adjudication Method: The document only states that images "were evaluated by US dentists." It does not describe any specific adjudication method (e.g., 2+1, 3+1 consensus, independent reads with no consensus).

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

• A formal MRMC comparative effectiveness study that quantifies improvements in human reader performance (e.g., AUC, sensitivity, specificity) with AI versus without AI assistance was not performed or described. The clinical performance testing involved dentists evaluating images from both devices, implying a comparative visual assessment, but not a controlled MRMC study in the context of AI assistance. The device itself is an intraoral sensor, not an AI diagnostic tool.

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

• This device (DUO sensors) is a hardware component for acquiring images, not an AI algorithm for image analysis. Therefore, a standalone algorithm performance study is not applicable in the traditional sense. The submission states, "Image analysis software is not part of the submission" and "The optional image analysis software is not part of this submission."

7. Type of Ground Truth Used

• For the clinical performance testing, the ground truth was based on the visual evaluation and judgment of US dentists comparing images from DUO sensors to those from the predicate Brasseler GEM. This can be considered a form of expert consensus/reader judgment on image quality and diagnostic utility, but specific "ground truth" for disease presence/absence (like pathology or outcomes data) is not explicitly detailed as this is not an AI diagnostic device. The statement "DUO captured X-ray images are suitable for recognition of normal anatomical structures, dental pathologies, and abnormal conditions" implies the images were assessed for their ability to show such features.

8. Sample Size for the Training Set

• The provided text does not mention a training set for the DUO sensors. As this is a hardware device (sensor) and not an AI diagnostic algorithm, a "training set" in the context of machine learning is not applicable here. The device uses established CMOS and scintillator technologies and is compared against a predicate device.

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

• Since there is no mention of a training set for an AI algorithm, the concept of establishing ground truth for a training set is not applicable to this submission.

Ask a specific question about this device

The RAYSCAN a- P, SC, OCL, OCS panoramic X-ray imaging system with Cephalostat is an extra-oral source X-ray system, intended for dental radiographic examination of the teeth, jaw, and oral structures, to include panoramic examinations and implantology and for TMJ studies and cephalometry. Images are obtained using the standard narrow beam technique.

RAYSCAN α-Expert (RAYSCAN α-P, SC, OCL, OCS) provides panoramic for scanning teeth, jaw and oral structures. By rotating the C-arm, which houses a high-voltage generator, an all-in-one Xray tube and a detector on each end, panoramic images of oral and maxillofacial structures are obtained byrecombining data scanned from different angles. Functionalities include panoramic image scanning for obtaining images of whole teeth, and a Cephalometric scanning option for obtaining Cephalic images.

The provided text describes a 510(k) premarket notification for the "RAYSAN α-Expert" dental X-ray system. The submission affirms its substantial equivalence to a predicate device, K142058. While it outlines several tests conducted to support this claim, it does not provide explicit acceptance criteria in a table format nor does it detail a specific study with quantitative performance metrics for a direct comparison against such criteria.

Here's a breakdown of the information that can be extracted, and where there are gaps regarding the requested specifics:

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

The document does not provide a table of acceptance criteria with corresponding device performance metrics. Instead, it states that "All test results were satisfactory" for performance (imaging performance) testing conducted according to IEC 61223-3-4. It also mentions that "a licensed practitioner reviewed the sample clinical images and deemed them to be of acceptable quality for the intended use." This indicates a subjective assessment of image quality rather than quantitative performance against defined acceptance criteria.

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: The document mentions that "images were gathered from all detectors of RAYSCAN α-Expert using protocols with random patient age, gender, and size" and that "Clinical imaging samples were collected from new detectors on the proposed device at the two offices where the predicate device was installed for the clinical test images." However, it does not specify the exact number of images or patients in the clinical test set.
• Data Provenance: The images were collected "at the two offices where the predicate device was installed for the clinical test images." The manufacturer is Ray Co., Ltd. located in South Korea. It's implied these are prospective clinical images gathered for the purpose of the submission.

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)

• Number of Experts: "The clinical performance of RAYSCAN α-Expert were clinically tested and approved by two licensed practitioners/clinicians."
• Qualifications of Experts: They are described as "licensed practitioners/clinicians." No specific details such as years of experience, specialization (e.g., radiologist, dentist), or board certification are provided.

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

The document states, "A licensed practitioner reviewed the sample clinical images and deemed them to be of acceptable quality for the intended use." It implies individual review, but does not specify any formal adjudication method (e.g., whether the two practitioners independently reviewed images and consensus was reached, or if there was a third adjudicator in case of disagreement).

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

• MRMC Study: No MRMC comparative effectiveness study is mentioned. This device is an X-ray imaging system, not an AI-assisted diagnostic tool for humans, so this type of study would not be applicable. The comparison is between the new device's image quality and the image quality of the predicate device.
• Effect Size: Not applicable.

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

This refers to an X-ray imaging device, not an algorithm. Therefore, "standalone (algorithm only)" performance is not applicable. The device's primary function is image acquisition.

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

The ground truth for the clinical image quality assessment appears to be expert opinion/consensus (from two licensed practitioners) regarding whether the images were "of acceptable quality for the intended use." There's no mention of pathology or outcomes data for establishing ground truth.

8. The sample size for the training set

The document mentions software validation, but this X-ray system is not described as an AI/ML device that requires a distinct "training set" in the context of machine learning model development. This question is not directly applicable to the type of device described.

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

As the device is not described as involving an AI/ML model with a training set, this question is not directly applicable. The software mentioned is for saving patient and image data, inquiries, and image generation, and was validated according to FDA guidance for software in medical devices, not specific AI/ML training.

Summary of what is present and what is missing:

• Acceptance Criteria/Performance Table: Not provided in the requested format. General statement of "satisfactory" test results and "acceptable quality."
• Test Set Sample Size & Provenance: Sample size not quantified. Provenance is South Korea, likely prospective.
• Number & Qualification of Experts: Two licensed practitioners/clinicians. No further qualification details.
• Adjudication Method: Not specified.
• MRMC Study: Not applicable.
• Standalone Performance: Not applicable.
• Type of Ground Truth: Expert opinion on image quality.
• Training Set Sample Size: Not applicable (not an AI/ML device in this context).
• Training Set Ground Truth: Not applicable.

Ask a specific question about this device

Digital image scanner of dental is intended to be used for scanning and processing digital images exposed on IP Imaging Plate in dental applications.

Digital image scanner of dental is a dental device that scans IP Imaging plates that have been exposed in place of dental X-ray film and allows the resulting images to be displayed on the screen and stored for later recovery. It will be used by licensed clinicians and authorized technicians for this purpose. The device is an intraoral Plate Scanner, which is designed to read out intraoral Plates of the size S0, S1, S2 and S3. The intraoral plates are put into the mouth of the patient, exposed to X-rays and then are read out with the device. The read-out-process is carried out with 630-645 nm laser. The laser beam is moved across the surface of the plate by an oscillating mirror. The laser beam stimulates the top coating of the plates, which consists of X-rays sensitive material. Depending on the exposed dose, the coating emits different levels of light. These light particles are then requisitioned by an optical sensor (Photo Multiplier tube/ PMT) and transferred into an electrical output signal. This signal is digitalized and is the data for the digital X-ray image. Before the plate is discharged, the remaining data is erased by a LED-PCB. The user chooses which size of plate he must use and prepares the device by inserting the appropriate plate insert into the device. He then exposes the plate and then puts the plate directly into the insert by pushing it out of the light protection envelope. The user closes the light protection over and starts the read-out process. After the read out process the picture is transmitted to the screen, the picture can be viewed, and the IP is erased and ready to use for the next acquisition.

The provided document is a 510(k) summary for a dental image scanner. It describes the device, compares it to a predicate device, and outlines the non-clinical testing performed to demonstrate substantial equivalence. However, it does not contain a detailed study proving the device meets specific acceptance criteria in the way medical imaging AI/CAD performance studies typically do, nor does it refer to a multi-reader multi-case (MRMC) study. The testing described focuses on device performance characteristics rather than diagnostic accuracy with human readers.

Therefore, many of the requested criteria cannot be directly extracted from this document, as they pertain to clinical or human performance studies, which are explicitly stated as "not required for this submission."

Here's the information that can be extracted or inferred, with explanations for what cannot be found:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't present a formal table of general acceptance criteria with performance results in the context of diagnostic accuracy. Instead, it lists technical performance tests and states that the "Imaging standard requirements were met" and "Laser products have passed safety test."

2. Sample size used for the test set and the data provenance

• Sample Size for Test Set: Not specified. The document refers to "image plates test" and "image accuracy and fidelity test," which are laboratory/technical performance tests, not clinical performance tests with a specific patient dataset.
• Data Provenance: Not applicable, as no patient data (images from humans) was used for performance testing (clinical testing was not required). The tests appear to be conducted on the device itself using phantom or test patterns.
• Retrospective/Prospective: Not applicable.

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

• This information is not provided because diagnostic ground truth from expert readers was not established or used, as clinical testing was not required. The "ground truth" for the technical tests would be the known properties of the phantoms/test patterns used.

4. Adjudication method for the test set

• Not applicable, as no expert reading or adjudication of diagnostic findings was involved.

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. The document explicitly states under section 7, "Clinical Testing: Clinical testing was not required for this submission." This type of study would fall under clinical testing.
• Effect Size: Not applicable as no such study was performed.

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

• The device is a hardware scanner, not an AI/CAD algorithm. The "Image Reading and Checking Testing" falls under standalone performance, as it assesses the device's ability to accurately scan and process images. However, this is about the quality of the image output from the scanner, not the diagnostic performance of an AI algorithm on those images.

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

• For the technical performance tests ("Image Reading and Checking Testing"), the ground truth would be established by the known characteristics of the test patterns, phantoms, and calibrated equipment used for measurement. It is not expert consensus, pathology, or outcomes data, as these relate to clinical diagnostic accuracy, which was not assessed.

8. The sample size for the training set

• Not applicable. This device is a scanner, not an AI or machine learning algorithm that requires a training set. The "software verification and validation testing" refers to typical software engineering V&V processes, not machine learning model training.

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

• Not applicable, as there is no training set for this device (it's not an AI/ML algorithm).

Ask a specific question about this device

The DEXIS sensor is a USB- driven digital sensor which is intended to acquire dental intra- oral radiographic images. The DEXIS sensor shall be operated by healthcare professionals, who are educated and competent to perform the acquisition of dental intra-oral radiographs. The DEXIS sensor can be used either in combination with special positioning devices to facilitate positioning and aligmment with the x-ray beam or it may also be positioned by hand with the assistance of the patient.

The DEXIS Sensors are an indirect converting x-ray detector, e.g. incident x-rays are converted by a scintillating material into (visible) light, this light is coupled optically to a light detection imager based on CMOS technology. The design of the sensor assembly supports the automatic detection of the incident x-rays to generate digital images for dental intra oral applications. The DEXIS Sensors support USB2.0 and USB 3.x connectivity to personal computers using a dedicated electronic assembly and a sensor software driver. The software and firmware for the subject device are similar to the software and firmware for the predicate device and both have a Moderate level of concern. The software performs only basic functions of image capture and transfer to a computer. The software does not perform any medical image manipulation such as image enhancements as these are expected to be performed in the dental viewing software(s) used in conjunction with the subject device.

The subject device DEXIS sensor refers to the dental intra-oral detector. The x-ray generator (an essential component for a fullyfunctional dental x-ray system) is not part of the submission.

The provided text is a 510(k) summary for the DEXIS Ti2 Intraoral Sensor, DEXIS IXS Size 1 Intraoral Sensor, and DEXIS IXS Size 2 Intraoral Sensor.

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with specific numerical targets and corresponding reported device performance values in a side-by-side format. However, it does state an important performance metric:

The document also implies that the device must conform to various international and FDA recognized consensus standards for medical electrical equipment, electromagnetic disturbances, usability, biological evaluation, risk management, and evaluation of imaging performance of dental X-ray. The conclusion states that non-clinical performance bench testing was conducted to determine conformance to these standards, implying successful adherence without providing specific numerical thresholds for each.

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

The document explicitly states: "Clinical data is not needed to characterize performance and establish substantial equivalence. The non-clinical test data characterize all performance aspects of the device based on well-established scientific and engineering principles. Clinical testing has not been conducted on this product."

Therefore, there was no clinical test set, sample size, or data provenance (country of origin, retrospective/prospective) for a study involving patients or real-world clinical data. The evaluation was based on non-clinical bench testing.

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

Since no clinical testing was performed, the concept of "ground truth" established by experts in the context of interpreting medical images from a test set does not apply. The performance was evaluated against technical specifications and standards using bench tests.

4. Adjudication Method for the Test Set

Not applicable, as no clinical test set was used that would require adjudication of expert interpretations.

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

No MRMC study was conducted. The document explicitly states that clinical testing has not been conducted. This means there is no data on how human readers might improve with or without AI assistance, as the device is a dental intraoral sensor, not an AI-powered diagnostic tool for interpretation.

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

Not applicable in the typical sense of an AI algorithm. The device itself is an imaging sensor. The "algorithm" here refers to the internal processing of the sensor to acquire and transfer digital images, not an AI for diagnosis. The performance evaluation was of the sensor's technical capabilities (e.g., resolution, MTF).

7. Type of Ground Truth Used

For the non-clinical bench testing, the "ground truth" would be the known physical properties and characteristics being measured, as defined by the standards and specifications. For instance, the X-ray resolution was measured against a known standard or ideal resolution target.

8. Sample Size for the Training Set

Not applicable. The DEXIS sensor is a hardware device for acquiring images and is not an AI algorithm that undergoes a "training" phase with a dataset.

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

Not applicable, as there was no training set for an AI algorithm.

Ask a specific question about this device

The Digital Wireless Intraoral X-Ray Sensor (Pluto0002XW) is used in conjunction with dental Radiography in medical units. The product is used for dental X-ray examination and the diagnosis of structural diseases. The product is expected to be used in hospitals and clinics, operated and used by trained professionals under the guidance of doctors. This device is not intended for mammography and conventional photography applications.

This device is suitable for providing dental radiography imaging for both adult and pediatric.

The Pluto0002XW Digital Wireless Intraoral X-Ray Sensor (Hereinafter referred to as Pluto0002XW) contains the digital intra-oral sensor. It features a 20um pixel pitch CMOS sensor with directly deposited CsI:Tl scintillator which ensures optimal resolution.

The major function of the Pluto0002XW is to convert the X-ray to digital image, with the application of high resolution X-ray imaging. Pluto0002XW is the key component of intra-oral DR system, enables to complete the digitalization of the medical X-ray imaging with the intra-oral DR system software.

The iRay intra-oral software (iRayDR) is part of the system, it is used to acquire, enhance, analyze, view and share images from the sensor.

This FDA document, K230998, is a 510(k) summary for a Digital Wireless Intraoral X-Ray Sensor. It focuses on demonstrating substantial equivalence to a predicate device rather than detailing extensive performance studies against specific acceptance criteria for diagnostic efficacy. Therefore, much of the requested information regarding "acceptance criteria" and "study that proves the device meets the acceptance criteria" in terms of clinical performance and AI-assistance aspects (e.g., MRMC studies, standalone AI performance) is not present as this device is a hardware component (X-ray sensor) and not an AI/ML-driven diagnostic software.

However, based on the provided text, we can glean information about the non-clinical studies performed to demonstrate safety and effectiveness for substantial equivalence.

Here's an attempt to answer your questions based solely on the provided text:

Acceptance Criteria and Device Performance (Non-Clinical)

The document does not present a table of acceptance criteria for diagnostic performance (e.g., sensitivity, specificity, accuracy) as it's not a diagnostic AI device or a comparative clinical study for human interpretation. Instead, the "acceptance criteria" can be inferred from the standards the device was tested against for safety, electromagnetic compatibility (EMC), wireless functionality, cybersecurity, and biocompatibility. The "reported device performance" is simply that the device "meet[s] the standard requirements" for these tests.

No explicit quantitative acceptance criteria or reported performance for diagnostic accuracy, sensitivity, or specificity are provided because this device is an imaging sensor, not a diagnostic algorithm that interprets images.

Study Details (Non-Clinical as reported in the 510(k) summary)

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

   Acceptance Criterion (Inferred from Standard Compliance)	Reported Device Performance (Summary Statement)
   Electrical Safety (IEC/ES 60601-1, IEC60601-2-65)	"All test results are meet the standard requirements."
   EMC Testing (IEC 60601-1-2)	"All test results are meet the standard requirements."
   Wireless Functionality & Coexistence (ANSI IEEE C63.27-2017)	"All test results are meet the standard requirements."
   Cybersecurity (Federal Food, Drug, and Cosmetics Act section 524B(b)(2))	"...to provide a reasonable assurance that the subject device with its wireless capabilities are cybersecure."
   Biocompatibility (ISO10993-1)	"the evaluation results and test result assured the safety the same as the predicate device."

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

   • Not applicable for clinical performance data. The document describes non-clinical engineering and safety tests. Thus, "sample size" would refer to the number of devices or test conditions, which are not specified in detail.
   • Data Provenance: Not specified, but generally, these tests are conducted in certified labs (often in the country of manufacture, China in this case, or by accredited third-party labs). The testing is prospective for the purpose of the 510(k) submission.

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

   • Not applicable. This relates to clinical diagnostic interpretation by experts, which is not evaluated for this hardware device.

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

   • Not applicable. This relates to clinical diagnostic interpretation.

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 study was not done. This device is an X-ray sensor, not an AI diagnostic tool. The document does not describe any human reader studies, with or without AI assistance.

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

   • No, a standalone algorithm performance study was not done. This device is hardware.

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

   • Not applicable for clinical diagnostic ground truth. For the non-clinical tests, the "ground truth" is compliance with the specified international and national safety and performance standards (e.g., IEC, ANSI IEEE, ISO).

8. The sample size for the training set:

   • Not applicable. This pertains to AI/ML model training, which is not mentioned for this device.

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

   • Not applicable. This pertains to AI/ML model training, which is not mentioned for this device.

In summary: The provided FDA document (a 510(k) summary) for the Digital Wireless Intraoral X-Ray Sensor focuses on demonstrating substantial equivalence through non-clinical performance and safety testing. It does not contain information related to clinical diagnostic performance, AI performance, or human-reader studies, as the device is a data acquisition component (X-ray sensor), not a diagnostic interpretation tool or AI software.

Ask a specific question about this device

Dental Sensors, models Tuxdeluxe, 6100B-Size 1, and 6101B-Size 2 are intended to collect dental x-ray photons and convert them into electronic impulses that may be stored, viewed, and manipulated for diagnostic use by dentists. This device must only be used in hospital environments, clinics or dental offices by trained and qualified dental personnel, and not used in the oxygen rich environment. This device is suitable for providing dental radiography imaging for both adult and pediatric patients.

This Intraoral Digital Imaging Sensor employs CMOS (Complementary Metal-Oxide-Semiconductor), protective optical fiber and scintillator. This sensor was developed to obtain a high-quality x-ray image from the human mouth and its structures. The acquisition process is made by positioning the sensor inside the mouth, behind the structure you want to perform the exam. The structure must be exposed to an x-ray dose using an external source. Once exposed, the sensor performs a conversion of the x-ray photons into a digital signal and transfers it to a computer through USB connection (Universal Serial Bus). The x-ray generator (an integral part of a complete dental x-ray system) is not part of the device. Device sensor sizes: Size 1: 24.1 x 36.2 x 5.9mm Size 2: 30.5 x 42.8 x 5.7mm. The I/O sensor is compatible with the following cleared software: Xray Vision / XV Capture (XV Web) / Curve / Sota. This software must be purchased separately by the end user.

The provided document is a 510(k) Premarket Notification from the FDA for the Tuxdeluxe Intraoral Dental Digital Imaging Sensor. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed acceptance criteria study for an AI/CAD system. Therefore, I cannot generate the specific information requested about acceptance criteria and a study proving a device meets them in the context of an AI/CAD system.

The document discusses the physical characteristics and general performance of the dental sensor, comparing it to an already cleared predicate device (NanoPix). The "study" mentioned for this device is primarily non-clinical testing to ensure safety, EMC, biocompatibility, and general performance, and an image quality analysis by a dentist. There is no mention of an AI algorithm or a comparative effectiveness study involving human readers with and without AI assistance.

Here's how to break down why the requested information cannot be fully provided based on the document:

• The Device: The Tuxdeluxe is a dental imaging sensor (hardware), not an AI/CAD software or system. It collects X-ray photons and converts them into electronic impulses for viewing. It does not perform diagnostic algorithms or AI-driven analysis.
• The Goal of the Submission: The 510(k) submission aims to prove "substantial equivalence" to a predicate device. This is a common regulatory pathway for medical devices that are similar in technology and intended use to devices already on the market. It does not require a full clinical trial to prove efficacy in the same way a novel drug or a high-risk AI algorithm might.
• "Acceptance Criteria" for this device: For this hardware device, acceptance criteria revolve around technical specifications (pixel size, line pairs/mm, DQE, operating temperature, etc.), safety standards (IEC 60601-1, EMC, usability), and basic image quality deemed suitable for diagnostic use by a qualified professional. They are not about the performance of an AI algorithm (e.g., sensitivity, specificity for detecting a disease).

However, I can extract the relevant information that is present and explain why other requested information is absent:

Acceptance Criteria and Device Performance (Based on "Comparison with predicate device" and "Non-clinical Testing")

Information Not Applicable or Not Provided in the Document (due to the nature of the device and submission type):

2. Sample size used for the test set and the data provenance: This refers to the number of images/cases used in a study evaluating a diagnostic algorithm. For this hardware device, there wasn't a "test set" of images in that sense for an algorithmic performance evaluation. The "image quality analysis" by the dentist is mentioned, but the number of images reviewed or their provenance is not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Ground truth establishment (often by multiple experts) is for diagnostic algorithm studies. Here, a "USA Board Certified Dentist" reviewed images for general clinical acceptability, but not to establish ground truth for an AI system.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable for this type of hardware device submission.
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: Not applicable. This is a hardware device, not an AI/CAD system designed to assist human readers. The document explicitly states "Clinical testing is not required for a finding of substantial equivalence."
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. There is no diagnostic algorithm in this device.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable as there's no diagnostic algorithm performance being evaluated against a ground truth. The "image quality analysis" by a single dentist is simply to confirm the images produced are acceptable.
8. The sample size for the training set: Not applicable. This is a hardware device, not a machine learning model requiring a training set.
9. How the ground truth for the training set was established: Not applicable for the same reason as above.

In summary, the provided document describes the regulatory approval of a dental imaging hardware device based on substantial equivalence to an existing predicate. It does not provide details about an AI/CAD system's acceptance criteria or performance study, as such studies would be required for AI-driven diagnostic software.

Ask a specific question about this device

The WeSensor is used for a radiographic examination by a dental professional to assist in the diagnosing of diseases of the teeth, jaw and oral structures.

The WeSensor is an intraoral digital x-ray sensor. It comprises three components: (1) an intraoral digital X-ray sensor which connects to a PC via a USB port; (2) WeSensor Software package; and (3) a sensor holder as an accessory.

The provided text describes the WeSensor, an intraoral digital X-ray sensor, and its clearance by the FDA based on substantial equivalence to predicate devices. The document contains information relevant to performance data and comparison with predicate devices, but it does not contain a detailed formal study report with specific acceptance criteria and detailed performance of the WeSensor against those criteria.

However, it does state "The successful test results including max.image resolution, DQE, and MTF indicate that the subject device performance is comparable to or exceed those of the predicate devices." and "clinical images were examined by Dr.Park, a qualified dentist in the state of Nevada. The results demonstrated no significant difference in diagnosing dental diseases between the subject device and the predicate device."

Based on the information available, here's an attempt to structure the answer, acknowledging the limitations for certain points where specific details are not provided:

Acceptance Criteria and Device Performance (Inferred from Predicate Comparison)

The document primarily relies on "substantial equivalence" to predicate devices rather than pre-defined acceptance criteria based on numerical thresholds. The acceptance criteria are implicitly met by demonstrating that the WeSensor's performance characteristics are "comparable to or exceed" those of the predicate devices.

Table of Performance Characteristics (Implied Acceptance Criteria = Comparable/Exceed Predicate)

Study Details

1. Sample Size and Data Provenance for Test Set:

   • Sample Size: The document does not explicitly state the sample size used for the clinical image examination or the performance testing (max. image resolution, DQE, MTF).
   • Data Provenance: The document states that "clinical images were examined by Dr. Park, a qualified dentist in the state of Nevada." This suggests the clinical images were likely generated prospectively or collected for this specific evaluation, and the data provenance is the USA (Nevada). It does not specify if the images were retrospective or prospective, only that they "were examined." The technical performance tests (DQE, MTF, resolution) are laboratory-based, not patient-data based.

2. Number of Experts and Qualifications for Ground Truth (Test Set):

   • Number of Experts: Only one expert is explicitly mentioned: "Dr. Park, a qualified dentist in the state of Nevada."
   • Qualifications: "qualified dentist in the state of Nevada." No specific years of experience or subspecialty certification (beyond general dentistry) are provided.

3. Adjudication Method for the Test Set:

   • Method: "None" as only one expert ("Dr. Park") is mentioned for the clinical image examination. There is no indication of multiple readers or an adjudication process for clinical ground truth.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • Was it done? No, a formal MRMC study is not described. The clinical evaluation mentioned involves a single dentist's comparison of images for diagnostic equivalence, not an assessment of human reader improvement with or without AI assistance.
   • Effect Size: Not applicable, as an MRMC study was not stated to be performed.

5. Standalone Performance (Algorithm Only):

   • Was it done? The WeSensor is an intraoral digital X-ray sensor, a hardware device that captures images. The "WeSensor Software package" is mentioned, and it performs "acquisition, storage, transmission along with simple editing functions." It does not appear to be an AI algorithm for diagnostic interpretation. Therefore, a standalone algorithm-only performance study (e.g., for AI interpretation) is not relevant or described. The clinical evaluation described evaluates the device's ability to produce images suitable for human diagnosis.

6. Type of Ground Truth Used:

   • For Clinical Images: "Expert consensus" by a single qualified dentist ("Dr. Park") comparing the subject device images to predicate device images for diagnostic equivalence. The document states, "The results demonstrated no significant difference in diagnosing dental diseases between the subject device and the predicate device."
   • For Technical Performance: Physical measurements (e.g., lp/mm, DQE, MTF) are used, which are objective quantitative metrics not requiring human ground truth.

7. Sample Size for Training Set:

   • The document does not describe a "training set" as the WeSensor is a hardware imaging device, not an AI/ML model that requires a data training phase. Its software handles image acquisition and management, not AI-based diagnosis.

8. How Ground Truth for Training Set was Established:

   • Not applicable as there is no mention of an AI/ML component with a training set.

Ask a specific question about this device

EzSensor XHD is intended to collect dental x-ray photons and convert them into electronic impulses that may be stored, viewed and manipulated for diagnostic use by dentists.

EzSensor XHD is a digital intraoral sensor which acquires digital intra-oral images. EzSensor XHD acquires intra oral images with a sensor that is connected to a computer to produce an image almost instantaneously following exposure. The primary advantage of direct sensor systems is the speed with which images are acquired. The ergonomic design based on human intraoral anatomy improves patient comfort. EzSensor XHD includes the software (firmware) with MODERATE level of concern.

The provided text is a 510(k) summary for the EzSensor XHD, a digital dental intraoral sensor. It aims to demonstrate substantial equivalence to a predicate device, not necessarily to prove the device meets specific acceptance criteria for a new, unproven technology. Therefore, the traditional concept of "acceptance criteria" and a "study that proves the device meets the acceptance criteria" in the context of a clinical trial with specific performance thresholds is not directly applicable in the way one might expect for a novel AI device.

Instead, the document focuses on demonstrating substantial equivalence to an already legally marketed predicate device (EzSensor Soft, EzSensor Soft i, EzSensor Bio, EzSensor Bio I, Model: 1.0, 1.5, 2.0; K151707). This is achieved by showing that the proposed device has the same indications for use and similar technological characteristics, and that any differences do not raise new questions of safety or effectiveness.

However, we can extract performance specifications and comparative data presented as part of the substantial equivalence claim.

Here's an attempt to structure the information based on your requested format, interpreting "acceptance criteria" as the performance metrics deemed acceptable for demonstrating substantial equivalence to the predicate device, and "study" as the non-clinical and comparative evaluations conducted.

Device Name: EzSensor XHD
Regulatory Product Code: MUH (Extraoral source X-ray system)

Interpretation of "Acceptance Criteria" in the Context of 510(k) Substantial Equivalence:

For a 510(k) submission, "acceptance criteria" are not explicitly defined as pass/fail thresholds against a clinical endpoint for a novel diagnostic. Instead, the "acceptance" is the FDA's determination of substantial equivalence to a predicate device. This is achieved by demonstrating that the new device is as safe and effective as the predicate device. The performance comparisons below serve as the data points to support this claim, rather than a direct set of pre-defined "acceptance criteria" for clinical accuracy or efficacy.

1. Table of Acceptance Criteria (Interpreted as Performance Metrics for Substantial Equivalence) and Reported Device Performance

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

The document describes non-clinical bench testing and a comparative review of clinical images.

• Non-clinical (Bench) Test Set: No specific sample size is given for the non-clinical tests (DQE, MTF, NPS, Electrical, Mechanical, Environmental, EMC). These tests are typically performed on a limited number of manufactured devices/prototypes.
• Clinical Image Test Set: The text states, "The clinical images obtained from the EzSsensor XHD and EzSensor Soft were reviewed and rated comparatively." No specific number of images or patients (sample size) is provided for this comparative review.
• Data Provenance: Not explicitly stated, but assumed to be from a controlled in-house setting given the nature of a 510(k) submission primarily relying on bench testing and limited comparative review. The studies are prospective in the sense that they were conducted specifically for this submission, although the images themselves could be from previous patient encounters (retrospective collection).

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

• The document mentions a "comparative review" of clinical images but does not specify the number or qualifications of experts who performed this review or established any form of ground truth for the clinical image set. It simply states the images were "reviewed and rated comparatively" and that "EzSensor XHD produces overall better definition and grayscale of bony and soft tissue images in comparison with EzSensor Soft."

4. Adjudication Method (for the Test Set)

• No adjudication method is described. The comparative review appears to be a qualitative assessment, not a formal quantitative study requiring adjudication of expert readings against a ground truth.

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

• No MRMC comparative effectiveness study was done as described in the provided text. The evaluation was a qualitative comparison of image quality, not a study of human readers' performance with and without AI assistance. The device itself is an imaging sensor, not an AI-assisted diagnostic tool.

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

• This question is not applicable in the context of this device. The EzSensor XHD is a hardware imaging sensor that collects X-ray photons and converts them to digital images for diagnostic use by dentists. It does not perform an algorithm-only diagnostic task without human interpretation. It is a data acquisition device, not a diagnostic AI.

7. Type of Ground Truth Used

• For the non-clinical performance metrics (DQE, MTF, NPS), the "ground truth" is established by physical measurements and standardized testing protocols performed according to FDA guidance and international standards (e.g., "Guidance for the Submissions of 510(k)'s for Solid State X-ray Imaging Devices").
• For the comparative clinical image review, the "ground truth" is implied to be the expert visual assessment of image quality enabling diagnostic use, compared to an accepted predicate device. There is no mention of pathology, clinical outcomes data, or a multi-expert consensus process for a defined "ground truth" in the sense of disease presence/absence.

8. Sample Size for the Training Set

• The EzSensor XHD is a digital imaging sensor, not an AI/machine learning algorithm that requires a "training set" of data in the typical sense. Therefore, there is no training set as would be understood for an AI device. The device's performance is determined by its physical and electronic design and manufacturing, not by learning from a dataset.

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

• Not applicable, as there is no training set for this hardware device.

Ask a specific question about this device